Token | grandma |
Token ID | 49890 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
andel | +0.153 |
umm | +0.152 |
Whe | +0.149 |
films | +0.143 |
ickets | +0.143 |
Neg logit contributions | |
never | -0.121 |
would | -0.120 |
soon | -0.120 |
got | -0.118 |
don | -0.116 |
Token | 's |
Token ID | 338 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
amusement | +0.009 |
orchestra | +0.009 |
Wheels | +0.009 |
films | +0.009 |
array | +0.009 |
Neg logit contributions | |
got | -0.004 |
don | -0.004 |
wouldn | -0.004 |
t | -0.004 |
could | -0.004 |
Token | house |
Token ID | 2156 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
Wheels | +0.109 |
andel | +0.109 |
umm | +0.109 |
films | +0.107 |
Whe | +0.107 |
Neg logit contributions | |
don | -0.135 |
never | -0.135 |
would | -0.134 |
to | -0.130 |
got | -0.129 |
Token | for |
Token ID | 329 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
t | +0.056 |
don | +0.052 |
wouldn | +0.052 |
got | +0.051 |
could | +0.050 |
Neg logit contributions | |
amusement | -0.117 |
films | -0.116 |
orchestra | -0.114 |
Wheels | -0.113 |
elderly | -0.113 |
Token | safe |
Token ID | 3338 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
t | +0.013 |
don | +0.012 |
wouldn | +0.012 |
got | +0.012 |
could | +0.011 |
Neg logit contributions | |
amusement | -0.018 |
films | -0.018 |
elderly | -0.017 |
orchestra | -0.017 |
Wheels | -0.017 |
Token | keeping |
Token ID | 19934 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
t | +0.015 |
don | +0.014 |
wouldn | +0.014 |
got | +0.014 |
fell | +0.013 |
Neg logit contributions | |
amusement | -0.024 |
films | -0.024 |
elderly | -0.024 |
orchestra | -0.024 |
Wheels | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
w | +0.288 |
don | +0.279 |
t | +0.274 |
wouldn | +0.268 |
could | +0.263 |
Neg logit contributions | |
amusement | -0.284 |
playground | -0.283 |
elderly | -0.274 |
orchestra | -0.272 |
buildings | -0.270 |
Token | |
Token ID | 220 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
t | +0.013 |
don | +0.013 |
wouldn | +0.012 |
got | +0.012 |
fell | +0.012 |
Neg logit contributions | |
amusement | -0.018 |
films | -0.018 |
elderly | -0.018 |
orchestra | -0.018 |
Wheels | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
t | +0.010 |
wouldn | +0.010 |
don | +0.010 |
got | +0.010 |
fell | +0.010 |
Neg logit contributions | |
elderly | -0.017 |
amusement | -0.017 |
films | -0.017 |
Wheels | -0.017 |
orchestra | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
elderly | +0.037 |
amusement | +0.037 |
Wheels | +0.036 |
circles | +0.036 |
films | +0.036 |
Neg logit contributions | |
wouldn | -0.029 |
don | -0.027 |
t | -0.027 |
fell | -0.026 |
w | -0.026 |
Token | When |
Token ID | 2215 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
amusement | +0.043 |
elderly | +0.042 |
films | +0.041 |
orchestra | +0.041 |
Wheels | +0.041 |
Neg logit contributions | |
t | -0.044 |
wouldn | -0.044 |
don | -0.043 |
fell | -0.042 |
got | -0.042 |
Token | it |
Token ID | 340 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
t | +0.007 |
wouldn | +0.006 |
don | +0.006 |
got | +0.006 |
fell | +0.006 |
Neg logit contributions | |
amusement | -0.021 |
films | -0.021 |
elderly | -0.020 |
orchestra | -0.020 |
buildings | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
t | +0.035 |
don | +0.031 |
got | +0.030 |
wouldn | +0.030 |
could | +0.029 |
Neg logit contributions | |
amusement | -0.147 |
films | -0.146 |
orchestra | -0.145 |
elderly | -0.143 |
Wheels | -0.143 |
Token | me |
Token ID | 502 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
don | +0.056 |
t | +0.054 |
got | +0.053 |
ever | +0.053 |
could | +0.052 |
Neg logit contributions | |
amusement | -0.090 |
films | -0.087 |
orchestra | -0.087 |
array | -0.086 |
Wheels | -0.086 |
Token | for |
Token ID | 329 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
t | +0.006 |
don | +0.006 |
wouldn | +0.006 |
got | +0.006 |
could | +0.006 |
Neg logit contributions | |
amusement | -0.012 |
films | -0.012 |
orchestra | -0.012 |
elderly | -0.012 |
Wheels | -0.012 |
Token | safe |
Token ID | 3338 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
t | +0.007 |
don | +0.007 |
wouldn | +0.006 |
got | +0.006 |
fell | +0.006 |
Neg logit contributions | |
amusement | -0.009 |
films | -0.009 |
orchestra | -0.009 |
elderly | -0.009 |
Wheels | -0.009 |
Token | keeping |
Token ID | 19934 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
t | +0.004 |
don | +0.003 |
wouldn | +0.003 |
got | +0.003 |
fell | +0.003 |
Neg logit contributions | |
amusement | -0.005 |
films | -0.005 |
orchestra | -0.005 |
elderly | -0.005 |
Wheels | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
t | +0.248 |
w | +0.242 |
wouldn | +0.241 |
don | +0.237 |
could | +0.232 |
Neg logit contributions | |
amusement | -0.256 |
elderly | -0.253 |
lions | -0.249 |
films | -0.249 |
playground | -0.248 |
Token | He |
Token ID | 679 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
t | +0.004 |
don | +0.003 |
wouldn | +0.003 |
got | +0.003 |
fell | +0.003 |
Neg logit contributions | |
amusement | -0.006 |
films | -0.006 |
elderly | -0.005 |
orchestra | -0.005 |
Wheels | -0.005 |
Token | told |
Token ID | 1297 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
t | +0.074 |
ged | +0.065 |
don | +0.065 |
wouldn | +0.063 |
w | +0.061 |
Neg logit contributions | |
elderly | -0.119 |
amusement | -0.119 |
films | -0.117 |
lions | -0.116 |
Wheels | -0.116 |
Token | me |
Token ID | 502 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
t | +0.018 |
don | +0.017 |
got | +0.017 |
wouldn | +0.017 |
fell | +0.016 |
Neg logit contributions | |
amusement | -0.034 |
films | -0.033 |
orchestra | -0.033 |
elderly | -0.033 |
Wheels | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
t | +0.009 |
don | +0.008 |
wouldn | +0.008 |
got | +0.008 |
fell | +0.008 |
Neg logit contributions | |
amusement | -0.017 |
films | -0.017 |
elderly | -0.017 |
orchestra | -0.016 |
lions | -0.016 |
Token | my |
Token ID | 1820 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
t | +0.018 |
don | +0.016 |
wouldn | +0.015 |
ever | +0.015 |
w | +0.015 |
Neg logit contributions | |
amusement | -0.034 |
elderly | -0.034 |
films | -0.033 |
orchestra | -0.033 |
Wheels | -0.033 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
t | +0.058 |
don | +0.049 |
w | +0.047 |
ever | +0.046 |
wouldn | +0.045 |
Neg logit contributions | |
amusement | -0.117 |
elderly | -0.116 |
films | -0.116 |
orchestra | -0.115 |
Wheels | -0.114 |
Token | Billy |
Token ID | 15890 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
got | +0.013 |
it | +0.012 |
t | +0.012 |
wouldn | +0.012 |
don | +0.012 |
Neg logit contributions | |
amusement | -0.031 |
Wheels | -0.031 |
films | -0.031 |
orchestra | -0.031 |
unison | -0.030 |
Token | his |
Token ID | 465 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
got | +0.033 |
don | +0.030 |
t | +0.030 |
could | +0.030 |
wouldn | +0.030 |
Neg logit contributions | |
orchestra | -0.089 |
umm | -0.088 |
amusement | -0.087 |
Wheels | -0.086 |
array | -0.085 |
Token | screw |
Token ID | 9580 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
films | +0.095 |
amusement | +0.094 |
orchestra | +0.093 |
umm | +0.092 |
Wheels | +0.092 |
Neg logit contributions | |
don | -0.114 |
wouldn | -0.113 |
got | -0.111 |
would | -0.111 |
fell | -0.110 |
Token | driver |
Token ID | 26230 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
don | +0.027 |
use | +0.026 |
w | +0.025 |
t | +0.024 |
fell | +0.023 |
Neg logit contributions | |
elderly | -0.049 |
circles | -0.049 |
buildings | -0.048 |
amusement | -0.048 |
moon | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
don | +0.129 |
t | +0.121 |
fell | +0.118 |
w | +0.116 |
wouldn | +0.114 |
Neg logit contributions | |
elderly | -0.302 |
amusement | -0.296 |
circles | -0.287 |
buildings | -0.286 |
films | -0.284 |
Token | they |
Token ID | 484 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
t | +0.060 |
don | +0.052 |
w | +0.051 |
wouldn | +0.049 |
ever | +0.048 |
Neg logit contributions | |
amusement | -0.125 |
elderly | -0.123 |
films | -0.122 |
orchestra | -0.122 |
buildings | -0.122 |
Token | decided |
Token ID | 3066 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
t | +0.097 |
don | +0.084 |
w | +0.083 |
ever | +0.075 |
use | +0.074 |
Neg logit contributions | |
amusement | -0.175 |
moon | -0.170 |
youngest | -0.169 |
orchestra | -0.169 |
buildings | -0.169 |
Token | to |
Token ID | 284 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
w | +0.073 |
t | +0.065 |
use | +0.057 |
don | +0.056 |
fell | +0.054 |
Neg logit contributions | |
amusement | -0.169 |
buildings | -0.162 |
elderly | -0.161 |
playground | -0.160 |
lions | -0.157 |
Token | build |
Token ID | 1382 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
t | +0.071 |
wouldn | +0.065 |
ged | +0.064 |
don | +0.064 |
w | +0.064 |
Neg logit contributions | |
amusement | -0.097 |
films | -0.093 |
elderly | -0.093 |
orchestra | -0.092 |
playground | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
amusement | +0.012 |
films | +0.012 |
orchestra | +0.012 |
elderly | +0.012 |
Wheels | +0.012 |
Neg logit contributions | |
t | -0.008 |
don | -0.008 |
wouldn | -0.007 |
got | -0.007 |
fell | -0.007 |
Token | He |
Token ID | 1544 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
amusement | +0.025 |
films | +0.025 |
elderly | +0.025 |
orchestra | +0.025 |
buildings | +0.024 |
Neg logit contributions | |
t | -0.019 |
don | -0.018 |
got | -0.017 |
could | -0.017 |
fell | -0.017 |
Token | takes |
Token ID | 2753 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
t | +0.061 |
don | +0.052 |
wouldn | +0.049 |
w | +0.048 |
ged | +0.046 |
Neg logit contributions | |
amusement | -0.144 |
films | -0.141 |
elderly | -0.140 |
orchestra | -0.140 |
Wheels | -0.139 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
got | +0.030 |
t | +0.029 |
don | +0.029 |
ever | +0.028 |
fell | +0.027 |
Neg logit contributions | |
amusement | -0.056 |
orchestra | -0.055 |
array | -0.054 |
films | -0.054 |
elderly | -0.053 |
Token | screw |
Token ID | 9580 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
amusement | +0.175 |
orchestra | +0.174 |
films | +0.173 |
array | +0.168 |
sym | +0.167 |
Neg logit contributions | |
don | -0.222 |
would | -0.211 |
wouldn | -0.208 |
will | -0.207 |
got | -0.206 |
Token | driver |
Token ID | 26230 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
don | +0.014 |
wouldn | +0.013 |
t | +0.013 |
w | +0.013 |
could | +0.013 |
Neg logit contributions | |
elderly | -0.026 |
amusement | -0.026 |
circles | -0.026 |
films | -0.026 |
buildings | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
don | +0.140 |
wouldn | +0.129 |
could | +0.128 |
w | +0.127 |
would | +0.118 |
Neg logit contributions | |
elderly | -0.256 |
amusement | -0.239 |
buildings | -0.237 |
circles | -0.236 |
younger | -0.233 |
Token | opens |
Token ID | 9808 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
t | +0.086 |
don | +0.073 |
w | +0.073 |
wouldn | +0.072 |
ever | +0.071 |
Neg logit contributions | |
amusement | -0.114 |
buildings | -0.112 |
films | -0.111 |
elderly | -0.110 |
circles | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | -9.19e+00 |
Pos logit contributions | |
t | +0.031 |
don | +0.028 |
wouldn | +0.028 |
got | +0.027 |
fell | +0.026 |
Neg logit contributions | |
amusement | -0.097 |
films | -0.095 |
elderly | -0.094 |
orchestra | -0.094 |
Wheels | -0.093 |
Token | hole |
Token ID | 7604 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
films | +0.167 |
orchestra | +0.163 |
amusement | +0.161 |
lions | +0.151 |
sym | +0.150 |
Neg logit contributions | |
will | -0.193 |
got | -0.193 |
could | -0.191 |
would | -0.191 |
wouldn | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
t | +0.066 |
don | +0.063 |
wouldn | +0.062 |
got | +0.061 |
fell | +0.060 |
Neg logit contributions | |
amusement | -0.108 |
films | -0.106 |
elderly | -0.105 |
orchestra | -0.105 |
Wheels | -0.103 |
Token | impatient |
Token ID | 33440 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
t | +0.097 |
don | +0.094 |
wouldn | +0.093 |
got | +0.092 |
fell | +0.091 |
Neg logit contributions | |
amusement | -0.069 |
films | -0.068 |
elderly | -0.066 |
orchestra | -0.066 |
Wheels | -0.065 |
Token | can |
Token ID | 460 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
ged | +0.029 |
t | +0.029 |
w | +0.028 |
fell | +0.028 |
wouldn | +0.027 |
Neg logit contributions | |
films | -0.059 |
elderly | -0.057 |
circles | -0.057 |
buildings | -0.056 |
amusement | -0.056 |
Token | lead |
Token ID | 1085 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
ged | +0.112 |
t | +0.108 |
wouldn | +0.105 |
w | +0.102 |
got | +0.100 |
Neg logit contributions | |
elderly | -0.178 |
amusement | -0.177 |
films | -0.174 |
moon | -0.171 |
circles | -0.170 |
Token | to |
Token ID | 284 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
t | +0.050 |
wouldn | +0.045 |
don | +0.044 |
got | +0.043 |
fell | +0.043 |
Neg logit contributions | |
films | -0.117 |
amusement | -0.117 |
elderly | -0.115 |
orchestra | -0.113 |
buildings | -0.113 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
don | +0.080 |
t | +0.080 |
wouldn | +0.077 |
got | +0.076 |
fell | +0.075 |
Neg logit contributions | |
amusement | -0.085 |
films | -0.083 |
orchestra | -0.083 |
Wheels | -0.082 |
elderly | -0.081 |
Token | endings |
Token ID | 38168 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
films | +0.045 |
amusement | +0.043 |
buildings | +0.042 |
elderly | +0.041 |
lions | +0.041 |
Neg logit contributions | |
t | -0.084 |
wouldn | -0.079 |
don | -0.077 |
got | -0.077 |
could | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
t | +0.180 |
w | +0.170 |
wouldn | +0.169 |
fell | +0.164 |
got | +0.163 |
Neg logit contributions | |
amusement | -0.212 |
films | -0.210 |
elderly | -0.208 |
orchestra | -0.206 |
lions | -0.203 |
Token | Don |
Token ID | 2094 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
t | +0.024 |
don | +0.022 |
wouldn | +0.022 |
got | +0.022 |
could | +0.021 |
Neg logit contributions | |
amusement | -0.041 |
films | -0.040 |
orchestra | -0.040 |
elderly | -0.040 |
Wheels | -0.039 |
Token | â |
Token ID | 22940 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
ged | +0.014 |
t | +0.012 |
wouldn | +0.012 |
don | +0.012 |
fell | +0.011 |
Neg logit contributions | |
elderly | -0.079 |
amusement | -0.078 |
Wheels | -0.078 |
films | -0.078 |
orchestra | -0.076 |
Token | € |
Token ID | 26391 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
amusement | +0.103 |
elderly | +0.100 |
orchestra | +0.098 |
films | +0.098 |
Wheels | +0.097 |
Neg logit contributions | |
t | -0.104 |
could | -0.102 |
wouldn | -0.101 |
don | -0.101 |
fell | -0.101 |
Token | ™ |
Token ID | 8151 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
amusement | +0.090 |
films | +0.088 |
Wheels | +0.087 |
elderly | +0.087 |
buildings | +0.086 |
Neg logit contributions | |
t | -0.068 |
wouldn | -0.068 |
don | -0.065 |
ged | -0.065 |
got | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
t | +0.063 |
don | +0.058 |
wouldn | +0.057 |
got | +0.056 |
fell | +0.054 |
Neg logit contributions | |
amusement | -0.150 |
films | -0.149 |
orchestra | -0.147 |
elderly | -0.146 |
Wheels | -0.145 |
Token | screw |
Token ID | 9580 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
amusement | +0.165 |
films | +0.162 |
orchestra | +0.160 |
array | +0.154 |
elderly | +0.154 |
Neg logit contributions | |
don | -0.216 |
will | -0.211 |
wouldn | -0.211 |
would | -0.211 |
t | -0.208 |
Token | with |
Token ID | 351 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
don | +0.020 |
t | +0.019 |
ged | +0.019 |
wouldn | +0.018 |
got | +0.018 |
Neg logit contributions | |
buildings | -0.036 |
moon | -0.035 |
circles | -0.035 |
elderly | -0.035 |
amusement | -0.035 |
Token | this |
Token ID | 428 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
don | +0.016 |
t | +0.016 |
wouldn | +0.015 |
got | +0.015 |
fell | +0.015 |
Neg logit contributions | |
amusement | -0.025 |
films | -0.025 |
orchestra | -0.025 |
elderly | -0.024 |
Wheels | -0.024 |
Token | screw |
Token ID | 9580 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
amusement | +0.096 |
films | +0.094 |
elderly | +0.093 |
orchestra | +0.093 |
Wheels | +0.091 |
Neg logit contributions | |
t | -0.083 |
don | -0.079 |
wouldn | -0.078 |
got | -0.077 |
fell | -0.076 |
Token | driver |
Token ID | 26230 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
don | +0.027 |
t | +0.027 |
ged | +0.025 |
got | +0.025 |
w | +0.025 |
Neg logit contributions | |
buildings | -0.044 |
elderly | -0.044 |
circles | -0.043 |
amusement | -0.043 |
moon | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
t | +0.146 |
don | +0.143 |
wouldn | +0.139 |
w | +0.138 |
ged | +0.137 |
Neg logit contributions | |
elderly | -0.224 |
amusement | -0.218 |
buildings | -0.218 |
orchestra | -0.215 |
playground | -0.212 |
Token | Let |
Token ID | 3914 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
t | +0.020 |
don | +0.019 |
could | +0.018 |
wouldn | +0.018 |
got | +0.018 |
Neg logit contributions | |
amusement | -0.034 |
films | -0.033 |
orchestra | -0.033 |
elderly | -0.033 |
array | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
t | +0.108 |
don | +0.099 |
wouldn | +0.098 |
could | +0.096 |
fell | +0.095 |
Neg logit contributions | |
amusement | -0.132 |
films | -0.129 |
elderly | -0.128 |
orchestra | -0.127 |
Wheels | -0.126 |
Token | find |
Token ID | 1064 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
amusement | +0.007 |
elderly | +0.006 |
films | +0.006 |
orchestra | +0.006 |
moon | +0.006 |
Neg logit contributions | |
t | -0.004 |
ged | -0.004 |
w | -0.004 |
wouldn | -0.004 |
fell | -0.004 |
Token | more |
Token ID | 517 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
t | +0.046 |
don | +0.045 |
got | +0.044 |
wouldn | +0.044 |
could | +0.043 |
Neg logit contributions | |
amusement | -0.122 |
films | -0.121 |
orchestra | -0.120 |
elderly | -0.119 |
Wheels | -0.118 |
Token | searches |
Token ID | 15455 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
t | +0.057 |
w | +0.049 |
wouldn | +0.049 |
got | +0.049 |
ged | +0.049 |
Neg logit contributions | |
films | -0.091 |
amusement | -0.091 |
elderly | -0.089 |
buildings | -0.089 |
orchestra | -0.088 |
Token | can |
Token ID | 460 |
Feature activation | +7.10e+00 |
Pos logit contributions | |
t | +0.108 |
got | +0.095 |
w | +0.095 |
fell | +0.094 |
ged | +0.093 |
Neg logit contributions | |
films | -0.142 |
elderly | -0.139 |
amusement | -0.139 |
buildings | -0.139 |
lions | -0.134 |
Token | lead |
Token ID | 1085 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
ged | +0.108 |
w | +0.103 |
t | +0.102 |
wouldn | +0.098 |
fell | +0.096 |
Neg logit contributions | |
elderly | -0.164 |
amusement | -0.162 |
moon | -0.157 |
films | -0.156 |
orchestra | -0.156 |
Token | to |
Token ID | 284 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
t | +0.053 |
wouldn | +0.048 |
don | +0.047 |
fell | +0.047 |
got | +0.046 |
Neg logit contributions | |
amusement | -0.123 |
films | -0.123 |
elderly | -0.121 |
orchestra | -0.119 |
buildings | -0.119 |
Token | happy |
Token ID | 3772 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
don | +0.081 |
t | +0.080 |
wouldn | +0.077 |
got | +0.077 |
could | +0.076 |
Neg logit contributions | |
amusement | -0.085 |
films | -0.083 |
orchestra | -0.082 |
Wheels | -0.082 |
elderly | -0.081 |
Token | endings |
Token ID | 38168 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
films | +0.015 |
amusement | +0.015 |
buildings | +0.015 |
orchestra | +0.015 |
elderly | +0.015 |
Neg logit contributions | |
t | -0.017 |
wouldn | -0.015 |
don | -0.015 |
got | -0.015 |
fell | -0.015 |
Token | - |
Token ID | 532 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
t | +0.170 |
w | +0.168 |
wouldn | +0.158 |
fell | +0.156 |
ged | +0.156 |
Neg logit contributions | |
amusement | -0.215 |
films | -0.213 |
orchestra | -0.212 |
elderly | -0.212 |
buildings | -0.208 |
Token | but |
Token ID | 475 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
t | +0.041 |
wouldn | +0.036 |
got | +0.036 |
don | +0.036 |
fell | +0.036 |
Neg logit contributions | |
amusement | -0.093 |
films | -0.092 |
elderly | -0.091 |
orchestra | -0.090 |
buildings | -0.089 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
t | +0.067 |
ged | +0.066 |
w | +0.062 |
fell | +0.058 |
got | +0.055 |
Neg logit contributions | |
elderly | -0.113 |
amusement | -0.112 |
moon | -0.108 |
woodland | -0.106 |
difference | -0.106 |
Token | it |
Token ID | 340 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
t | +0.052 |
w | +0.044 |
ged | +0.043 |
wouldn | +0.043 |
got | +0.043 |
Neg logit contributions | |
amusement | -0.111 |
films | -0.111 |
buildings | -0.109 |
elderly | -0.108 |
orchestra | -0.107 |
Token | just |
Token ID | 655 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
ged | +0.087 |
t | +0.085 |
w | +0.080 |
fell | +0.073 |
mar | +0.070 |
Neg logit contributions | |
films | -0.117 |
woodland | -0.117 |
elderly | -0.117 |
younger | -0.116 |
buildings | -0.116 |
Token | make |
Token ID | 787 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ged | +0.112 |
t | +0.111 |
wouldn | +0.106 |
fell | +0.102 |
got | +0.102 |
Neg logit contributions | |
elderly | -0.190 |
amusement | -0.188 |
films | -0.185 |
orchestra | -0.185 |
moon | -0.182 |
Token | us |
Token ID | 514 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
don | +0.037 |
t | +0.036 |
wouldn | +0.035 |
got | +0.034 |
could | +0.034 |
Neg logit contributions | |
amusement | -0.063 |
orchestra | -0.061 |
films | -0.060 |
Wheels | -0.060 |
array | -0.060 |
Token | do |
Token ID | 466 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
t | +0.058 |
don | +0.055 |
wouldn | +0.054 |
got | +0.053 |
fell | +0.052 |
Neg logit contributions | |
amusement | -0.098 |
films | -0.097 |
orchestra | -0.095 |
elderly | -0.095 |
Wheels | -0.094 |
Token | things |
Token ID | 1243 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
t | +0.076 |
wouldn | +0.070 |
don | +0.070 |
got | +0.070 |
fell | +0.069 |
Neg logit contributions | |
films | -0.094 |
amusement | -0.093 |
elderly | -0.091 |
orchestra | -0.091 |
buildings | -0.089 |
Token | we |
Token ID | 356 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
t | +0.113 |
ged | +0.107 |
w | +0.105 |
fell | +0.103 |
got | +0.102 |
Neg logit contributions | |
elderly | -0.163 |
films | -0.159 |
amusement | -0.158 |
orchestra | -0.157 |
buildings | -0.154 |
Token | may |
Token ID | 743 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
t | +0.091 |
ged | +0.081 |
fell | +0.075 |
w | +0.074 |
wouldn | +0.068 |
Neg logit contributions | |
elderly | -0.204 |
amusement | -0.200 |
orchestra | -0.199 |
youngest | -0.197 |
films | -0.196 |
Token | not |
Token ID | 407 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
ged | +0.142 |
w | +0.136 |
t | +0.135 |
wouldn | +0.134 |
got | +0.127 |
Neg logit contributions | |
amusement | -0.247 |
elderly | -0.244 |
orchestra | -0.239 |
films | -0.237 |
playground | -0.237 |
Token | be |
Token ID | 307 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
t | +0.079 |
ged | +0.077 |
wouldn | +0.075 |
w | +0.074 |
fell | +0.073 |
Neg logit contributions | |
elderly | -0.150 |
amusement | -0.150 |
orchestra | -0.146 |
films | -0.146 |
Wheels | -0.142 |
Token | prepared |
Token ID | 5597 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
t | +0.029 |
don | +0.028 |
wouldn | +0.027 |
got | +0.027 |
fell | +0.027 |
Neg logit contributions | |
amusement | -0.039 |
films | -0.038 |
elderly | -0.038 |
orchestra | -0.038 |
Wheels | -0.037 |
Token | for |
Token ID | 329 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
t | +0.078 |
don | +0.072 |
wouldn | +0.072 |
got | +0.071 |
fell | +0.071 |
Neg logit contributions | |
amusement | -0.130 |
films | -0.129 |
elderly | -0.127 |
orchestra | -0.125 |
buildings | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
t | +0.020 |
don | +0.019 |
wouldn | +0.018 |
got | +0.018 |
could | +0.018 |
Neg logit contributions | |
amusement | -0.030 |
films | -0.029 |
orchestra | -0.029 |
elderly | -0.029 |
Wheels | -0.029 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
t | +0.013 |
don | +0.013 |
could | +0.012 |
got | +0.012 |
wouldn | +0.012 |
Neg logit contributions | |
amusement | -0.028 |
films | -0.028 |
orchestra | -0.027 |
elderly | -0.027 |
lions | -0.026 |
Token | had |
Token ID | 550 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
t | +0.028 |
don | +0.025 |
wouldn | +0.024 |
got | +0.023 |
fell | +0.023 |
Neg logit contributions | |
amusement | -0.071 |
elderly | -0.070 |
films | -0.070 |
orchestra | -0.070 |
Wheels | -0.069 |
Token | planted |
Token ID | 18969 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
t | +0.059 |
got | +0.056 |
don | +0.054 |
wouldn | +0.054 |
could | +0.054 |
Neg logit contributions | |
films | -0.133 |
amusement | -0.132 |
orchestra | -0.129 |
Wheels | -0.128 |
elderly | -0.127 |
Token | it |
Token ID | 340 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
amusement | +0.003 |
orchestra | +0.003 |
films | +0.003 |
Wheels | +0.003 |
elderly | +0.002 |
Neg logit contributions | |
could | -0.002 |
t | -0.002 |
don | -0.002 |
got | -0.002 |
would | -0.001 |
Token | weeks |
Token ID | 2745 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
t | +0.072 |
don | +0.067 |
wouldn | +0.063 |
w | +0.062 |
got | +0.062 |
Neg logit contributions | |
elderly | -0.141 |
films | -0.140 |
amusement | -0.140 |
moon | -0.137 |
circles | -0.137 |
Token | ago |
Token ID | 2084 |
Feature activation | +9.89e+00 |
Pos logit contributions | |
t | +0.073 |
don | +0.070 |
wouldn | +0.069 |
got | +0.066 |
fell | +0.066 |
Neg logit contributions | |
amusement | -0.137 |
elderly | -0.136 |
films | -0.134 |
orchestra | -0.133 |
buildings | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
t | +0.137 |
don | +0.127 |
wouldn | +0.125 |
got | +0.121 |
fell | +0.120 |
Neg logit contributions | |
amusement | -0.250 |
films | -0.246 |
elderly | -0.246 |
orchestra | -0.242 |
buildings | -0.241 |
Token | but |
Token ID | 475 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
t | +0.039 |
don | +0.036 |
wouldn | +0.035 |
got | +0.035 |
fell | +0.034 |
Neg logit contributions | |
amusement | -0.064 |
films | -0.063 |
elderly | -0.062 |
orchestra | -0.062 |
Wheels | -0.061 |
Token | now |
Token ID | 783 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
t | +0.046 |
w | +0.039 |
don | +0.038 |
fell | +0.038 |
ged | +0.037 |
Neg logit contributions | |
amusement | -0.094 |
elderly | -0.093 |
films | -0.090 |
orchestra | -0.089 |
array | -0.089 |
Token | she |
Token ID | 673 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
t | +0.041 |
w | +0.035 |
ged | +0.032 |
don | +0.032 |
wouldn | +0.030 |
Neg logit contributions | |
amusement | -0.084 |
elderly | -0.081 |
buildings | -0.080 |
playground | -0.080 |
orchestra | -0.080 |
Token | could |
Token ID | 714 |
Feature activation | +7.08e+00 |
Pos logit contributions | |
t | +0.045 |
don | +0.038 |
ged | +0.037 |
w | +0.037 |
use | +0.032 |
Neg logit contributions | |
elderly | -0.129 |
amusement | -0.127 |
array | -0.124 |
youngest | -0.124 |
orchestra | -0.124 |
Token | fighting |
Token ID | 4330 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
t | +0.098 |
fell | +0.088 |
ged | +0.088 |
wouldn | +0.085 |
got | +0.084 |
Neg logit contributions | |
elderly | -0.096 |
films | -0.085 |
younger | -0.083 |
lions | -0.082 |
elephants | -0.082 |
Token | can |
Token ID | 460 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
t | +0.080 |
ged | +0.074 |
fell | +0.070 |
w | +0.069 |
wouldn | +0.068 |
Neg logit contributions | |
films | -0.129 |
circles | -0.129 |
buildings | -0.127 |
elderly | -0.126 |
moon | -0.125 |
Token | lead |
Token ID | 1085 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
ged | +0.116 |
wouldn | +0.112 |
t | +0.110 |
w | +0.105 |
fell | +0.105 |
Neg logit contributions | |
elderly | -0.179 |
circles | -0.173 |
amusement | -0.172 |
Wheels | -0.172 |
monkeys | -0.172 |
Token | to |
Token ID | 284 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
t | +0.037 |
wouldn | +0.033 |
don | +0.032 |
fell | +0.032 |
got | +0.031 |
Neg logit contributions | |
films | -0.117 |
amusement | -0.117 |
elderly | -0.117 |
buildings | -0.115 |
lions | -0.114 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
don | +0.089 |
t | +0.088 |
got | +0.085 |
wouldn | +0.084 |
fell | +0.083 |
Neg logit contributions | |
amusement | -0.087 |
orchestra | -0.084 |
films | -0.084 |
Wheels | -0.083 |
elderly | -0.082 |
Token | endings |
Token ID | 38168 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
films | +0.047 |
amusement | +0.046 |
buildings | +0.045 |
lions | +0.044 |
elderly | +0.044 |
Neg logit contributions | |
t | -0.086 |
wouldn | -0.081 |
don | -0.079 |
could | -0.079 |
got | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
t | +0.183 |
w | +0.175 |
wouldn | +0.174 |
fell | +0.170 |
got | +0.168 |
Neg logit contributions | |
amusement | -0.194 |
films | -0.193 |
elderly | -0.192 |
lions | -0.188 |
orchestra | -0.188 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
t | +0.013 |
don | +0.012 |
wouldn | +0.012 |
got | +0.012 |
could | +0.012 |
Neg logit contributions | |
amusement | -0.027 |
films | -0.027 |
orchestra | -0.027 |
elderly | -0.026 |
Wheels | -0.026 |
Token | One |
Token ID | 3198 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
amusement | +0.097 |
films | +0.095 |
orchestra | +0.094 |
elderly | +0.094 |
Wheels | +0.093 |
Neg logit contributions | |
t | -0.046 |
don | -0.043 |
wouldn | -0.042 |
got | -0.042 |
fell | -0.041 |
Token | day |
Token ID | 1110 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
orchestra | +0.113 |
amusement | +0.113 |
films | +0.113 |
buildings | +0.110 |
array | +0.109 |
Neg logit contributions | |
t | -0.076 |
got | -0.073 |
don | -0.071 |
fell | -0.071 |
could | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
wouldn | +0.035 |
never | +0.032 |
ried | +0.031 |
t | +0.031 |
ign | +0.030 |
Neg logit contributions | |
films | -0.026 |
lions | -0.025 |
woodland | -0.025 |
Wheels | -0.025 |
elderly | -0.025 |
Token | respect |
Token ID | 2461 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
t | +0.064 |
wouldn | +0.059 |
could | +0.057 |
ged | +0.056 |
fell | +0.055 |
Neg logit contributions | |
amusement | -0.123 |
elderly | -0.120 |
films | -0.117 |
orchestra | -0.116 |
playground | -0.115 |
Token | them |
Token ID | 606 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
t | +0.031 |
don | +0.029 |
wouldn | +0.029 |
got | +0.029 |
could | +0.028 |
Neg logit contributions | |
amusement | -0.042 |
films | -0.041 |
orchestra | -0.041 |
elderly | -0.041 |
Wheels | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
t | +0.045 |
don | +0.044 |
wouldn | +0.042 |
got | +0.041 |
could | +0.041 |
Neg logit contributions | |
amusement | -0.096 |
orchestra | -0.094 |
films | -0.093 |
Wheels | -0.092 |
elderly | -0.092 |
Token | because |
Token ID | 780 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
t | +0.034 |
got | +0.030 |
wouldn | +0.030 |
fell | +0.030 |
w | +0.029 |
Neg logit contributions | |
amusement | -0.078 |
films | -0.077 |
elderly | -0.077 |
orchestra | -0.075 |
buildings | -0.075 |
Token | things |
Token ID | 1243 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
t | +0.032 |
wouldn | +0.028 |
got | +0.028 |
don | +0.028 |
fell | +0.027 |
Neg logit contributions | |
amusement | -0.082 |
films | -0.081 |
elderly | -0.081 |
buildings | -0.079 |
lions | -0.079 |
Token | can |
Token ID | 460 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
ged | +0.071 |
t | +0.071 |
w | +0.064 |
fell | +0.060 |
to | +0.059 |
Neg logit contributions | |
elderly | -0.138 |
films | -0.138 |
buildings | -0.137 |
amusement | -0.132 |
moon | -0.131 |
Token | go |
Token ID | 467 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
ged | +0.151 |
wouldn | +0.145 |
t | +0.140 |
w | +0.138 |
got | +0.134 |
Neg logit contributions | |
amusement | -0.224 |
elderly | -0.224 |
moon | -0.216 |
films | -0.212 |
monkeys | -0.212 |
Token | wrong |
Token ID | 2642 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
t | +0.089 |
w | +0.085 |
fell | +0.083 |
ged | +0.083 |
wouldn | +0.081 |
Neg logit contributions | |
elderly | -0.128 |
amusement | -0.123 |
films | -0.122 |
buildings | -0.122 |
younger | -0.118 |
Token | very |
Token ID | 845 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
films | +0.002 |
amusement | +0.002 |
elderly | +0.002 |
buildings | +0.002 |
orchestra | +0.002 |
Neg logit contributions | |
t | -0.001 |
wouldn | -0.001 |
got | -0.001 |
fell | -0.001 |
don | -0.001 |
Token | quickly |
Token ID | 2952 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
t | +0.015 |
got | +0.015 |
wouldn | +0.014 |
ged | +0.014 |
don | +0.014 |
Neg logit contributions | |
elderly | -0.020 |
buildings | -0.019 |
amusement | -0.019 |
films | -0.019 |
orchestra | -0.018 |
Token | if |
Token ID | 611 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
t | +0.104 |
wouldn | +0.095 |
got | +0.094 |
w | +0.094 |
don | +0.094 |
Neg logit contributions | |
amusement | -0.148 |
elderly | -0.147 |
films | -0.146 |
buildings | -0.143 |
orchestra | -0.142 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
t | +0.021 |
don | +0.020 |
could | +0.020 |
wouldn | +0.019 |
got | +0.019 |
Neg logit contributions | |
amusement | -0.032 |
films | -0.031 |
orchestra | -0.031 |
elderly | -0.030 |
lions | -0.030 |
Token | learned |
Token ID | 4499 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
t | +0.027 |
don | +0.024 |
w | +0.022 |
ged | +0.021 |
wouldn | +0.021 |
Neg logit contributions | |
elderly | -0.053 |
amusement | -0.052 |
orchestra | -0.051 |
films | -0.051 |
Wheels | -0.050 |
Token | that |
Token ID | 326 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
t | +0.050 |
don | +0.047 |
wouldn | +0.046 |
got | +0.046 |
fell | +0.045 |
Neg logit contributions | |
amusement | -0.084 |
elderly | -0.083 |
films | -0.083 |
orchestra | -0.081 |
Wheels | -0.080 |
Token | sorting |
Token ID | 29407 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
t | +0.027 |
ged | +0.025 |
wouldn | +0.025 |
got | +0.024 |
fell | +0.023 |
Neg logit contributions | |
films | -0.055 |
amusement | -0.055 |
elderly | -0.054 |
circles | -0.053 |
moon | -0.052 |
Token | things |
Token ID | 1243 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
t | +0.049 |
fell | +0.045 |
wouldn | +0.045 |
got | +0.045 |
don | +0.045 |
Neg logit contributions | |
films | -0.048 |
elderly | -0.047 |
amusement | -0.047 |
buildings | -0.047 |
circles | -0.046 |
Token | may |
Token ID | 743 |
Feature activation | +9.80e+00 |
Pos logit contributions | |
ged | +0.077 |
t | +0.076 |
w | +0.074 |
fell | +0.068 |
mar | +0.063 |
Neg logit contributions | |
elderly | -0.162 |
buildings | -0.160 |
circles | -0.159 |
ways | -0.157 |
films | -0.155 |
Token | seem |
Token ID | 1283 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
ged | +0.152 |
w | +0.145 |
t | +0.133 |
wouldn | +0.131 |
fell | +0.129 |
Neg logit contributions | |
elderly | -0.237 |
amusement | -0.232 |
playground | -0.224 |
circles | -0.223 |
films | -0.222 |
Token | like |
Token ID | 588 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
t | +0.165 |
w | +0.157 |
ged | +0.155 |
wouldn | +0.155 |
fell | +0.154 |
Neg logit contributions | |
elderly | -0.112 |
amusement | -0.110 |
films | -0.110 |
orchestra | -0.104 |
buildings | -0.104 |
Token | a |
Token ID | 257 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
t | +0.045 |
don | +0.043 |
wouldn | +0.043 |
got | +0.042 |
fell | +0.042 |
Neg logit contributions | |
amusement | -0.044 |
films | -0.044 |
elderly | -0.043 |
orchestra | -0.043 |
Wheels | -0.042 |
Token | lot |
Token ID | 1256 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
amusement | +0.082 |
films | +0.080 |
Wheels | +0.079 |
orchestra | +0.078 |
elderly | +0.077 |
Neg logit contributions | |
don | -0.093 |
would | -0.090 |
wouldn | -0.089 |
t | -0.089 |
got | -0.088 |
Token | of |
Token ID | 286 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
t | +0.000 |
don | +0.000 |
wouldn | +0.000 |
got | +0.000 |
could | +0.000 |
Neg logit contributions | |
amusement | -0.000 |
films | -0.000 |
orchestra | -0.000 |
elderly | -0.000 |
Wheels | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -9.37e+00 |
Pos logit contributions | |
t | +0.043 |
don | +0.040 |
w | +0.036 |
wouldn | +0.036 |
ged | +0.036 |
Neg logit contributions | |
elderly | -0.083 |
amusement | -0.080 |
lions | -0.078 |
films | -0.077 |
youngest | -0.076 |
Token | pistol |
Token ID | 16790 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
amusement | +0.133 |
films | +0.129 |
orchestra | +0.127 |
array | +0.124 |
Wheels | +0.122 |
Neg logit contributions | |
don | -0.230 |
would | -0.222 |
got | -0.222 |
t | -0.218 |
will | -0.217 |
Token | gently |
Token ID | 15165 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
t | +0.065 |
don | +0.061 |
wouldn | +0.059 |
got | +0.057 |
fell | +0.057 |
Neg logit contributions | |
amusement | -0.119 |
films | -0.117 |
elderly | -0.117 |
orchestra | -0.116 |
lions | -0.114 |
Token | so |
Token ID | 523 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
t | +0.076 |
don | +0.068 |
wouldn | +0.067 |
w | +0.065 |
could | +0.065 |
Neg logit contributions | |
amusement | -0.128 |
films | -0.125 |
elderly | -0.125 |
orchestra | -0.123 |
Wheels | -0.121 |
Token | it |
Token ID | 340 |
Feature activation | +7.04e+00 |
Pos logit contributions | |
t | +0.031 |
don | +0.027 |
wouldn | +0.027 |
got | +0.026 |
could | +0.025 |
Neg logit contributions | |
amusement | -0.090 |
elderly | -0.089 |
films | -0.088 |
orchestra | -0.087 |
Wheels | -0.086 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +9.74e+00 |
Pos logit contributions | |
t | +0.063 |
don | +0.052 |
w | +0.052 |
ged | +0.048 |
ever | +0.045 |
Neg logit contributions | |
amusement | -0.201 |
elderly | -0.201 |
films | -0.198 |
moon | -0.197 |
orchestra | -0.197 |
Token | 't |
Token ID | 470 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
w | +0.098 |
would | +0.092 |
wouldn | +0.090 |
use | +0.089 |
ged | +0.086 |
Neg logit contributions | |
elderly | -0.243 |
Wheels | -0.236 |
circles | -0.233 |
orchestra | -0.229 |
amusement | -0.227 |
Token | break |
Token ID | 2270 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
w | +0.113 |
ged | +0.103 |
t | +0.103 |
wouldn | +0.098 |
could | +0.096 |
Neg logit contributions | |
elderly | -0.155 |
amusement | -0.147 |
orchestra | -0.145 |
younger | -0.145 |
monkeys | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
t | +0.058 |
got | +0.050 |
don | +0.050 |
wouldn | +0.049 |
would | +0.048 |
Neg logit contributions | |
circles | -0.141 |
amusement | -0.139 |
elderly | -0.139 |
buildings | -0.138 |
films | -0.137 |
Token | He |
Token ID | 679 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
t | +0.022 |
don | +0.021 |
could | +0.021 |
wouldn | +0.020 |
got | +0.020 |
Neg logit contributions | |
amusement | -0.037 |
films | -0.037 |
orchestra | -0.036 |
elderly | -0.036 |
array | -0.035 |
Token | brought |
Token ID | 3181 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
t | +0.077 |
don | +0.062 |
w | +0.062 |
ever | +0.058 |
ged | +0.056 |
Neg logit contributions | |
amusement | -0.177 |
elderly | -0.172 |
films | -0.171 |
orchestra | -0.170 |
buildings | -0.169 |
Token | But |
Token ID | 887 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
t | +0.012 |
could | +0.011 |
don | +0.011 |
got | +0.011 |
wouldn | +0.010 |
Neg logit contributions | |
amusement | -0.020 |
orchestra | -0.020 |
films | -0.020 |
elderly | -0.020 |
array | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
t | +0.025 |
don | +0.022 |
got | +0.022 |
fell | +0.022 |
wouldn | +0.022 |
Neg logit contributions | |
amusement | -0.044 |
elderly | -0.043 |
films | -0.043 |
orchestra | -0.042 |
buildings | -0.042 |
Token | was |
Token ID | 373 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
t | +0.041 |
don | +0.037 |
wouldn | +0.036 |
got | +0.035 |
fell | +0.034 |
Neg logit contributions | |
amusement | -0.131 |
films | -0.129 |
elderly | -0.128 |
orchestra | -0.128 |
Wheels | -0.126 |
Token | so |
Token ID | 523 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
t | +0.020 |
don | +0.018 |
wouldn | +0.018 |
got | +0.018 |
fell | +0.018 |
Neg logit contributions | |
amusement | -0.033 |
films | -0.032 |
orchestra | -0.032 |
elderly | -0.031 |
Wheels | -0.031 |
Token | long |
Token ID | 890 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
t | +0.053 |
wouldn | +0.051 |
don | +0.051 |
got | +0.050 |
could | +0.049 |
Neg logit contributions | |
elderly | -0.043 |
amusement | -0.043 |
films | -0.042 |
orchestra | -0.041 |
buildings | -0.041 |
Token | ago |
Token ID | 2084 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
amusement | +0.023 |
elderly | +0.023 |
films | +0.023 |
buildings | +0.023 |
orchestra | +0.023 |
Neg logit contributions | |
t | -0.014 |
don | -0.013 |
wouldn | -0.012 |
got | -0.012 |
w | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
t | +0.136 |
don | +0.127 |
wouldn | +0.123 |
w | +0.120 |
got | +0.119 |
Neg logit contributions | |
amusement | -0.241 |
elderly | -0.236 |
films | -0.234 |
buildings | -0.233 |
playground | -0.232 |
Token | everything |
Token ID | 2279 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
t | +0.024 |
don | +0.022 |
wouldn | +0.022 |
got | +0.021 |
could | +0.021 |
Neg logit contributions | |
amusement | -0.076 |
films | -0.075 |
orchestra | -0.075 |
elderly | -0.074 |
Wheels | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
t | +0.045 |
w | +0.041 |
don | +0.039 |
ged | +0.039 |
got | +0.035 |
Neg logit contributions | |
amusement | -0.131 |
elderly | -0.130 |
buildings | -0.128 |
films | -0.128 |
orchestra | -0.128 |
Token | a |
Token ID | 257 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
t | +0.039 |
don | +0.037 |
wouldn | +0.036 |
got | +0.036 |
fell | +0.035 |
Neg logit contributions | |
amusement | -0.054 |
films | -0.053 |
elderly | -0.052 |
orchestra | -0.052 |
Wheels | -0.051 |
Token | bit |
Token ID | 1643 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
films | +0.086 |
amusement | +0.083 |
Wheels | +0.083 |
orchestra | +0.082 |
elderly | +0.080 |
Neg logit contributions | |
t | -0.091 |
don | -0.088 |
got | -0.088 |
would | -0.087 |
wouldn | -0.087 |
Token | 's |
Token ID | 338 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
t | +0.008 |
don | +0.007 |
wouldn | +0.006 |
ged | +0.006 |
w | +0.006 |
Neg logit contributions | |
films | -0.017 |
amusement | -0.017 |
lions | -0.017 |
elderly | -0.017 |
jungle | -0.016 |
Token | leg |
Token ID | 1232 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
amusement | +0.051 |
orchestra | +0.051 |
Wheels | +0.048 |
films | +0.048 |
array | +0.047 |
Neg logit contributions | |
don | -0.072 |
would | -0.071 |
wouldn | -0.070 |
could | -0.069 |
got | -0.069 |
Token | healed |
Token ID | 28557 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
t | +0.043 |
don | +0.039 |
ged | +0.038 |
wouldn | +0.036 |
w | +0.035 |
Neg logit contributions | |
elderly | -0.113 |
amusement | -0.113 |
films | -0.112 |
Wheels | -0.112 |
buildings | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
t | +0.031 |
don | +0.027 |
got | +0.027 |
wouldn | +0.027 |
fell | +0.026 |
Neg logit contributions | |
films | -0.048 |
amusement | -0.048 |
elderly | -0.047 |
lions | -0.046 |
buildings | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
t | +0.061 |
don | +0.050 |
w | +0.049 |
ged | +0.049 |
wouldn | +0.048 |
Neg logit contributions | |
amusement | -0.113 |
films | -0.112 |
elderly | -0.112 |
buildings | -0.110 |
lions | -0.109 |
Token | could |
Token ID | 714 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
t | +0.084 |
ged | +0.076 |
don | +0.073 |
w | +0.071 |
use | +0.066 |
Neg logit contributions | |
moon | -0.189 |
elderly | -0.185 |
films | -0.185 |
buildings | -0.185 |
Wheels | -0.184 |
Token | hop |
Token ID | 1725 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
ged | +0.159 |
w | +0.150 |
t | +0.147 |
wouldn | +0.138 |
got | +0.130 |
Neg logit contributions | |
moon | -0.214 |
elderly | -0.213 |
amusement | -0.207 |
films | -0.203 |
playground | -0.200 |
Token | again |
Token ID | 757 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
wouldn | +0.077 |
w | +0.076 |
t | +0.076 |
don | +0.075 |
got | +0.072 |
Neg logit contributions | |
amusement | -0.109 |
films | -0.109 |
circles | -0.107 |
elderly | -0.106 |
orchestra | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
t | +0.084 |
don | +0.078 |
wouldn | +0.078 |
got | +0.076 |
fell | +0.075 |
Neg logit contributions | |
amusement | -0.125 |
films | -0.124 |
elderly | -0.122 |
orchestra | -0.121 |
Wheels | -0.119 |
Token | Anna |
Token ID | 11735 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
t | +0.019 |
could | +0.019 |
don | +0.019 |
got | +0.017 |
fell | +0.017 |
Neg logit contributions | |
amusement | -0.041 |
orchestra | -0.040 |
films | -0.039 |
array | -0.038 |
elderly | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
t | +0.033 |
don | +0.027 |
w | +0.027 |
wouldn | +0.027 |
ged | +0.026 |
Neg logit contributions | |
elderly | -0.059 |
amusement | -0.059 |
films | -0.058 |
orchestra | -0.058 |
circles | -0.058 |
Token | his |
Token ID | 465 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
amusement | +0.017 |
films | +0.016 |
orchestra | +0.016 |
elderly | +0.016 |
Wheels | +0.016 |
Neg logit contributions | |
t | -0.012 |
don | -0.012 |
wouldn | -0.011 |
got | -0.011 |
could | -0.011 |
Token | garden |
Token ID | 11376 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
films | +0.100 |
orchestra | +0.100 |
Wheels | +0.096 |
amusement | +0.095 |
andel | +0.094 |
Neg logit contributions | |
got | -0.137 |
fell | -0.133 |
could | -0.133 |
don | -0.132 |
would | -0.130 |
Token | and |
Token ID | 290 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
t | +0.028 |
could | +0.028 |
don | +0.027 |
got | +0.027 |
wouldn | +0.027 |
Neg logit contributions | |
films | -0.064 |
amusement | -0.064 |
orchestra | -0.064 |
Wheels | -0.063 |
elderly | -0.061 |
Token | how |
Token ID | 703 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
t | +0.053 |
w | +0.044 |
don | +0.044 |
wouldn | +0.043 |
fell | +0.041 |
Neg logit contributions | |
amusement | -0.114 |
elderly | -0.111 |
films | -0.111 |
buildings | -0.109 |
orchestra | -0.109 |
Token | it |
Token ID | 340 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
t | +0.028 |
wouldn | +0.026 |
don | +0.025 |
ged | +0.025 |
got | +0.025 |
Neg logit contributions | |
elderly | -0.058 |
amusement | -0.056 |
films | -0.056 |
buildings | -0.056 |
lions | -0.055 |
Token | could |
Token ID | 714 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
t | +0.083 |
ged | +0.077 |
w | +0.075 |
don | +0.066 |
wouldn | +0.059 |
Neg logit contributions | |
elderly | -0.191 |
buildings | -0.191 |
elephants | -0.189 |
lions | -0.188 |
moon | -0.187 |
Token | be |
Token ID | 307 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
t | +0.139 |
wouldn | +0.130 |
ged | +0.128 |
w | +0.127 |
could | +0.123 |
Neg logit contributions | |
amusement | -0.240 |
elderly | -0.235 |
films | -0.228 |
playground | -0.227 |
orchestra | -0.227 |
Token | used |
Token ID | 973 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
t | +0.020 |
don | +0.019 |
got | +0.019 |
wouldn | +0.019 |
could | +0.019 |
Neg logit contributions | |
amusement | -0.034 |
films | -0.033 |
orchestra | -0.033 |
Wheels | -0.033 |
elderly | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
t | +0.048 |
don | +0.044 |
wouldn | +0.043 |
got | +0.043 |
fell | +0.042 |
Neg logit contributions | |
amusement | -0.103 |
films | -0.101 |
elderly | -0.101 |
orchestra | -0.099 |
buildings | -0.098 |
Token | get |
Token ID | 651 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
t | +0.058 |
don | +0.057 |
got | +0.055 |
wouldn | +0.055 |
fell | +0.054 |
Neg logit contributions | |
films | -0.098 |
amusement | -0.097 |
orchestra | -0.096 |
Wheels | -0.095 |
elderly | -0.095 |
Token | whatever |
Token ID | 4232 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
t | +0.059 |
don | +0.055 |
wouldn | +0.054 |
got | +0.053 |
fell | +0.053 |
Neg logit contributions | |
amusement | -0.087 |
elderly | -0.086 |
films | -0.085 |
orchestra | -0.083 |
buildings | -0.083 |
Token | will |
Token ID | 481 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
it | +0.021 |
could | +0.020 |
got | +0.020 |
don | +0.020 |
fell | +0.019 |
Neg logit contributions | |
orchestra | -0.057 |
array | -0.056 |
Wheels | -0.056 |
umm | -0.055 |
films | -0.055 |
Token | find |
Token ID | 1064 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
t | +0.125 |
ged | +0.122 |
w | +0.120 |
wouldn | +0.114 |
could | +0.108 |
Neg logit contributions | |
amusement | -0.238 |
films | -0.235 |
elderly | -0.233 |
orchestra | -0.233 |
playground | -0.227 |
Token | some |
Token ID | 617 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
t | +0.073 |
don | +0.068 |
wouldn | +0.067 |
got | +0.066 |
fell | +0.065 |
Neg logit contributions | |
amusement | -0.137 |
films | -0.135 |
elderly | -0.133 |
orchestra | -0.133 |
Wheels | -0.131 |
Token | flowers |
Token ID | 12734 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
amusement | +0.056 |
films | +0.055 |
orchestra | +0.054 |
Wheels | +0.054 |
elderly | +0.053 |
Neg logit contributions | |
t | -0.064 |
don | -0.063 |
wouldn | -0.062 |
got | -0.061 |
could | -0.061 |
Token | we |
Token ID | 356 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
t | +0.043 |
ged | +0.041 |
w | +0.041 |
wouldn | +0.040 |
don | +0.039 |
Neg logit contributions | |
elderly | -0.079 |
amusement | -0.077 |
films | -0.076 |
lions | -0.075 |
elephants | -0.075 |
Token | can |
Token ID | 460 |
Feature activation | +9.63e+00 |
Pos logit contributions | |
t | +0.086 |
ged | +0.072 |
w | +0.067 |
wouldn | +0.062 |
to | +0.062 |
Neg logit contributions | |
elderly | -0.171 |
elephants | -0.170 |
moon | -0.169 |
amusement | -0.168 |
playground | -0.167 |
Token | take |
Token ID | 1011 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ged | +0.147 |
t | +0.143 |
wouldn | +0.141 |
w | +0.139 |
fell | +0.130 |
Neg logit contributions | |
amusement | -0.224 |
elderly | -0.224 |
moon | -0.218 |
films | -0.217 |
playground | -0.217 |
Token | ." |
Token ID | 526 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
t | +0.037 |
wouldn | +0.034 |
don | +0.033 |
fell | +0.032 |
got | +0.032 |
Neg logit contributions | |
films | -0.068 |
amusement | -0.067 |
buildings | -0.065 |
lions | -0.065 |
orchestra | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
t | +0.004 |
don | +0.004 |
got | +0.003 |
could | +0.003 |
wouldn | +0.003 |
Neg logit contributions | |
amusement | -0.007 |
films | -0.007 |
orchestra | -0.007 |
elderly | -0.007 |
array | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
amusement | +0.031 |
films | +0.031 |
orchestra | +0.031 |
array | +0.031 |
buildings | +0.031 |
Neg logit contributions | |
t | -0.011 |
don | -0.010 |
could | -0.009 |
got | -0.009 |
fell | -0.009 |
Token | Ben |
Token ID | 11696 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
films | +0.038 |
amusement | +0.038 |
orchestra | +0.037 |
buildings | +0.037 |
elderly | +0.037 |
Neg logit contributions | |
t | -0.030 |
don | -0.028 |
got | -0.027 |
could | -0.027 |
never | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
t | +0.055 |
wouldn | +0.050 |
don | +0.050 |
could | +0.048 |
fell | +0.048 |
Neg logit contributions | |
amusement | -0.089 |
films | -0.089 |
elderly | -0.087 |
orchestra | -0.086 |
lions | -0.085 |
Token | little |
Token ID | 1310 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
amusement | +0.063 |
films | +0.062 |
orchestra | +0.061 |
buildings | +0.061 |
Wheels | +0.061 |
Neg logit contributions | |
t | -0.069 |
don | -0.066 |
got | -0.065 |
wouldn | -0.064 |
fell | -0.064 |
Token | break |
Token ID | 2270 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
amusement | +0.120 |
films | +0.119 |
orchestra | +0.117 |
elderly | +0.116 |
Wheels | +0.116 |
Neg logit contributions | |
t | -0.080 |
don | -0.077 |
wouldn | -0.075 |
got | -0.075 |
fell | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
t | +0.048 |
don | +0.045 |
wouldn | +0.044 |
got | +0.044 |
fell | +0.043 |
Neg logit contributions | |
films | -0.077 |
amusement | -0.077 |
elderly | -0.077 |
orchestra | -0.076 |
buildings | -0.075 |
Token | I |
Token ID | 314 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
t | +0.062 |
ged | +0.052 |
w | +0.050 |
wouldn | +0.048 |
ever | +0.047 |
Neg logit contributions | |
amusement | -0.105 |
elderly | -0.104 |
films | -0.102 |
buildings | -0.102 |
orchestra | -0.100 |
Token | 'll |
Token ID | 1183 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
ged | +0.071 |
w | +0.059 |
t | +0.057 |
wouldn | +0.047 |
mar | +0.046 |
Neg logit contributions | |
elderly | -0.157 |
amusement | -0.152 |
difference | -0.150 |
Wheels | -0.146 |
youngest | -0.146 |
Token | tell |
Token ID | 1560 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
t | +0.133 |
ged | +0.128 |
w | +0.123 |
wouldn | +0.120 |
could | +0.116 |
Neg logit contributions | |
amusement | -0.240 |
elderly | -0.235 |
orchestra | -0.232 |
playground | -0.231 |
films | -0.229 |
Token | you |
Token ID | 345 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
t | +0.034 |
don | +0.034 |
wouldn | +0.031 |
got | +0.030 |
could | +0.030 |
Neg logit contributions | |
amusement | -0.117 |
orchestra | -0.115 |
films | -0.115 |
array | -0.114 |
elderly | -0.113 |
Token | a |
Token ID | 257 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
t | +0.090 |
wouldn | +0.084 |
don | +0.084 |
got | +0.082 |
fell | +0.081 |
Neg logit contributions | |
amusement | -0.144 |
films | -0.142 |
elderly | -0.141 |
orchestra | -0.139 |
Wheels | -0.137 |
Token | story |
Token ID | 1621 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
amusement | +0.035 |
films | +0.034 |
orchestra | +0.034 |
buildings | +0.034 |
Wheels | +0.033 |
Neg logit contributions | |
t | -0.038 |
would | -0.037 |
don | -0.037 |
got | -0.037 |
wouldn | -0.036 |
Token | while |
Token ID | 981 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
t | +0.063 |
don | +0.061 |
wouldn | +0.060 |
got | +0.059 |
fell | +0.058 |
Neg logit contributions | |
amusement | -0.084 |
films | -0.083 |
elderly | -0.082 |
orchestra | -0.082 |
Wheels | -0.080 |
Token | my |
Token ID | 1820 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
t | +0.035 |
don | +0.030 |
wouldn | +0.029 |
w | +0.029 |
fell | +0.028 |
Neg logit contributions | |
amusement | -0.060 |
elderly | -0.060 |
films | -0.059 |
orchestra | -0.058 |
Wheels | -0.058 |
Token | said |
Token ID | 531 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
t | +0.071 |
w | +0.059 |
don | +0.059 |
wouldn | +0.056 |
ever | +0.055 |
Neg logit contributions | |
elderly | -0.122 |
films | -0.120 |
amusement | -0.119 |
orchestra | -0.117 |
lions | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
t | +0.049 |
w | +0.045 |
don | +0.044 |
wouldn | +0.043 |
got | +0.043 |
Neg logit contributions | |
amusement | -0.090 |
films | -0.090 |
elderly | -0.088 |
orchestra | -0.088 |
lions | -0.086 |
Token | " |
Token ID | 366 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
t | +0.062 |
don | +0.058 |
wouldn | +0.057 |
got | +0.057 |
fell | +0.057 |
Neg logit contributions | |
amusement | -0.067 |
films | -0.066 |
elderly | -0.065 |
orchestra | -0.065 |
Wheels | -0.064 |
Token | we |
Token ID | 732 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
t | +0.022 |
don | +0.021 |
wouldn | +0.021 |
got | +0.021 |
fell | +0.021 |
Neg logit contributions | |
amusement | -0.033 |
films | -0.032 |
elderly | -0.032 |
orchestra | -0.032 |
Wheels | -0.031 |
Token | 'll |
Token ID | 1183 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
t | +0.056 |
fell | +0.046 |
wouldn | +0.043 |
ged | +0.043 |
could | +0.042 |
Neg logit contributions | |
films | -0.112 |
orchestra | -0.109 |
amusement | -0.109 |
Wheels | -0.108 |
lions | -0.107 |
Token | be |
Token ID | 307 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
t | +0.132 |
ged | +0.123 |
w | +0.122 |
wouldn | +0.120 |
fell | +0.116 |
Neg logit contributions | |
amusement | -0.247 |
elderly | -0.240 |
films | -0.239 |
orchestra | -0.238 |
playground | -0.234 |
Token | home |
Token ID | 1363 |
Feature activation | +6.50e+00 |
Pos logit contributions | |
don | +0.042 |
got | +0.040 |
never | +0.039 |
soon | +0.039 |
wouldn | +0.039 |
Neg logit contributions | |
amusement | -0.067 |
umm | -0.065 |
orchestra | -0.064 |
Wheels | -0.064 |
buildings | -0.063 |
Token | soon |
Token ID | 2582 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
t | +0.061 |
don | +0.056 |
wouldn | +0.054 |
got | +0.053 |
fell | +0.051 |
Neg logit contributions | |
amusement | -0.196 |
films | -0.194 |
orchestra | -0.192 |
elderly | -0.191 |
Wheels | -0.190 |
Token | ." |
Token ID | 526 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
t | +0.087 |
wouldn | +0.080 |
don | +0.080 |
got | +0.078 |
could | +0.078 |
Neg logit contributions | |
amusement | -0.147 |
films | -0.146 |
elderly | -0.144 |
orchestra | -0.143 |
Wheels | -0.141 |
Token | |
Token ID | 220 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
t | +0.012 |
don | +0.012 |
got | +0.011 |
could | +0.011 |
wouldn | +0.011 |
Neg logit contributions | |
amusement | -0.025 |
films | -0.024 |
orchestra | -0.024 |
elderly | -0.024 |
lions | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
t | +0.016 |
don | +0.014 |
wouldn | +0.013 |
w | +0.013 |
could | +0.013 |
Neg logit contributions | |
amusement | -0.044 |
elderly | -0.044 |
films | -0.043 |
orchestra | -0.042 |
buildings | -0.042 |
Token | got |
Token ID | 1392 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
t | +0.077 |
w | +0.068 |
don | +0.067 |
ged | +0.063 |
use | +0.058 |
Neg logit contributions | |
elderly | -0.164 |
youngest | -0.156 |
amusement | -0.155 |
Wheels | -0.154 |
orchestra | -0.154 |
Token | his |
Token ID | 465 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
t | +0.053 |
don | +0.048 |
wouldn | +0.047 |
fell | +0.045 |
w | +0.045 |
Neg logit contributions | |
elderly | -0.087 |
amusement | -0.085 |
films | -0.085 |
buildings | -0.081 |
youngest | -0.081 |
Token | little |
Token ID | 1310 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
amusement | +0.095 |
films | +0.093 |
orchestra | +0.093 |
Wheels | +0.091 |
array | +0.090 |
Neg logit contributions | |
t | -0.115 |
don | -0.113 |
wouldn | -0.113 |
got | -0.112 |
fell | -0.110 |
Token | screw |
Token ID | 9580 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
films | +0.130 |
amusement | +0.129 |
Wheels | +0.129 |
orchestra | +0.126 |
lions | +0.124 |
Neg logit contributions | |
don | -0.153 |
got | -0.148 |
wouldn | -0.146 |
fell | -0.145 |
would | -0.141 |
Token | driver |
Token ID | 26230 |
Feature activation | +9.55e+00 |
Pos logit contributions | |
don | +0.018 |
t | +0.018 |
wouldn | +0.017 |
could | +0.016 |
got | +0.016 |
Neg logit contributions | |
elderly | -0.036 |
amusement | -0.036 |
films | -0.035 |
orchestra | -0.035 |
buildings | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
don | +0.145 |
t | +0.136 |
wouldn | +0.134 |
could | +0.132 |
w | +0.131 |
Neg logit contributions | |
elderly | -0.230 |
amusement | -0.221 |
films | -0.215 |
orchestra | -0.214 |
buildings | -0.213 |
Token | started |
Token ID | 2067 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
t | +0.062 |
w | +0.053 |
don | +0.052 |
ever | +0.048 |
wouldn | +0.047 |
Neg logit contributions | |
elderly | -0.113 |
amusement | -0.112 |
buildings | -0.111 |
films | -0.109 |
playground | -0.109 |
Token | to |
Token ID | 284 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
t | +0.053 |
don | +0.048 |
wouldn | +0.047 |
got | +0.046 |
fell | +0.045 |
Neg logit contributions | |
amusement | -0.152 |
films | -0.150 |
elderly | -0.148 |
orchestra | -0.148 |
Wheels | -0.146 |
Token | screw |
Token ID | 9580 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
t | +0.056 |
wouldn | +0.051 |
don | +0.051 |
got | +0.050 |
could | +0.050 |
Neg logit contributions | |
amusement | -0.082 |
films | -0.081 |
elderly | -0.080 |
orchestra | -0.079 |
Wheels | -0.078 |
Token | in |
Token ID | 287 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
t | +0.043 |
don | +0.042 |
wouldn | +0.040 |
got | +0.039 |
fell | +0.039 |
Neg logit contributions | |
amusement | -0.071 |
elderly | -0.070 |
buildings | -0.070 |
films | -0.070 |
circles | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
t | +0.028 |
don | +0.026 |
got | +0.026 |
wouldn | +0.026 |
could | +0.025 |
Neg logit contributions | |
amusement | -0.052 |
films | -0.051 |
elderly | -0.051 |
orchestra | -0.050 |
Wheels | -0.050 |
Token | he |
Token ID | 339 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
don | +0.009 |
t | +0.009 |
got | +0.009 |
could | +0.009 |
wouldn | +0.009 |
Neg logit contributions | |
amusement | -0.029 |
orchestra | -0.028 |
array | -0.028 |
films | -0.028 |
elderly | -0.027 |
Token | noticed |
Token ID | 6810 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
t | +0.048 |
don | +0.043 |
wouldn | +0.041 |
w | +0.040 |
got | +0.039 |
Neg logit contributions | |
amusement | -0.117 |
elderly | -0.115 |
films | -0.114 |
orchestra | -0.114 |
Wheels | -0.113 |
Token | that |
Token ID | 326 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
orchestra | +0.028 |
Wheels | +0.027 |
umm | +0.027 |
films | +0.027 |
array | +0.027 |
Neg logit contributions | |
could | -0.012 |
got | -0.011 |
it | -0.011 |
would | -0.011 |
wouldn | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
don | +0.004 |
got | +0.003 |
could | +0.003 |
wouldn | +0.003 |
it | +0.003 |
Neg logit contributions | |
orchestra | -0.006 |
amusement | -0.006 |
unison | -0.006 |
array | -0.006 |
Wheels | -0.006 |
Token | Sm |
Token ID | 2439 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
amusement | +0.197 |
Wheels | +0.190 |
films | +0.185 |
unison | +0.179 |
orchestra | +0.179 |
Neg logit contributions | |
don | -0.290 |
t | -0.289 |
got | -0.285 |
ever | -0.285 |
never | -0.282 |
Token | elly |
Token ID | 6148 |
Feature activation | -8.62e+00 |
Pos logit contributions | |
amusement | +0.317 |
films | +0.311 |
elderly | +0.305 |
orchestra | +0.305 |
Wheels | +0.299 |
Neg logit contributions | |
t | -0.344 |
don | -0.330 |
wouldn | -0.326 |
got | -0.323 |
fell | -0.319 |
Token | King |
Token ID | 2677 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
amusement | +0.118 |
films | +0.111 |
Wheels | +0.111 |
elderly | +0.109 |
orchestra | +0.108 |
Neg logit contributions | |
t | -0.224 |
don | -0.220 |
got | -0.219 |
wouldn | -0.214 |
could | -0.214 |
Token | was |
Token ID | 373 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
amusement | +0.068 |
films | +0.068 |
orchestra | +0.067 |
elderly | +0.066 |
Wheels | +0.066 |
Neg logit contributions | |
t | -0.017 |
got | -0.016 |
wouldn | -0.016 |
don | -0.016 |
could | -0.016 |
Token | cruel |
Token ID | 12177 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
never | +0.007 |
got | +0.007 |
t | +0.007 |
ever | +0.007 |
could | +0.007 |
Neg logit contributions | |
amusement | -0.011 |
films | -0.011 |
Wheels | -0.011 |
orchestra | -0.011 |
buildings | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
amusement | +0.104 |
films | +0.102 |
orchestra | +0.101 |
elderly | +0.101 |
Wheels | +0.100 |
Neg logit contributions | |
t | -0.050 |
don | -0.047 |
wouldn | -0.046 |
got | -0.046 |
could | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
t | +0.028 |
don | +0.028 |
could | +0.027 |
got | +0.027 |
wouldn | +0.027 |
Neg logit contributions | |
amusement | -0.063 |
films | -0.062 |
orchestra | -0.062 |
array | -0.061 |
elderly | -0.061 |
Token | got |
Token ID | 1392 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
t | +0.055 |
don | +0.045 |
w | +0.045 |
ged | +0.044 |
wouldn | +0.038 |
Neg logit contributions | |
elderly | -0.146 |
orchestra | -0.143 |
amusement | -0.139 |
moon | -0.137 |
lions | -0.136 |
Token | rid |
Token ID | 5755 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
t | +0.031 |
don | +0.028 |
wouldn | +0.027 |
got | +0.026 |
fell | +0.026 |
Neg logit contributions | |
elderly | -0.080 |
amusement | -0.080 |
films | -0.079 |
orchestra | -0.077 |
Wheels | -0.076 |
Token | of |
Token ID | 286 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
amusement | +0.045 |
films | +0.044 |
orchestra | +0.043 |
elderly | +0.043 |
Wheels | +0.042 |
Neg logit contributions | |
t | -0.043 |
don | -0.041 |
wouldn | -0.040 |
got | -0.040 |
could | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
orchestra | +0.033 |
amusement | +0.032 |
array | +0.032 |
Wheels | +0.032 |
sym | +0.032 |
Neg logit contributions | |
don | -0.015 |
it | -0.015 |
ever | -0.014 |
never | -0.014 |
wouldn | -0.014 |
Token | intr |
Token ID | 9913 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
amusement | +0.176 |
films | +0.165 |
unison | +0.165 |
Wheels | +0.164 |
orchestra | +0.157 |
Neg logit contributions | |
don | -0.273 |
fell | -0.264 |
got | -0.262 |
would | -0.260 |
ever | -0.260 |
Token | uders |
Token ID | 48739 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
amusement | +0.243 |
orchestra | +0.225 |
Wheels | +0.221 |
elderly | +0.218 |
films | +0.217 |
Neg logit contributions | |
t | -0.366 |
don | -0.364 |
fell | -0.359 |
ever | -0.359 |
got | -0.359 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
t | +0.026 |
don | +0.025 |
wouldn | +0.024 |
got | +0.024 |
fell | +0.024 |
Neg logit contributions | |
amusement | -0.050 |
films | -0.050 |
orchestra | -0.049 |
elderly | -0.049 |
Wheels | -0.048 |
Token | She |
Token ID | 1375 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
t | +0.015 |
don | +0.015 |
could | +0.015 |
got | +0.014 |
fell | +0.013 |
Neg logit contributions | |
films | -0.035 |
amusement | -0.034 |
orchestra | -0.034 |
array | -0.033 |
elderly | -0.033 |
Token | did |
Token ID | 750 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
t | +0.064 |
don | +0.054 |
w | +0.053 |
ged | +0.051 |
wouldn | +0.050 |
Neg logit contributions | |
amusement | -0.139 |
elderly | -0.139 |
orchestra | -0.136 |
films | -0.135 |
moon | -0.134 |
Token | not |
Token ID | 407 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
t | +0.047 |
wouldn | +0.038 |
don | +0.038 |
got | +0.037 |
could | +0.036 |
Neg logit contributions | |
amusement | -0.184 |
films | -0.182 |
elderly | -0.180 |
orchestra | -0.179 |
Wheels | -0.177 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
t | +0.057 |
don | +0.051 |
w | +0.049 |
ged | +0.047 |
wouldn | +0.045 |
Neg logit contributions | |
elderly | -0.103 |
amusement | -0.102 |
films | -0.099 |
orchestra | -0.099 |
youngest | -0.098 |
Token | her |
Token ID | 607 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
t | +0.011 |
got | +0.009 |
don | +0.009 |
wouldn | +0.009 |
could | +0.008 |
Neg logit contributions | |
amusement | -0.074 |
films | -0.073 |
orchestra | -0.073 |
Wheels | -0.073 |
elderly | -0.072 |
Token | name |
Token ID | 1438 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
umm | +0.126 |
array | +0.120 |
andel | +0.120 |
Wheels | +0.119 |
orchestra | +0.118 |
Neg logit contributions | |
would | -0.121 |
got | -0.120 |
don | -0.120 |
could | -0.117 |
to | -0.116 |
Token | to |
Token ID | 284 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
t | +0.014 |
don | +0.013 |
wouldn | +0.013 |
got | +0.013 |
fell | +0.013 |
Neg logit contributions | |
amusement | -0.032 |
films | -0.031 |
orchestra | -0.031 |
elderly | -0.031 |
Wheels | -0.031 |
Token | be |
Token ID | 307 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
t | +0.025 |
don | +0.025 |
wouldn | +0.024 |
got | +0.024 |
could | +0.023 |
Neg logit contributions | |
amusement | -0.056 |
films | -0.056 |
orchestra | -0.055 |
elderly | -0.055 |
Wheels | -0.055 |
Token | Tw |
Token ID | 1815 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
umm | +0.039 |
amusement | +0.038 |
Wheels | +0.038 |
unison | +0.037 |
array | +0.037 |
Neg logit contributions | |
don | -0.020 |
got | -0.020 |
ever | -0.019 |
never | -0.019 |
it | -0.019 |
Token | inkle |
Token ID | 19894 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
amusement | +0.287 |
films | +0.281 |
elderly | +0.275 |
orchestra | +0.274 |
buildings | +0.268 |
Neg logit contributions | |
t | -0.332 |
don | -0.317 |
wouldn | -0.313 |
got | -0.311 |
fell | -0.307 |
Token | ! |
Token ID | 0 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
amusement | +0.148 |
playground | +0.143 |
orchestra | +0.141 |
jungle | +0.139 |
array | +0.138 |
Neg logit contributions | |
wouldn | -0.057 |
could | -0.056 |
don | -0.055 |
got | -0.055 |
would | -0.055 |
Token | Her |
Token ID | 2332 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
amusement | +0.021 |
array | +0.020 |
elderly | +0.019 |
films | +0.019 |
orchestra | +0.019 |
Neg logit contributions | |
t | -0.017 |
could | -0.016 |
don | -0.016 |
wouldn | -0.016 |
got | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
elephants | +0.143 |
lions | +0.143 |
monkeys | +0.143 |
amusement | +0.142 |
buildings | +0.139 |
Neg logit contributions | |
don | -0.089 |
got | -0.086 |
could | -0.085 |
would | -0.085 |
wouldn | -0.084 |
Token | my |
Token ID | 1820 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
t | +0.027 |
don | +0.025 |
fell | +0.024 |
wouldn | +0.024 |
w | +0.024 |
Neg logit contributions | |
elderly | -0.032 |
amusement | -0.031 |
orchestra | -0.031 |
circles | -0.030 |
moon | -0.030 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
amusement | +0.018 |
films | +0.017 |
orchestra | +0.017 |
lions | +0.016 |
elderly | +0.016 |
Neg logit contributions | |
t | -0.011 |
could | -0.011 |
got | -0.011 |
don | -0.011 |
wouldn | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
t | +0.011 |
don | +0.010 |
wouldn | +0.010 |
got | +0.010 |
fell | +0.010 |
Neg logit contributions | |
amusement | -0.027 |
films | -0.027 |
orchestra | -0.027 |
elderly | -0.026 |
Wheels | -0.026 |
Token | she |
Token ID | 673 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
amusement | +0.006 |
films | +0.006 |
elderly | +0.006 |
orchestra | +0.006 |
Wheels | +0.006 |
Neg logit contributions | |
t | -0.003 |
don | -0.002 |
wouldn | -0.002 |
got | -0.002 |
fell | -0.002 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
t | +0.027 |
don | +0.025 |
wouldn | +0.024 |
ever | +0.022 |
got | +0.022 |
Neg logit contributions | |
amusement | -0.066 |
elderly | -0.064 |
films | -0.064 |
Wheels | -0.064 |
orchestra | -0.064 |
Token | a |
Token ID | 257 |
Feature activation | -7.37e+00 |
Pos logit contributions | |
films | +0.045 |
orchestra | +0.045 |
umm | +0.044 |
Wheels | +0.044 |
amusement | +0.044 |
Neg logit contributions | |
it | -0.018 |
got | -0.018 |
could | -0.018 |
fell | -0.018 |
never | -0.017 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
films | +0.135 |
amusement | +0.127 |
orchestra | +0.126 |
opl | +0.125 |
buildings | +0.121 |
Neg logit contributions | |
got | -0.164 |
don | -0.162 |
fell | -0.158 |
would | -0.157 |
could | -0.157 |
Token | ile |
Token ID | 576 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
amusement | +0.292 |
elderly | +0.284 |
orchestra | +0.279 |
films | +0.278 |
buildings | +0.275 |
Neg logit contributions | |
t | -0.339 |
w | -0.315 |
got | -0.311 |
ever | -0.307 |
fell | -0.305 |
Token | in |
Token ID | 287 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
amusement | +0.095 |
films | +0.094 |
orchestra | +0.093 |
elderly | +0.093 |
Wheels | +0.092 |
Neg logit contributions | |
t | -0.048 |
don | -0.045 |
got | -0.045 |
wouldn | -0.044 |
fell | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
orchestra | +0.089 |
films | +0.086 |
Wheels | +0.084 |
amusement | +0.084 |
umm | +0.084 |
Neg logit contributions | |
it | -0.040 |
got | -0.038 |
don | -0.038 |
fell | -0.037 |
ever | -0.037 |
Token | water |
Token ID | 1660 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
films | +0.236 |
orchestra | +0.223 |
cartoons | +0.214 |
pian | +0.213 |
sentences | +0.208 |
Neg logit contributions | |
got | -0.272 |
fell | -0.252 |
could | -0.251 |
never | -0.247 |
would | -0.236 |
Token | ! |
Token ID | 0 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
amusement | +0.025 |
films | +0.025 |
orchestra | +0.024 |
elderly | +0.024 |
Wheels | +0.024 |
Neg logit contributions | |
t | -0.015 |
don | -0.014 |
wouldn | -0.014 |
got | -0.014 |
could | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -8.01e+00 |
Pos logit contributions | |
elderly | +0.086 |
moon | +0.084 |
films | +0.083 |
lions | +0.081 |
woodland | +0.081 |
Neg logit contributions | |
t | -0.076 |
wouldn | -0.073 |
use | -0.068 |
ll | -0.064 |
w | -0.062 |
Token | big |
Token ID | 1263 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
amusement | +0.139 |
orchestra | +0.131 |
buildings | +0.128 |
films | +0.128 |
array | +0.126 |
Neg logit contributions | |
don | -0.191 |
got | -0.187 |
fell | -0.183 |
t | -0.183 |
could | -0.182 |
Token | bird |
Token ID | 6512 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
amusement | +0.179 |
unison | +0.176 |
array | +0.171 |
rhythms | +0.169 |
orchestra | +0.168 |
Neg logit contributions | |
got | -0.236 |
don | -0.229 |
fell | -0.229 |
would | -0.219 |
could | -0.211 |
Token | named |
Token ID | 3706 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
jungle | +0.069 |
zoo | +0.065 |
lions | +0.064 |
moon | +0.063 |
films | +0.063 |
Neg logit contributions | |
t | -0.087 |
wouldn | -0.086 |
don | -0.085 |
ged | -0.075 |
managed | -0.075 |
Token | O |
Token ID | 440 |
Feature activation | -9.29e+00 |
Pos logit contributions | |
orchestra | +0.114 |
amusement | +0.113 |
films | +0.110 |
array | +0.109 |
rhythms | +0.109 |
Neg logit contributions | |
don | -0.057 |
got | -0.053 |
t | -0.053 |
it | -0.052 |
could | -0.052 |
Token | str |
Token ID | 2536 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
jungle | +0.257 |
elderly | +0.257 |
amusement | +0.255 |
playground | +0.253 |
Wheels | +0.253 |
Neg logit contributions | |
wouldn | -0.089 |
don | -0.089 |
t | -0.088 |
could | -0.079 |
ged | -0.077 |
Token | ich |
Token ID | 488 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
amusement | +0.227 |
films | +0.226 |
orchestra | +0.218 |
Wheels | +0.206 |
elderly | +0.206 |
Neg logit contributions | |
t | -0.381 |
don | -0.359 |
got | -0.359 |
wouldn | -0.358 |
fell | -0.357 |
Token | wanted |
Token ID | 2227 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
films | +0.061 |
amusement | +0.061 |
elderly | +0.060 |
lions | +0.060 |
orchestra | +0.059 |
Neg logit contributions | |
t | -0.050 |
don | -0.047 |
wouldn | -0.047 |
got | -0.044 |
fell | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
t | +0.003 |
got | +0.002 |
could | +0.001 |
don | +0.001 |
fell | +0.001 |
Neg logit contributions | |
orchestra | -0.036 |
films | -0.036 |
amusement | -0.036 |
Wheels | -0.036 |
unison | -0.035 |
Token | swim |
Token ID | 9422 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
t | +0.026 |
don | +0.025 |
got | +0.025 |
fell | +0.024 |
could | +0.023 |
Neg logit contributions | |
amusement | -0.052 |
films | -0.052 |
orchestra | -0.052 |
Wheels | -0.051 |
elderly | -0.051 |
Token | in |
Token ID | 287 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
t | +0.011 |
wouldn | +0.011 |
don | +0.010 |
ged | +0.010 |
w | +0.010 |
Neg logit contributions | |
amusement | -0.023 |
elderly | -0.023 |
films | -0.023 |
orchestra | -0.022 |
playground | -0.022 |
Token | had |
Token ID | 550 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
amusement | +0.047 |
elderly | +0.047 |
films | +0.046 |
orchestra | +0.046 |
buildings | +0.046 |
Neg logit contributions | |
t | -0.015 |
don | -0.013 |
w | -0.012 |
wouldn | -0.012 |
ged | -0.012 |
Token | two |
Token ID | 734 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
t | +0.035 |
got | +0.035 |
could | +0.033 |
wouldn | +0.033 |
never | +0.032 |
Neg logit contributions | |
films | -0.072 |
orchestra | -0.071 |
amusement | -0.071 |
Wheels | -0.070 |
array | -0.068 |
Token | rulers |
Token ID | 24925 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
amusement | +0.113 |
orchestra | +0.110 |
films | +0.108 |
Wheels | +0.107 |
elderly | +0.103 |
Neg logit contributions | |
got | -0.151 |
t | -0.151 |
could | -0.149 |
don | -0.149 |
would | -0.145 |
Token | , |
Token ID | 11 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
amusement | +0.035 |
films | +0.035 |
elderly | +0.034 |
orchestra | +0.034 |
buildings | +0.034 |
Neg logit contributions | |
t | -0.024 |
don | -0.023 |
wouldn | -0.022 |
got | -0.022 |
fell | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
don | +0.014 |
t | +0.014 |
got | +0.014 |
wouldn | +0.014 |
could | +0.014 |
Neg logit contributions | |
amusement | -0.024 |
films | -0.024 |
orchestra | -0.024 |
Wheels | -0.023 |
elderly | -0.023 |
Token | Sm |
Token ID | 2439 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
amusement | +0.182 |
Wheels | +0.177 |
films | +0.173 |
array | +0.168 |
sym | +0.168 |
Neg logit contributions | |
don | -0.245 |
ever | -0.234 |
never | -0.234 |
got | -0.232 |
t | -0.229 |
Token | elly |
Token ID | 6148 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
amusement | +0.269 |
films | +0.263 |
elderly | +0.258 |
orchestra | +0.257 |
Wheels | +0.254 |
Neg logit contributions | |
t | -0.330 |
don | -0.317 |
wouldn | -0.312 |
got | -0.310 |
could | -0.306 |
Token | King |
Token ID | 2677 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
amusement | +0.102 |
films | +0.097 |
elderly | +0.095 |
Wheels | +0.095 |
orchestra | +0.094 |
Neg logit contributions | |
t | -0.184 |
don | -0.180 |
got | -0.178 |
wouldn | -0.176 |
could | -0.174 |
Token | and |
Token ID | 290 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
amusement | +0.082 |
films | +0.082 |
orchestra | +0.080 |
Wheels | +0.079 |
elderly | +0.079 |
Neg logit contributions | |
t | -0.028 |
could | -0.027 |
got | -0.027 |
wouldn | -0.026 |
don | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
t | +0.015 |
got | +0.015 |
don | +0.015 |
wouldn | +0.015 |
could | +0.015 |
Neg logit contributions | |
amusement | -0.034 |
films | -0.033 |
orchestra | -0.033 |
Wheels | -0.033 |
elderly | -0.032 |
Token | St |
Token ID | 520 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
amusement | +0.181 |
Wheels | +0.176 |
films | +0.171 |
array | +0.165 |
andel | +0.165 |
Neg logit contributions | |
don | -0.248 |
got | -0.237 |
ever | -0.237 |
never | -0.236 |
t | -0.232 |
Token | woods |
Token ID | 16479 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
unison | +0.219 |
ement | +0.216 |
sentences | +0.210 |
films | +0.210 |
andel | +0.209 |
Neg logit contributions | |
got | -0.260 |
never | -0.240 |
went | -0.239 |
to | -0.230 |
would | -0.230 |
Token | when |
Token ID | 618 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
t | +0.016 |
don | +0.015 |
got | +0.015 |
wouldn | +0.014 |
fell | +0.014 |
Neg logit contributions | |
amusement | -0.033 |
films | -0.033 |
orchestra | -0.033 |
Wheels | -0.032 |
elderly | -0.032 |
Token | she |
Token ID | 673 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
t | +0.024 |
wouldn | +0.022 |
don | +0.022 |
got | +0.020 |
could | +0.020 |
Neg logit contributions | |
amusement | -0.069 |
elderly | -0.067 |
films | -0.066 |
buildings | -0.066 |
playground | -0.066 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
t | +0.024 |
don | +0.023 |
wouldn | +0.022 |
w | +0.020 |
ever | +0.020 |
Neg logit contributions | |
amusement | -0.049 |
elderly | -0.048 |
playground | -0.048 |
Wheels | -0.047 |
jungle | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | -7.78e+00 |
Pos logit contributions | |
orchestra | +0.066 |
films | +0.065 |
umm | +0.065 |
Wheels | +0.064 |
array | +0.063 |
Neg logit contributions | |
it | -0.023 |
got | -0.021 |
could | -0.019 |
never | -0.019 |
fell | -0.019 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
films | +0.144 |
youngest | +0.135 |
orchestra | +0.135 |
opl | +0.135 |
ways | +0.135 |
Neg logit contributions | |
got | -0.168 |
would | -0.166 |
don | -0.164 |
fell | -0.159 |
could | -0.158 |
Token | ile |
Token ID | 576 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
amusement | +0.309 |
elderly | +0.303 |
orchestra | +0.299 |
buildings | +0.298 |
amaz | +0.298 |
Neg logit contributions | |
t | -0.316 |
w | -0.290 |
ever | -0.284 |
got | -0.283 |
could | -0.276 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
amusement | +0.102 |
orchestra | +0.101 |
films | +0.101 |
elderly | +0.099 |
Wheels | +0.098 |
Neg logit contributions | |
t | -0.045 |
got | -0.044 |
fell | -0.044 |
could | -0.043 |
don | -0.042 |
Token | She |
Token ID | 1375 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
elderly | +0.021 |
amusement | +0.020 |
Wheels | +0.020 |
woodland | +0.020 |
array | +0.020 |
Neg logit contributions | |
t | -0.023 |
wouldn | -0.023 |
w | -0.022 |
don | -0.022 |
ever | -0.021 |
Token | lly |
Token ID | 12810 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
t | +0.034 |
don | +0.030 |
wouldn | +0.028 |
w | +0.028 |
ged | +0.025 |
Neg logit contributions | |
elderly | -0.087 |
amusement | -0.086 |
monkeys | -0.084 |
lions | -0.084 |
Wheels | -0.084 |
Token | said |
Token ID | 531 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
amusement | +0.012 |
elderly | +0.012 |
films | +0.012 |
orchestra | +0.012 |
Wheels | +0.011 |
Neg logit contributions | |
t | -0.004 |
don | -0.004 |
wouldn | -0.004 |
w | -0.003 |
fell | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
elderly | +0.006 |
films | +0.006 |
amusement | +0.006 |
Wheels | +0.006 |
orchestra | +0.006 |
Neg logit contributions | |
t | -0.004 |
don | -0.004 |
wouldn | -0.004 |
w | -0.004 |
ever | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
t | +0.049 |
w | +0.042 |
ged | +0.041 |
don | +0.040 |
't | +0.037 |
Neg logit contributions | |
elderly | -0.082 |
moon | -0.080 |
amusement | -0.079 |
youngest | -0.078 |
younger | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
t | +0.018 |
wouldn | +0.017 |
don | +0.017 |
w | +0.017 |
got | +0.016 |
Neg logit contributions | |
films | -0.034 |
lions | -0.033 |
amusement | -0.033 |
elderly | -0.033 |
monkeys | -0.032 |
Token | Mr |
Token ID | 1770 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
t | +0.043 |
don | +0.041 |
wouldn | +0.041 |
got | +0.040 |
fell | +0.040 |
Neg logit contributions | |
amusement | -0.041 |
films | -0.040 |
orchestra | -0.039 |
elderly | -0.039 |
Wheels | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
amusement | +0.270 |
films | +0.263 |
orchestra | +0.263 |
elderly | +0.259 |
Wheels | +0.256 |
Neg logit contributions | |
t | -0.155 |
don | -0.148 |
wouldn | -0.144 |
got | -0.143 |
could | -0.142 |
Token | Sp |
Token ID | 1338 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
amusement | +0.122 |
orchestra | +0.118 |
array | +0.116 |
films | +0.116 |
buildings | +0.111 |
Neg logit contributions | |
don | -0.096 |
t | -0.094 |
could | -0.092 |
fell | -0.090 |
got | -0.090 |
Token | ud |
Token ID | 463 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
amusement | +0.264 |
films | +0.253 |
orchestra | +0.251 |
elderly | +0.247 |
buildings | +0.245 |
Neg logit contributions | |
t | -0.344 |
don | -0.320 |
wouldn | -0.319 |
got | -0.313 |
fell | -0.312 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
don | +0.022 |
t | +0.022 |
cannot | +0.021 |
w | +0.021 |
will | +0.021 |
Neg logit contributions | |
elderly | -0.029 |
lions | -0.029 |
monkeys | -0.029 |
elephants | -0.028 |
youngest | -0.028 |
Token | " |
Token ID | 366 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
t | +0.025 |
w | +0.025 |
ever | +0.022 |
don | +0.022 |
wouldn | +0.022 |
Neg logit contributions | |
elderly | -0.018 |
films | -0.016 |
moon | -0.016 |
lions | -0.016 |
elephants | -0.016 |
Token | I |
Token ID | 40 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
amusement | +0.024 |
elderly | +0.023 |
Wheels | +0.023 |
moon | +0.023 |
films | +0.023 |
Neg logit contributions | |
t | -0.016 |
don | -0.016 |
wouldn | -0.016 |
ged | -0.015 |
ever | -0.015 |
Token | want |
Token ID | 765 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ged | +0.043 |
ried | +0.033 |
w | +0.032 |
t | +0.030 |
mar | +0.030 |
Neg logit contributions | |
amusement | -0.045 |
difference | -0.045 |
elderly | -0.044 |
playground | -0.041 |
jungle | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
amusement | +0.003 |
films | +0.003 |
elderly | +0.003 |
orchestra | +0.003 |
Wheels | +0.003 |
Neg logit contributions | |
t | -0.002 |
don | -0.002 |
wouldn | -0.002 |
got | -0.002 |
fell | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
amusement | +0.053 |
elderly | +0.052 |
films | +0.052 |
Wheels | +0.052 |
circles | +0.051 |
Neg logit contributions | |
wouldn | -0.046 |
don | -0.043 |
t | -0.041 |
w | -0.041 |
ever | -0.040 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
amusement | +0.064 |
films | +0.063 |
elderly | +0.062 |
orchestra | +0.062 |
Wheels | +0.061 |
Neg logit contributions | |
t | -0.056 |
don | -0.055 |
wouldn | -0.054 |
got | -0.053 |
fell | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
t | +0.026 |
don | +0.024 |
wouldn | +0.024 |
got | +0.023 |
could | +0.023 |
Neg logit contributions | |
amusement | -0.053 |
films | -0.052 |
elderly | -0.051 |
orchestra | -0.051 |
buildings | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
amusement | +0.010 |
films | +0.010 |
orchestra | +0.010 |
elderly | +0.010 |
array | +0.010 |
Neg logit contributions | |
t | -0.007 |
don | -0.007 |
got | -0.007 |
wouldn | -0.007 |
fell | -0.007 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
orchestra | +0.197 |
unison | +0.195 |
amusement | +0.195 |
films | +0.192 |
array | +0.184 |
Neg logit contributions | |
got | -0.271 |
t | -0.262 |
fell | -0.258 |
don | -0.258 |
could | -0.255 |
Token | ile |
Token ID | 576 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
amusement | +0.235 |
films | +0.228 |
orchestra | +0.224 |
elderly | +0.220 |
Wheels | +0.214 |
Neg logit contributions | |
t | -0.370 |
don | -0.351 |
got | -0.350 |
wouldn | -0.348 |
could | -0.346 |
Token | jumped |
Token ID | 11687 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
amusement | +0.067 |
films | +0.066 |
orchestra | +0.065 |
elderly | +0.065 |
Wheels | +0.064 |
Neg logit contributions | |
t | -0.024 |
got | -0.022 |
wouldn | -0.022 |
don | -0.022 |
fell | -0.021 |
Token | out |
Token ID | 503 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
t | +0.008 |
don | +0.007 |
wouldn | +0.007 |
got | +0.007 |
could | +0.007 |
Neg logit contributions | |
amusement | -0.016 |
films | -0.016 |
elderly | -0.016 |
orchestra | -0.016 |
Wheels | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
t | +0.011 |
got | +0.010 |
fell | +0.010 |
don | +0.010 |
ever | +0.010 |
Neg logit contributions | |
amusement | -0.019 |
films | -0.019 |
orchestra | -0.019 |
Wheels | -0.018 |
buildings | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
orchestra | +0.077 |
amusement | +0.077 |
films | +0.077 |
Wheels | +0.076 |
buildings | +0.074 |
Neg logit contributions | |
got | -0.045 |
don | -0.045 |
fell | -0.044 |
t | -0.044 |
wouldn | -0.042 |
Token | pond |
Token ID | 16723 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
orchestra | +0.165 |
films | +0.154 |
amusement | +0.146 |
pian | +0.143 |
unison | +0.142 |
Neg logit contributions | |
don | -0.301 |
got | -0.297 |
t | -0.295 |
fell | -0.285 |
could | -0.281 |
Token | . |
Token ID | 13 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
amusement | +0.017 |
orchestra | +0.017 |
films | +0.017 |
Wheels | +0.017 |
elderly | +0.017 |
Neg logit contributions | |
t | -0.009 |
don | -0.008 |
got | -0.008 |
wouldn | -0.008 |
could | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
orchestra | +0.002 |
amusement | +0.002 |
array | +0.002 |
youngest | +0.002 |
rhythms | +0.002 |
Neg logit contributions | |
could | -0.001 |
don | -0.001 |
t | -0.001 |
got | -0.001 |
cannot | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
t | +0.062 |
wouldn | +0.052 |
don | +0.052 |
w | +0.050 |
fell | +0.049 |
Neg logit contributions | |
amusement | -0.142 |
elderly | -0.138 |
films | -0.137 |
orchestra | -0.136 |
Wheels | -0.135 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
orchestra | +0.024 |
amusement | +0.023 |
array | +0.023 |
sym | +0.022 |
umm | +0.022 |
Neg logit contributions | |
don | -0.013 |
got | -0.012 |
could | -0.012 |
it | -0.012 |
fell | -0.012 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
orchestra | +0.169 |
films | +0.163 |
amusement | +0.154 |
unison | +0.148 |
pian | +0.146 |
Neg logit contributions | |
don | -0.293 |
got | -0.283 |
t | -0.279 |
fell | -0.277 |
could | -0.271 |
Token | ile |
Token ID | 576 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
amusement | +0.208 |
films | +0.204 |
elderly | +0.198 |
orchestra | +0.198 |
Wheels | +0.193 |
Neg logit contributions | |
t | -0.382 |
don | -0.370 |
wouldn | -0.367 |
got | -0.364 |
fell | -0.360 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
amusement | +0.061 |
films | +0.060 |
orchestra | +0.059 |
elderly | +0.059 |
Wheels | +0.058 |
Neg logit contributions | |
t | -0.031 |
don | -0.029 |
wouldn | -0.028 |
got | -0.028 |
fell | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
orchestra | +0.002 |
amusement | +0.002 |
array | +0.002 |
elderly | +0.002 |
youngest | +0.002 |
Neg logit contributions | |
don | -0.001 |
t | -0.001 |
could | -0.001 |
got | -0.001 |
fell | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
t | +0.043 |
don | +0.038 |
wouldn | +0.037 |
got | +0.033 |
w | +0.033 |
Neg logit contributions | |
amusement | -0.131 |
films | -0.129 |
elderly | -0.129 |
Wheels | -0.127 |
lions | -0.127 |
Token | still |
Token ID | 991 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
orchestra | +0.002 |
amusement | +0.002 |
films | +0.002 |
umm | +0.002 |
Wheels | +0.002 |
Neg logit contributions | |
don | -0.001 |
fell | -0.001 |
never | -0.001 |
got | -0.001 |
could | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
wouldn | +0.030 |
t | +0.030 |
don | +0.028 |
never | +0.027 |
could | +0.027 |
Neg logit contributions | |
films | -0.044 |
amusement | -0.041 |
lions | -0.041 |
elderly | -0.041 |
Wheels | -0.041 |
Token | Lily |
Token ID | 20037 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
amusement | +0.025 |
films | +0.025 |
elderly | +0.025 |
orchestra | +0.024 |
Wheels | +0.024 |
Neg logit contributions | |
t | -0.021 |
don | -0.020 |
wouldn | -0.020 |
got | -0.019 |
fell | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
elderly | +0.021 |
films | +0.021 |
amusement | +0.021 |
playground | +0.020 |
orchestra | +0.020 |
Neg logit contributions | |
t | -0.013 |
don | -0.011 |
wouldn | -0.011 |
ged | -0.011 |
w | -0.011 |
Token | Mr |
Token ID | 1770 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
amusement | +0.025 |
films | +0.024 |
elderly | +0.024 |
Wheels | +0.023 |
movies | +0.023 |
Neg logit contributions | |
t | -0.024 |
wouldn | -0.022 |
could | -0.021 |
don | -0.021 |
fell | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
amusement | +0.289 |
orchestra | +0.282 |
films | +0.281 |
elderly | +0.275 |
Wheels | +0.273 |
Neg logit contributions | |
t | -0.159 |
don | -0.153 |
wouldn | -0.148 |
got | -0.148 |
could | -0.147 |
Token | Sp |
Token ID | 1338 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
amusement | +0.120 |
orchestra | +0.118 |
array | +0.113 |
films | +0.111 |
buildings | +0.111 |
Neg logit contributions | |
don | -0.100 |
t | -0.097 |
could | -0.093 |
fell | -0.092 |
got | -0.092 |
Token | ud |
Token ID | 463 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
amusement | +0.271 |
orchestra | +0.257 |
films | +0.256 |
buildings | +0.252 |
elephants | +0.251 |
Neg logit contributions | |
t | -0.336 |
wouldn | -0.310 |
don | -0.309 |
got | -0.303 |
could | -0.303 |
Token | went |
Token ID | 1816 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
t | +0.013 |
don | +0.013 |
wouldn | +0.011 |
cannot | +0.011 |
w | +0.011 |
Neg logit contributions | |
lions | -0.030 |
elderly | -0.030 |
films | -0.030 |
youngest | -0.029 |
monkeys | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
t | +0.039 |
don | +0.038 |
wouldn | +0.037 |
w | +0.033 |
could | +0.032 |
Neg logit contributions | |
films | -0.133 |
amusement | -0.131 |
elderly | -0.131 |
lions | -0.128 |
orchestra | -0.128 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
don | +0.021 |
got | +0.020 |
t | +0.020 |
fell | +0.019 |
could | +0.019 |
Neg logit contributions | |
amusement | -0.033 |
orchestra | -0.032 |
array | -0.032 |
Wheels | -0.032 |
films | -0.032 |
Token | park |
Token ID | 3952 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
orchestra | +0.171 |
unison | +0.166 |
andel | +0.164 |
ement | +0.162 |
array | +0.158 |
Neg logit contributions | |
would | -0.293 |
got | -0.289 |
never | -0.278 |
will | -0.275 |
could | -0.274 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
amusement | +0.019 |
films | +0.019 |
orchestra | +0.019 |
elderly | +0.019 |
Wheels | +0.018 |
Neg logit contributions | |
t | -0.012 |
don | -0.011 |
wouldn | -0.011 |
got | -0.011 |
fell | -0.011 |
Token | |
Token ID | 220 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
amusement | +0.016 |
orchestra | +0.016 |
films | +0.016 |
elderly | +0.015 |
array | +0.015 |
Neg logit contributions | |
t | -0.007 |
could | -0.007 |
don | -0.007 |
got | -0.007 |
fell | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
amusement | +0.012 |
elderly | +0.012 |
films | +0.012 |
Wheels | +0.012 |
orchestra | +0.012 |
Neg logit contributions | |
t | -0.007 |
wouldn | -0.007 |
don | -0.007 |
got | -0.007 |
fell | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
amusement | +0.060 |
films | +0.059 |
elderly | +0.058 |
Wheels | +0.058 |
orchestra | +0.058 |
Neg logit contributions | |
wouldn | -0.034 |
t | -0.034 |
don | -0.033 |
got | -0.032 |
fell | -0.031 |
Token | The |
Token ID | 464 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
amusement | +0.071 |
orchestra | +0.070 |
films | +0.070 |
elderly | +0.069 |
array | +0.067 |
Neg logit contributions | |
t | -0.048 |
never | -0.042 |
don | -0.042 |
got | -0.042 |
could | -0.042 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
orchestra | +0.176 |
unison | +0.169 |
films | +0.167 |
amusement | +0.167 |
sym | +0.158 |
Neg logit contributions | |
got | -0.293 |
don | -0.288 |
t | -0.284 |
ever | -0.275 |
fell | -0.274 |
Token | ile |
Token ID | 576 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
amusement | +0.252 |
orchestra | +0.240 |
films | +0.240 |
elderly | +0.232 |
Wheels | +0.227 |
Neg logit contributions | |
t | -0.357 |
don | -0.336 |
got | -0.333 |
could | -0.330 |
wouldn | -0.329 |
Token | soon |
Token ID | 2582 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
amusement | +0.052 |
films | +0.052 |
elderly | +0.051 |
orchestra | +0.051 |
Wheels | +0.051 |
Neg logit contributions | |
t | -0.019 |
don | -0.018 |
wouldn | -0.017 |
got | -0.016 |
fell | -0.016 |
Token | found |
Token ID | 1043 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
t | +0.028 |
got | +0.026 |
don | +0.025 |
wouldn | +0.025 |
fell | +0.025 |
Neg logit contributions | |
amusement | -0.096 |
films | -0.095 |
orchestra | -0.094 |
elderly | -0.093 |
Wheels | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
got | +0.007 |
could | +0.007 |
t | +0.007 |
wouldn | +0.007 |
fell | +0.007 |
Neg logit contributions | |
orchestra | -0.013 |
films | -0.013 |
amusement | -0.013 |
Wheels | -0.013 |
array | -0.013 |
Token | friend |
Token ID | 1545 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
films | +0.118 |
amusement | +0.113 |
Wheels | +0.110 |
orchestra | +0.109 |
buildings | +0.104 |
Neg logit contributions | |
got | -0.142 |
would | -0.141 |
don | -0.140 |
t | -0.138 |
fell | -0.138 |
Token | an |
Token ID | 281 |
Feature activation | -9.90e+00 |
Pos logit contributions | |
amusement | +0.007 |
orchestra | +0.007 |
films | +0.007 |
buildings | +0.007 |
Wheels | +0.007 |
Neg logit contributions | |
got | -0.006 |
fell | -0.006 |
don | -0.006 |
t | -0.006 |
never | -0.006 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
unison | +0.134 |
Wheels | +0.133 |
films | +0.131 |
circles | +0.121 |
amusement | +0.121 |
Neg logit contributions | |
ever | -0.243 |
got | -0.239 |
fell | -0.237 |
never | -0.236 |
t | -0.235 |
Token | ich |
Token ID | 488 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
films | +0.244 |
amusement | +0.237 |
orchestra | +0.225 |
elderly | +0.217 |
Wheels | +0.217 |
Neg logit contributions | |
t | -0.337 |
w | -0.311 |
fell | -0.307 |
ever | -0.307 |
wouldn | -0.305 |
Token | . |
Token ID | 13 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
films | +0.084 |
amusement | +0.084 |
orchestra | +0.082 |
youngest | +0.081 |
elderly | +0.081 |
Neg logit contributions | |
t | -0.038 |
fell | -0.037 |
got | -0.037 |
could | -0.037 |
ever | -0.035 |
Token | The |
Token ID | 383 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
orchestra | +0.014 |
films | +0.014 |
amusement | +0.013 |
elderly | +0.013 |
array | +0.013 |
Neg logit contributions | |
t | -0.010 |
got | -0.009 |
don | -0.009 |
could | -0.009 |
fell | -0.009 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
films | +0.145 |
amusement | +0.140 |
orchestra | +0.133 |
unison | +0.127 |
Wheels | +0.124 |
Neg logit contributions | |
got | -0.294 |
t | -0.294 |
don | -0.288 |
fell | -0.287 |
never | -0.283 |
Token | ich |
Token ID | 488 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
amusement | +0.223 |
films | +0.222 |
orchestra | +0.209 |
elderly | +0.203 |
Wheels | +0.202 |
Neg logit contributions | |
t | -0.374 |
don | -0.354 |
wouldn | -0.353 |
got | -0.349 |
fell | -0.349 |
Token | has |
Token ID | 468 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
lions | +0.037 |
films | +0.037 |
buildings | +0.037 |
elephants | +0.037 |
amusement | +0.037 |
Neg logit contributions | |
t | -0.021 |
don | -0.018 |
wouldn | -0.018 |
ged | -0.017 |
got | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
t | +0.020 |
got | +0.020 |
fell | +0.020 |
don | +0.019 |
could | +0.019 |
Neg logit contributions | |
films | -0.024 |
amusement | -0.024 |
orchestra | -0.024 |
Wheels | -0.023 |
elderly | -0.023 |
Token | long |
Token ID | 890 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
amusement | +0.081 |
films | +0.079 |
orchestra | +0.077 |
elderly | +0.077 |
Wheels | +0.076 |
Neg logit contributions | |
t | -0.123 |
don | -0.119 |
wouldn | -0.118 |
got | -0.117 |
fell | -0.116 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
amusement | +0.053 |
array | +0.053 |
jungle | +0.053 |
orchestra | +0.053 |
playground | +0.053 |
Neg logit contributions | |
t | -0.197 |
wouldn | -0.189 |
don | -0.188 |
could | -0.186 |
ever | -0.182 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
amusement | +0.001 |
elderly | +0.001 |
buildings | +0.001 |
elephants | +0.001 |
films | +0.001 |
Neg logit contributions | |
t | -0.001 |
w | -0.000 |
fell | -0.000 |
ever | -0.000 |
wouldn | -0.000 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
elderly | +0.028 |
amusement | +0.027 |
jungle | +0.027 |
playground | +0.027 |
lions | +0.026 |
Neg logit contributions | |
t | -0.017 |
don | -0.014 |
ged | -0.014 |
w | -0.014 |
ever | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
t | +0.010 |
got | +0.009 |
don | +0.008 |
wouldn | +0.008 |
could | +0.008 |
Neg logit contributions | |
amusement | -0.045 |
films | -0.045 |
orchestra | -0.045 |
elderly | -0.044 |
Wheels | -0.044 |
Token | see |
Token ID | 766 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
t | +0.026 |
don | +0.024 |
wouldn | +0.024 |
got | +0.023 |
fell | +0.022 |
Neg logit contributions | |
amusement | -0.060 |
films | -0.059 |
elderly | -0.059 |
orchestra | -0.058 |
Wheels | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
it | +0.017 |
could | +0.016 |
got | +0.016 |
don | +0.016 |
would | +0.016 |
Neg logit contributions | |
orchestra | -0.036 |
umm | -0.036 |
sym | -0.035 |
amusement | -0.034 |
array | -0.034 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
unison | +0.145 |
orchestra | +0.144 |
amusement | +0.144 |
igsaw | +0.143 |
amaz | +0.138 |
Neg logit contributions | |
don | -0.321 |
would | -0.318 |
will | -0.316 |
ever | -0.305 |
can | -0.302 |
Token | iles |
Token ID | 2915 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
amusement | +0.270 |
orchestra | +0.257 |
elderly | +0.252 |
films | +0.250 |
array | +0.249 |
Neg logit contributions | |
t | -0.348 |
could | -0.315 |
don | -0.315 |
got | -0.314 |
ever | -0.314 |
Token | most |
Token ID | 749 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
amusement | +0.058 |
films | +0.058 |
elderly | +0.057 |
orchestra | +0.057 |
Wheels | +0.056 |
Neg logit contributions | |
t | -0.037 |
wouldn | -0.034 |
don | -0.034 |
got | -0.033 |
fell | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
amusement | +0.202 |
sidelines | +0.201 |
orchestra | +0.199 |
unison | +0.199 |
youngest | +0.194 |
Neg logit contributions | |
ever | -0.079 |
t | -0.076 |
could | -0.075 |
don | -0.070 |
would | -0.069 |
Token | all |
Token ID | 477 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
amusement | +0.138 |
orchestra | +0.137 |
array | +0.132 |
elderly | +0.132 |
Wheels | +0.131 |
Neg logit contributions | |
don | -0.083 |
got | -0.080 |
could | -0.078 |
t | -0.078 |
ever | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
amusement | +0.007 |
orchestra | +0.007 |
films | +0.007 |
elderly | +0.007 |
Wheels | +0.007 |
Neg logit contributions | |
t | -0.004 |
don | -0.004 |
got | -0.004 |
could | -0.004 |
wouldn | -0.004 |
Token | After |
Token ID | 3260 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
amusement | +0.065 |
films | +0.064 |
elderly | +0.063 |
orchestra | +0.063 |
Wheels | +0.062 |
Neg logit contributions | |
t | -0.054 |
don | -0.052 |
wouldn | -0.051 |
got | -0.050 |
fell | -0.050 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
t | +0.013 |
got | +0.013 |
don | +0.012 |
fell | +0.012 |
could | +0.012 |
Neg logit contributions | |
orchestra | -0.022 |
amusement | -0.022 |
films | -0.021 |
elderly | -0.021 |
array | -0.021 |
Token | my |
Token ID | 1820 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
amusement | +0.066 |
elderly | +0.065 |
jungle | +0.063 |
films | +0.062 |
lions | +0.062 |
Neg logit contributions | |
t | -0.054 |
don | -0.051 |
wouldn | -0.050 |
ged | -0.050 |
could | -0.048 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
t | +0.008 |
don | +0.008 |
wouldn | +0.008 |
w | +0.007 |
ged | +0.007 |
Neg logit contributions | |
amusement | -0.020 |
films | -0.019 |
elderly | -0.019 |
lions | -0.019 |
Wheels | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
orchestra | +0.044 |
unison | +0.043 |
Wheels | +0.042 |
array | +0.042 |
sym | +0.042 |
Neg logit contributions | |
it | -0.020 |
never | -0.020 |
got | -0.019 |
don | -0.018 |
could | -0.018 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
orchestra | +0.147 |
films | +0.140 |
unison | +0.137 |
amusement | +0.136 |
array | +0.126 |
Neg logit contributions | |
t | -0.333 |
got | -0.319 |
don | -0.316 |
fell | -0.306 |
ever | -0.305 |
Token | ile |
Token ID | 576 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
amusement | +0.231 |
orchestra | +0.220 |
films | +0.220 |
elderly | +0.217 |
Wheels | +0.210 |
Neg logit contributions | |
t | -0.369 |
don | -0.350 |
got | -0.346 |
wouldn | -0.344 |
could | -0.341 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
amusement | +0.061 |
films | +0.060 |
orchestra | +0.060 |
elderly | +0.060 |
Wheels | +0.059 |
Neg logit contributions | |
t | -0.026 |
don | -0.024 |
wouldn | -0.024 |
got | -0.024 |
fell | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
t | +0.012 |
don | +0.011 |
got | +0.011 |
wouldn | +0.011 |
could | +0.011 |
Neg logit contributions | |
amusement | -0.030 |
orchestra | -0.030 |
films | -0.030 |
elderly | -0.029 |
Wheels | -0.029 |
Token | went |
Token ID | 1816 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
t | +0.049 |
don | +0.043 |
w | +0.040 |
wouldn | +0.040 |
ged | +0.037 |
Neg logit contributions | |
amusement | -0.124 |
elderly | -0.123 |
films | -0.122 |
orchestra | -0.120 |
Wheels | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
t | +0.051 |
don | +0.050 |
wouldn | +0.050 |
w | +0.047 |
could | +0.046 |
Neg logit contributions | |
amusement | -0.110 |
elderly | -0.109 |
films | -0.106 |
orchestra | -0.105 |
playground | -0.104 |
Token | time |
Token ID | 640 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
amusement | +0.127 |
films | +0.125 |
elderly | +0.121 |
orchestra | +0.119 |
Wheels | +0.119 |
Neg logit contributions | |
t | -0.164 |
wouldn | -0.160 |
don | -0.158 |
could | -0.155 |
got | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
lions | +0.012 |
films | +0.012 |
amusement | +0.012 |
circles | +0.012 |
playground | +0.011 |
Neg logit contributions | |
wouldn | -0.012 |
t | -0.011 |
w | -0.010 |
ged | -0.010 |
would | -0.010 |
Token | there |
Token ID | 612 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
elderly | +0.094 |
moon | +0.094 |
lions | +0.093 |
films | +0.093 |
Wheels | +0.092 |
Neg logit contributions | |
t | -0.066 |
wouldn | -0.065 |
use | -0.060 |
ged | -0.055 |
w | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
t | +0.022 |
wouldn | +0.020 |
don | +0.019 |
ged | +0.019 |
w | +0.019 |
Neg logit contributions | |
amusement | -0.044 |
playground | -0.043 |
Wheels | -0.043 |
films | -0.043 |
elderly | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -8.31e+00 |
Pos logit contributions | |
orchestra | +0.138 |
amusement | +0.134 |
buildings | +0.131 |
array | +0.130 |
umm | +0.129 |
Neg logit contributions | |
got | -0.055 |
t | -0.054 |
fell | -0.053 |
ever | -0.053 |
don | -0.053 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
amusement | +0.163 |
opl | +0.160 |
circles | +0.155 |
umm | +0.153 |
buildings | +0.152 |
Neg logit contributions | |
don | -0.176 |
got | -0.173 |
fell | -0.167 |
would | -0.165 |
could | -0.164 |
Token | ile |
Token ID | 576 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
amaz | +0.326 |
amusement | +0.326 |
buildings | +0.307 |
array | +0.306 |
orchestra | +0.304 |
Neg logit contributions | |
t | -0.305 |
w | -0.287 |
ever | -0.277 |
got | -0.265 |
could | -0.264 |
Token | named |
Token ID | 3706 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
amusement | +0.108 |
films | +0.104 |
orchestra | +0.104 |
elderly | +0.102 |
Wheels | +0.102 |
Neg logit contributions | |
t | -0.069 |
got | -0.065 |
could | -0.064 |
don | -0.064 |
fell | -0.064 |
Token | Jim |
Token ID | 5395 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
orchestra | +0.112 |
amusement | +0.109 |
films | +0.105 |
array | +0.104 |
rhythms | +0.103 |
Neg logit contributions | |
don | -0.068 |
t | -0.068 |
could | -0.064 |
got | -0.064 |
fell | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
films | +0.042 |
lions | +0.042 |
amusement | +0.041 |
moon | +0.041 |
jungle | +0.041 |
Neg logit contributions | |
t | -0.044 |
wouldn | -0.040 |
don | -0.040 |
ged | -0.037 |
fell | -0.037 |
Token | Jim |
Token ID | 5395 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
amusement | +0.036 |
films | +0.035 |
elderly | +0.034 |
buildings | +0.033 |
lions | +0.033 |
Neg logit contributions | |
t | -0.055 |
wouldn | -0.053 |
don | -0.053 |
got | -0.051 |
fell | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
t | +0.024 |
don | +0.023 |
wouldn | +0.022 |
got | +0.022 |
fell | +0.022 |
Neg logit contributions | |
amusement | -0.039 |
films | -0.039 |
elderly | -0.038 |
orchestra | -0.038 |
Wheels | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
t | +0.008 |
don | +0.008 |
wouldn | +0.007 |
got | +0.007 |
could | +0.007 |
Neg logit contributions | |
amusement | -0.010 |
films | -0.010 |
orchestra | -0.010 |
elderly | -0.010 |
Wheels | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
amusement | +0.053 |
elderly | +0.052 |
Wheels | +0.051 |
jungle | +0.051 |
films | +0.051 |
Neg logit contributions | |
wouldn | -0.040 |
don | -0.038 |
t | -0.037 |
got | -0.037 |
fell | -0.035 |
Token | Bill |
Token ID | 17798 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
amusement | +0.057 |
elderly | +0.054 |
films | +0.054 |
orchestra | +0.053 |
Wheels | +0.053 |
Neg logit contributions | |
t | -0.055 |
don | -0.054 |
wouldn | -0.054 |
got | -0.052 |
fell | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
t | +0.003 |
don | +0.002 |
wouldn | +0.002 |
got | +0.002 |
fell | +0.002 |
Neg logit contributions | |
amusement | -0.007 |
films | -0.007 |
elderly | -0.007 |
orchestra | -0.007 |
Wheels | -0.007 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
unison | +0.207 |
films | +0.199 |
ement | +0.196 |
amusement | +0.195 |
umm | +0.193 |
Neg logit contributions | |
never | -0.240 |
would | -0.236 |
got | -0.234 |
ever | -0.234 |
don | -0.232 |
Token | ich |
Token ID | 488 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
amusement | +0.235 |
films | +0.231 |
orchestra | +0.220 |
Wheels | +0.210 |
elderly | +0.209 |
Neg logit contributions | |
t | -0.363 |
wouldn | -0.340 |
don | -0.340 |
w | -0.338 |
got | -0.335 |
Token | was |
Token ID | 373 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
amusement | +0.045 |
films | +0.045 |
orchestra | +0.044 |
elderly | +0.044 |
Wheels | +0.044 |
Neg logit contributions | |
t | -0.014 |
wouldn | -0.013 |
don | -0.013 |
got | -0.013 |
fell | -0.013 |
Token | now |
Token ID | 783 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
never | +0.011 |
got | +0.011 |
fell | +0.010 |
t | +0.010 |
ever | +0.010 |
Neg logit contributions | |
films | -0.021 |
umm | -0.021 |
amusement | -0.021 |
buildings | -0.020 |
Wheels | -0.020 |
Token | even |
Token ID | 772 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
t | +0.081 |
don | +0.078 |
got | +0.078 |
wouldn | +0.078 |
fell | +0.077 |
Neg logit contributions | |
amusement | -0.106 |
films | -0.105 |
orchestra | -0.102 |
Wheels | -0.102 |
buildings | -0.100 |
Token | gr |
Token ID | 1036 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
got | +0.068 |
wouldn | +0.068 |
don | +0.067 |
t | +0.066 |
could | +0.066 |
Neg logit contributions | |
amusement | -0.065 |
films | -0.065 |
orchestra | -0.063 |
Wheels | -0.063 |
array | -0.062 |
Token | One |
Token ID | 3198 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
amusement | +0.086 |
films | +0.085 |
elderly | +0.084 |
orchestra | +0.084 |
Wheels | +0.083 |
Neg logit contributions | |
t | -0.049 |
don | -0.046 |
wouldn | -0.045 |
got | -0.044 |
fell | -0.044 |
Token | day |
Token ID | 1110 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
films | +0.125 |
orchestra | +0.124 |
buildings | +0.123 |
elephants | +0.121 |
amusement | +0.121 |
Neg logit contributions | |
got | -0.069 |
t | -0.069 |
fell | -0.065 |
ever | -0.064 |
would | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
wouldn | +0.031 |
t | +0.028 |
don | +0.028 |
will | +0.028 |
never | +0.028 |
Neg logit contributions | |
films | -0.032 |
playground | -0.032 |
woodland | -0.031 |
amusement | -0.031 |
elderly | -0.031 |
Token | Sammy |
Token ID | 44067 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
amusement | +0.041 |
elderly | +0.040 |
playground | +0.039 |
woodland | +0.038 |
moon | +0.038 |
Neg logit contributions | |
wouldn | -0.049 |
t | -0.048 |
use | -0.046 |
don | -0.045 |
w | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
playground | +0.011 |
amusement | +0.011 |
jungle | +0.011 |
elderly | +0.011 |
moon | +0.011 |
Neg logit contributions | |
t | -0.008 |
wouldn | -0.006 |
don | -0.006 |
w | -0.006 |
ged | -0.005 |
Token | crocod |
Token ID | 37565 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
unison | +0.169 |
amusement | +0.160 |
orchestra | +0.155 |
array | +0.154 |
amaz | +0.153 |
Neg logit contributions | |
would | -0.270 |
t | -0.269 |
don | -0.268 |
could | -0.263 |
got | -0.263 |
Token | ile |
Token ID | 576 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
amusement | +0.295 |
orchestra | +0.282 |
films | +0.275 |
array | +0.275 |
amaz | +0.273 |
Neg logit contributions | |
t | -0.324 |
w | -0.296 |
got | -0.292 |
could | -0.292 |
ever | -0.289 |
Token | was |
Token ID | 373 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
films | +0.083 |
amusement | +0.083 |
jungle | +0.083 |
elderly | +0.082 |
lions | +0.082 |
Neg logit contributions | |
t | -0.033 |
don | -0.030 |
wouldn | -0.028 |
ged | -0.026 |
w | -0.025 |
Token | hanging |
Token ID | 10938 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
amusement | +0.006 |
orchestra | +0.006 |
films | +0.006 |
Wheels | +0.006 |
elderly | +0.006 |
Neg logit contributions | |
t | -0.004 |
got | -0.004 |
don | -0.003 |
wouldn | -0.003 |
fell | -0.003 |
Token | out |
Token ID | 503 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
amusement | +0.023 |
films | +0.023 |
elderly | +0.022 |
orchestra | +0.022 |
Wheels | +0.022 |
Neg logit contributions | |
t | -0.012 |
don | -0.012 |
wouldn | -0.011 |
got | -0.011 |
fell | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
amusement | +0.000 |
orchestra | +0.000 |
films | +0.000 |
Wheels | +0.000 |
elderly | +0.000 |
Neg logit contributions | |
t | -0.000 |
got | -0.000 |
could | -0.000 |
fell | -0.000 |
wouldn | -0.000 |
Token | |
Token ID | 220 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
amusement | +0.012 |
films | +0.012 |
orchestra | +0.012 |
array | +0.012 |
elderly | +0.012 |
Neg logit contributions | |
t | -0.007 |
could | -0.006 |
got | -0.006 |
fell | -0.006 |
don | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
elderly | +0.002 |
Wheels | +0.002 |
films | +0.002 |
circles | +0.002 |
amusement | +0.002 |
Neg logit contributions | |
wouldn | -0.001 |
t | -0.001 |
got | -0.001 |
w | -0.001 |
don | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
amusement | +0.055 |
films | +0.054 |
elderly | +0.054 |
Wheels | +0.053 |
orchestra | +0.053 |
Neg logit contributions | |
wouldn | -0.033 |
t | -0.032 |
don | -0.032 |
got | -0.030 |
fell | -0.030 |
Token | The |
Token ID | 464 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
films | +0.064 |
orchestra | +0.062 |
amusement | +0.062 |
umm | +0.060 |
lions | +0.060 |
Neg logit contributions | |
t | -0.048 |
got | -0.045 |
could | -0.044 |
never | -0.043 |
don | -0.043 |
Token | hipp |
Token ID | 18568 |
Feature activation | -8.98e+00 |
Pos logit contributions | |
orchestra | +0.143 |
amusement | +0.138 |
films | +0.135 |
unison | +0.134 |
rhythms | +0.132 |
Neg logit contributions | |
got | -0.293 |
t | -0.285 |
don | -0.285 |
ever | -0.274 |
never | -0.272 |
Token | opot |
Token ID | 43372 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
amusement | +0.307 |
films | +0.305 |
orchestra | +0.303 |
elderly | +0.297 |
Wheels | +0.295 |
Neg logit contributions | |
t | -0.056 |
got | -0.047 |
could | -0.045 |
don | -0.045 |
wouldn | -0.043 |
Token | amus |
Token ID | 25509 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
amusement | +0.206 |
films | +0.197 |
orchestra | +0.192 |
elderly | +0.180 |
playground | +0.179 |
Neg logit contributions | |
t | -0.373 |
wouldn | -0.356 |
don | -0.355 |
ever | -0.354 |
got | -0.354 |
Token | smiled |
Token ID | 13541 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
amusement | +0.067 |
films | +0.066 |
elderly | +0.066 |
orchestra | +0.065 |
Wheels | +0.065 |
Neg logit contributions | |
t | -0.022 |
don | -0.020 |
wouldn | -0.019 |
got | -0.018 |
fell | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
t | +0.010 |
don | +0.009 |
wouldn | +0.009 |
got | +0.009 |
could | +0.009 |
Neg logit contributions | |
amusement | -0.024 |
films | -0.024 |
orchestra | -0.024 |
Wheels | -0.023 |
elderly | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
t | +0.038 |
w | +0.034 |
don | +0.034 |
wouldn | +0.033 |
ever | +0.032 |
Neg logit contributions | |
elderly | -0.049 |
amusement | -0.048 |
array | -0.047 |
orchestra | -0.047 |
films | -0.046 |
Token | then |
Token ID | 788 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
t | +0.032 |
don | +0.029 |
wouldn | +0.029 |
got | +0.028 |
fell | +0.027 |
Neg logit contributions | |
amusement | -0.084 |
films | -0.083 |
elderly | -0.082 |
orchestra | -0.081 |
Wheels | -0.081 |
Token | they |
Token ID | 484 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
t | +0.053 |
don | +0.049 |
wouldn | +0.048 |
got | +0.047 |
fell | +0.046 |
Neg logit contributions | |
amusement | -0.154 |
films | -0.153 |
orchestra | -0.151 |
elderly | -0.150 |
Wheels | -0.149 |
Token | arrived |
Token ID | 5284 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
t | +0.046 |
don | +0.044 |
wouldn | +0.043 |
w | +0.043 |
ged | +0.039 |
Neg logit contributions | |
amusement | -0.094 |
elderly | -0.086 |
playground | -0.086 |
Wheels | -0.085 |
lions | -0.084 |
Token | home |
Token ID | 1363 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
t | +0.000 |
don | +0.000 |
wouldn | +0.000 |
got | +0.000 |
could | +0.000 |
Neg logit contributions | |
amusement | -0.001 |
elderly | -0.001 |
films | -0.001 |
orchestra | -0.001 |
buildings | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
t | +0.057 |
don | +0.052 |
wouldn | +0.052 |
w | +0.050 |
got | +0.049 |
Neg logit contributions | |
amusement | -0.116 |
elderly | -0.116 |
films | -0.113 |
orchestra | -0.113 |
buildings | -0.112 |
Token | A |
Token ID | 317 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
don | +0.014 |
t | +0.014 |
wouldn | +0.014 |
got | +0.014 |
could | +0.014 |
Neg logit contributions | |
films | -0.025 |
amusement | -0.025 |
orchestra | -0.025 |
Wheels | -0.024 |
lions | -0.024 |
Token | str |
Token ID | 2536 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
films | +0.097 |
structures | +0.088 |
orchestra | +0.087 |
opl | +0.087 |
buildings | +0.086 |
Neg logit contributions | |
got | -0.125 |
would | -0.117 |
could | -0.114 |
don | -0.114 |
fell | -0.113 |
Token | id |
Token ID | 312 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
amusement | +0.261 |
films | +0.261 |
orchestra | +0.251 |
elderly | +0.244 |
Wheels | +0.243 |
Neg logit contributions | |
t | -0.325 |
wouldn | -0.309 |
don | -0.309 |
got | -0.305 |
fell | -0.302 |
Token | put |
Token ID | 1234 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
amusement | +0.106 |
elderly | +0.103 |
orchestra | +0.102 |
films | +0.102 |
lions | +0.100 |
Neg logit contributions | |
t | -0.070 |
don | -0.067 |
wouldn | -0.065 |
could | -0.063 |
fell | -0.063 |
Token | her |
Token ID | 607 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
amusement | +0.013 |
elderly | +0.013 |
films | +0.013 |
orchestra | +0.013 |
Wheels | +0.013 |
Neg logit contributions | |
t | -0.005 |
don | -0.004 |
wouldn | -0.004 |
got | -0.004 |
could | -0.004 |
Token | balloon |
Token ID | 21190 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
films | +0.101 |
orchestra | +0.101 |
amusement | +0.100 |
Wheels | +0.096 |
lions | +0.093 |
Neg logit contributions | |
t | -0.137 |
got | -0.136 |
don | -0.136 |
fell | -0.133 |
wouldn | -0.132 |
Token | in |
Token ID | 287 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
t | +0.011 |
don | +0.010 |
wouldn | +0.010 |
got | +0.010 |
could | +0.010 |
Neg logit contributions | |
amusement | -0.027 |
films | -0.026 |
elderly | -0.026 |
orchestra | -0.026 |
Wheels | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
t | +0.073 |
don | +0.071 |
wouldn | +0.069 |
got | +0.068 |
fell | +0.067 |
Neg logit contributions | |
amusement | -0.122 |
films | -0.120 |
orchestra | -0.119 |
elderly | -0.118 |
Wheels | -0.117 |
Token | It |
Token ID | 632 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
could | +0.005 |
don | +0.005 |
t | +0.005 |
got | +0.005 |
wouldn | +0.005 |
Neg logit contributions | |
amusement | -0.009 |
orchestra | -0.008 |
lions | -0.008 |
films | -0.008 |
playground | -0.008 |
Token | polished |
Token ID | 23895 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
t | +0.056 |
don | +0.048 |
w | +0.046 |
ged | +0.043 |
wouldn | +0.043 |
Neg logit contributions | |
amusement | -0.139 |
elderly | -0.139 |
orchestra | -0.137 |
moon | -0.137 |
films | -0.136 |
Token | everything |
Token ID | 2279 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
t | +0.020 |
don | +0.020 |
wouldn | +0.019 |
got | +0.019 |
could | +0.019 |
Neg logit contributions | |
amusement | -0.036 |
films | -0.035 |
orchestra | -0.035 |
elderly | -0.035 |
Wheels | -0.035 |
Token | it |
Token ID | 340 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
t | +0.054 |
don | +0.050 |
w | +0.049 |
got | +0.047 |
wouldn | +0.047 |
Neg logit contributions | |
films | -0.112 |
amusement | -0.112 |
elderly | -0.112 |
buildings | -0.111 |
circles | -0.111 |
Token | could |
Token ID | 714 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
t | +0.076 |
w | +0.072 |
don | +0.067 |
ged | +0.066 |
wouldn | +0.060 |
Neg logit contributions | |
moon | -0.123 |
circles | -0.122 |
buildings | -0.120 |
films | -0.119 |
elderly | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
t | +0.123 |
w | +0.122 |
ged | +0.119 |
wouldn | +0.117 |
don | +0.111 |
Neg logit contributions | |
elderly | -0.174 |
amusement | -0.174 |
moon | -0.171 |
orchestra | -0.168 |
array | -0.165 |
Token | It |
Token ID | 632 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
could | +0.009 |
t | +0.009 |
don | +0.008 |
got | +0.008 |
wouldn | +0.008 |
Neg logit contributions | |
amusement | -0.012 |
orchestra | -0.011 |
films | -0.011 |
elderly | -0.011 |
lions | -0.011 |
Token | made |
Token ID | 925 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
t | +0.066 |
don | +0.057 |
w | +0.055 |
ged | +0.053 |
wouldn | +0.050 |
Neg logit contributions | |
elderly | -0.144 |
amusement | -0.144 |
moon | -0.144 |
orchestra | -0.143 |
films | -0.141 |
Token | them |
Token ID | 606 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
it | +0.030 |
don | +0.030 |
got | +0.028 |
ever | +0.027 |
could | +0.027 |
Neg logit contributions | |
amusement | -0.065 |
orchestra | -0.062 |
playground | -0.061 |
films | -0.060 |
Wheels | -0.060 |
Token | all |
Token ID | 477 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
t | +0.070 |
don | +0.065 |
wouldn | +0.065 |
got | +0.063 |
fell | +0.062 |
Neg logit contributions | |
amusement | -0.102 |
films | -0.101 |
elderly | -0.100 |
orchestra | -0.099 |
Wheels | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
t | +0.029 |
don | +0.027 |
wouldn | +0.026 |
got | +0.026 |
fell | +0.025 |
Neg logit contributions | |
amusement | -0.061 |
films | -0.061 |
elderly | -0.059 |
orchestra | -0.059 |
Wheels | -0.059 |
Token | tea |
Token ID | 8887 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
amusement | +0.196 |
orchestra | +0.177 |
array | +0.169 |
unison | +0.168 |
films | +0.167 |
Neg logit contributions | |
don | -0.253 |
got | -0.247 |
would | -0.246 |
will | -0.245 |
fell | -0.242 |
Token | bag |
Token ID | 6131 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
amusement | +0.026 |
films | +0.025 |
orchestra | +0.025 |
elderly | +0.025 |
Wheels | +0.024 |
Neg logit contributions | |
t | -0.020 |
don | -0.019 |
wouldn | -0.019 |
got | -0.019 |
could | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
don | +0.044 |
t | +0.043 |
wouldn | +0.043 |
ged | +0.042 |
got | +0.041 |
Neg logit contributions | |
elderly | -0.069 |
amusement | -0.066 |
films | -0.066 |
buildings | -0.065 |
orchestra | -0.065 |
Token | it |
Token ID | 340 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
t | +0.031 |
ged | +0.028 |
got | +0.027 |
wouldn | +0.026 |
fell | +0.025 |
Neg logit contributions | |
elderly | -0.065 |
films | -0.063 |
amusement | -0.062 |
Wheels | -0.062 |
moon | -0.062 |
Token | will |
Token ID | 481 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
ged | +0.082 |
t | +0.071 |
w | +0.060 |
ever | +0.055 |
mar | +0.052 |
Neg logit contributions | |
moon | -0.165 |
Wheels | -0.164 |
younger | -0.164 |
films | -0.163 |
swings | -0.161 |
Token | be |
Token ID | 307 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ged | +0.140 |
t | +0.126 |
w | +0.123 |
wouldn | +0.120 |
could | +0.115 |
Neg logit contributions | |
elderly | -0.181 |
moon | -0.178 |
amusement | -0.177 |
Wheels | -0.171 |
orchestra | -0.171 |
Token | less |
Token ID | 1342 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
t | +0.037 |
don | +0.034 |
wouldn | +0.034 |
got | +0.033 |
fell | +0.033 |
Neg logit contributions | |
amusement | -0.030 |
films | -0.030 |
elderly | -0.030 |
orchestra | -0.029 |
Wheels | -0.029 |
Token | thick |
Token ID | 6546 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
t | +0.010 |
don | +0.010 |
wouldn | +0.010 |
got | +0.010 |
fell | +0.009 |
Neg logit contributions | |
amusement | -0.008 |
films | -0.008 |
orchestra | -0.008 |
elderly | -0.008 |
Wheels | -0.008 |
Token | ." |
Token ID | 526 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
films | +0.068 |
amusement | +0.067 |
elderly | +0.066 |
orchestra | +0.066 |
buildings | +0.065 |
Neg logit contributions | |
t | -0.041 |
don | -0.038 |
wouldn | -0.038 |
got | -0.038 |
fell | -0.037 |
Token | |
Token ID | 220 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
t | +0.014 |
don | +0.013 |
wouldn | +0.013 |
got | +0.013 |
fell | +0.012 |
Neg logit contributions | |
amusement | -0.026 |
films | -0.025 |
elderly | -0.025 |
orchestra | -0.025 |
Wheels | -0.025 |
Token | do |
Token ID | 466 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
ged | +0.056 |
t | +0.055 |
w | +0.047 |
wouldn | +0.047 |
fell | +0.046 |
Neg logit contributions | |
elderly | -0.131 |
amusement | -0.125 |
orchestra | -0.125 |
Wheels | -0.123 |
playground | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
t | +0.055 |
fell | +0.049 |
wouldn | +0.049 |
got | +0.049 |
don | +0.048 |
Neg logit contributions | |
films | -0.091 |
elderly | -0.090 |
amusement | -0.090 |
orchestra | -0.089 |
buildings | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
don | +0.019 |
wouldn | +0.018 |
t | +0.018 |
could | +0.018 |
would | +0.017 |
Neg logit contributions | |
amusement | -0.026 |
films | -0.026 |
orchestra | -0.025 |
Wheels | -0.025 |
array | -0.025 |
Token | then |
Token ID | 788 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
t | +0.035 |
wouldn | +0.029 |
got | +0.029 |
ged | +0.029 |
w | +0.029 |
Neg logit contributions | |
amusement | -0.072 |
elderly | -0.071 |
films | -0.071 |
orchestra | -0.070 |
buildings | -0.069 |
Token | you |
Token ID | 345 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
t | +0.071 |
ged | +0.058 |
wouldn | +0.056 |
w | +0.056 |
got | +0.055 |
Neg logit contributions | |
amusement | -0.155 |
films | -0.152 |
elderly | -0.151 |
orchestra | -0.150 |
buildings | -0.148 |
Token | can |
Token ID | 460 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
t | +0.034 |
ged | +0.028 |
wouldn | +0.027 |
got | +0.026 |
fell | +0.026 |
Neg logit contributions | |
amusement | -0.132 |
elderly | -0.130 |
films | -0.130 |
Wheels | -0.129 |
orchestra | -0.129 |
Token | quit |
Token ID | 11238 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
t | +0.117 |
wouldn | +0.109 |
ged | +0.107 |
don | +0.105 |
got | +0.104 |
Neg logit contributions | |
amusement | -0.182 |
elderly | -0.179 |
orchestra | -0.178 |
films | -0.177 |
Wheels | -0.175 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
t | +0.077 |
don | +0.074 |
wouldn | +0.072 |
got | +0.071 |
fell | +0.070 |
Neg logit contributions | |
amusement | -0.110 |
films | -0.108 |
orchestra | -0.107 |
elderly | -0.107 |
Wheels | -0.105 |
Token | It |
Token ID | 632 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
t | +0.021 |
don | +0.021 |
wouldn | +0.020 |
could | +0.020 |
got | +0.019 |
Neg logit contributions | |
amusement | -0.033 |
films | -0.033 |
orchestra | -0.032 |
elderly | -0.032 |
buildings | -0.032 |
Token | might |
Token ID | 1244 |
Feature activation | +6.71e+00 |
Pos logit contributions | |
ged | +0.085 |
t | +0.080 |
w | +0.068 |
don | +0.066 |
fell | +0.065 |
Neg logit contributions | |
elderly | -0.152 |
Wheels | -0.151 |
moon | -0.150 |
films | -0.150 |
younger | -0.149 |
Token | make |
Token ID | 787 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ged | +0.093 |
t | +0.092 |
wouldn | +0.086 |
could | +0.084 |
got | +0.082 |
Neg logit contributions | |
amusement | -0.166 |
elderly | -0.165 |
orchestra | -0.160 |
Wheels | -0.158 |
films | -0.158 |
Token | to |
Token ID | 284 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
t | +0.041 |
don | +0.041 |
w | +0.039 |
wouldn | +0.039 |
fell | +0.038 |
Neg logit contributions | |
elderly | -0.078 |
amusement | -0.078 |
orchestra | -0.075 |
films | -0.075 |
playground | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
t | +0.032 |
don | +0.031 |
got | +0.031 |
wouldn | +0.030 |
could | +0.030 |
Neg logit contributions | |
amusement | -0.048 |
films | -0.047 |
orchestra | -0.047 |
Wheels | -0.046 |
elderly | -0.046 |
Token | laundry |
Token ID | 25724 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
andel | +0.203 |
motions | +0.192 |
rhythms | +0.191 |
films | +0.189 |
flashes | +0.187 |
Neg logit contributions | |
would | -0.246 |
never | -0.240 |
got | -0.233 |
will | -0.232 |
ever | -0.221 |
Token | so |
Token ID | 523 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
t | +0.008 |
got | +0.007 |
wouldn | +0.007 |
don | +0.007 |
could | +0.007 |
Neg logit contributions | |
amusement | -0.008 |
films | -0.008 |
Wheels | -0.008 |
orchestra | -0.008 |
elderly | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
t | +0.008 |
don | +0.007 |
wouldn | +0.007 |
got | +0.007 |
fell | +0.007 |
Neg logit contributions | |
amusement | -0.026 |
elderly | -0.025 |
films | -0.025 |
orchestra | -0.025 |
Wheels | -0.025 |
Token | could |
Token ID | 714 |
Feature activation | +7.53e+00 |
Pos logit contributions | |
t | +0.046 |
w | +0.043 |
ged | +0.039 |
don | +0.037 |
use | +0.031 |
Neg logit contributions | |
elderly | -0.143 |
youngest | -0.140 |
orchestra | -0.138 |
films | -0.137 |
moon | -0.137 |
Token | wash |
Token ID | 13502 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
w | +0.116 |
ged | +0.114 |
t | +0.113 |
wouldn | +0.108 |
fell | +0.100 |
Neg logit contributions | |
amusement | -0.181 |
elderly | -0.175 |
playground | -0.172 |
orchestra | -0.171 |
films | -0.170 |
Token | them |
Token ID | 606 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
t | +0.029 |
don | +0.026 |
wouldn | +0.026 |
fell | +0.025 |
got | +0.025 |
Neg logit contributions | |
films | -0.066 |
amusement | -0.066 |
elderly | -0.064 |
orchestra | -0.064 |
Wheels | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
t | +0.040 |
don | +0.036 |
wouldn | +0.036 |
got | +0.035 |
fell | +0.035 |
Neg logit contributions | |
amusement | -0.068 |
films | -0.067 |
elderly | -0.067 |
orchestra | -0.065 |
buildings | -0.065 |
Token | |
Token ID | 220 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
amusement | +0.010 |
films | +0.009 |
orchestra | +0.009 |
elderly | +0.009 |
Wheels | +0.009 |
Neg logit contributions | |
t | -0.006 |
don | -0.006 |
got | -0.006 |
wouldn | -0.006 |
could | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
amusement | +0.004 |
films | +0.004 |
elderly | +0.004 |
Wheels | +0.004 |
orchestra | +0.004 |
Neg logit contributions | |
t | -0.002 |
wouldn | -0.002 |
don | -0.002 |
got | -0.002 |
fell | -0.002 |
Token | ran |
Token ID | 4966 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
amusement | +0.045 |
films | +0.045 |
elderly | +0.044 |
orchestra | +0.044 |
Wheels | +0.044 |
Neg logit contributions | |
t | -0.016 |
don | -0.015 |
wouldn | -0.014 |
got | -0.014 |
fell | -0.014 |
Token | as |
Token ID | 355 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
t | +0.050 |
don | +0.047 |
wouldn | +0.046 |
got | +0.044 |
could | +0.043 |
Neg logit contributions | |
amusement | -0.129 |
films | -0.126 |
elderly | -0.125 |
orchestra | -0.125 |
Wheels | -0.123 |
Token | fast |
Token ID | 3049 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
t | +0.084 |
don | +0.079 |
wouldn | +0.078 |
got | +0.077 |
fell | +0.075 |
Neg logit contributions | |
amusement | -0.141 |
films | -0.139 |
elderly | -0.137 |
orchestra | -0.137 |
Wheels | -0.135 |
Token | as |
Token ID | 355 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
amusement | +0.012 |
films | +0.012 |
buildings | +0.012 |
elderly | +0.012 |
lions | +0.012 |
Neg logit contributions | |
t | -0.008 |
wouldn | -0.007 |
don | -0.007 |
w | -0.007 |
could | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
t | +0.040 |
don | +0.037 |
could | +0.035 |
wouldn | +0.035 |
fell | +0.034 |
Neg logit contributions | |
amusement | -0.163 |
films | -0.161 |
orchestra | -0.159 |
Wheels | -0.157 |
elderly | -0.156 |
Token | could |
Token ID | 714 |
Feature activation | +7.56e+00 |
Pos logit contributions | |
t | +0.024 |
w | +0.022 |
don | +0.020 |
use | +0.013 |
wouldn | +0.013 |
Neg logit contributions | |
elderly | -0.142 |
circles | -0.140 |
monkeys | -0.140 |
moon | -0.140 |
Wheels | -0.140 |
Token | to |
Token ID | 284 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
w | +0.141 |
t | +0.123 |
wouldn | +0.122 |
don | +0.122 |
use | +0.117 |
Neg logit contributions | |
circles | -0.157 |
playground | -0.152 |
amusement | -0.151 |
elderly | -0.149 |
moon | -0.146 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
got | +0.017 |
don | +0.017 |
fell | +0.016 |
t | +0.015 |
wouldn | +0.015 |
Neg logit contributions | |
films | -0.055 |
orchestra | -0.054 |
Wheels | -0.054 |
amusement | -0.054 |
elderly | -0.053 |
Token | red |
Token ID | 2266 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
films | +0.155 |
Wheels | +0.154 |
orchestra | +0.152 |
ement | +0.150 |
sym | +0.145 |
Neg logit contributions | |
would | -0.266 |
never | -0.263 |
will | -0.257 |
got | -0.246 |
soon | -0.246 |
Token | barn |
Token ID | 25203 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
orchestra | +0.125 |
amusement | +0.122 |
elderly | +0.116 |
films | +0.115 |
Wheels | +0.113 |
Neg logit contributions | |
got | -0.218 |
t | -0.213 |
would | -0.211 |
fell | -0.204 |
wouldn | -0.203 |
Token | and |
Token ID | 290 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
t | +0.022 |
got | +0.020 |
wouldn | +0.020 |
could | +0.020 |
fell | +0.020 |
Neg logit contributions | |
films | -0.042 |
amusement | -0.042 |
orchestra | -0.041 |
Wheels | -0.041 |
elderly | -0.040 |
Token | started |
Token ID | 2067 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
t | +0.047 |
don | +0.044 |
wouldn | +0.042 |
got | +0.040 |
fell | +0.040 |
Neg logit contributions | |
amusement | -0.121 |
films | -0.118 |
elderly | -0.117 |
orchestra | -0.117 |
Wheels | -0.116 |
Token | to |
Token ID | 284 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
t | +0.025 |
don | +0.021 |
wouldn | +0.021 |
got | +0.020 |
could | +0.019 |
Neg logit contributions | |
amusement | -0.122 |
films | -0.120 |
elderly | -0.119 |
orchestra | -0.119 |
Wheels | -0.118 |
Token | melt |
Token ID | 16867 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
don | +0.032 |
got | +0.030 |
wouldn | +0.030 |
fell | +0.030 |
t | +0.029 |
Neg logit contributions | |
films | -0.065 |
orchestra | -0.064 |
amusement | -0.064 |
elderly | -0.063 |
Wheels | -0.063 |
Token | through |
Token ID | 832 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
don | +0.013 |
wouldn | +0.013 |
got | +0.013 |
t | +0.012 |
fell | +0.012 |
Neg logit contributions | |
amusement | -0.030 |
films | -0.030 |
orchestra | -0.029 |
Wheels | -0.029 |
elderly | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
orchestra | +0.034 |
films | +0.033 |
Wheels | +0.033 |
amusement | +0.032 |
elderly | +0.032 |
Neg logit contributions | |
it | -0.016 |
got | -0.015 |
don | -0.015 |
ever | -0.015 |
fell | -0.015 |
Token | ! |
Token ID | 0 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
t | +0.047 |
wouldn | +0.043 |
don | +0.043 |
got | +0.043 |
fell | +0.042 |
Neg logit contributions | |
amusement | -0.096 |
films | -0.095 |
orchestra | -0.094 |
Wheels | -0.093 |
elderly | -0.092 |
Token | The |
Token ID | 383 |
Feature activation | -9.94e+00 |
Pos logit contributions | |
t | +0.002 |
could | +0.002 |
don | +0.002 |
got | +0.002 |
fell | +0.002 |
Neg logit contributions | |
amusement | -0.005 |
films | -0.004 |
orchestra | -0.004 |
elderly | -0.004 |
array | -0.004 |
Token | cold |
Token ID | 4692 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
films | +0.189 |
orchestra | +0.187 |
amusement | +0.175 |
campus | +0.171 |
sym | +0.170 |
Neg logit contributions | |
got | -0.217 |
don | -0.214 |
fell | -0.204 |
could | -0.202 |
tried | -0.200 |
Token | water |
Token ID | 1660 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
amusement | +0.087 |
films | +0.087 |
orchestra | +0.085 |
Wheels | +0.081 |
elderly | +0.081 |
Neg logit contributions | |
t | -0.138 |
got | -0.134 |
don | -0.132 |
fell | -0.131 |
wouldn | -0.130 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
t | +0.014 |
don | +0.013 |
wouldn | +0.012 |
got | +0.012 |
could | +0.011 |
Neg logit contributions | |
amusement | -0.039 |
films | -0.038 |
elderly | -0.038 |
orchestra | -0.038 |
Wheels | -0.038 |
Token | strange |
Token ID | 6283 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
t | +0.006 |
don | +0.006 |
wouldn | +0.006 |
got | +0.006 |
fell | +0.006 |
Neg logit contributions | |
amusement | -0.007 |
films | -0.007 |
elderly | -0.007 |
orchestra | -0.007 |
Wheels | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
amusement | +0.048 |
orchestra | +0.048 |
films | +0.047 |
Wheels | +0.047 |
elderly | +0.047 |
Neg logit contributions | |
t | -0.033 |
don | -0.032 |
got | -0.032 |
could | -0.030 |
wouldn | -0.030 |
Token | mail |
Token ID | 6920 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
amusement | +0.157 |
films | +0.152 |
orchestra | +0.151 |
elderly | +0.148 |
Wheels | +0.146 |
Neg logit contributions | |
t | -0.265 |
don | -0.256 |
got | -0.255 |
wouldn | -0.253 |
could | -0.250 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
amusement | +0.010 |
films | +0.009 |
orchestra | +0.009 |
elderly | +0.009 |
Wheels | +0.009 |
Neg logit contributions | |
t | -0.006 |
wouldn | -0.005 |
got | -0.005 |
could | -0.005 |
don | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
orchestra | +0.030 |
amusement | +0.030 |
films | +0.030 |
elderly | +0.029 |
array | +0.028 |
Neg logit contributions | |
t | -0.017 |
don | -0.016 |
could | -0.016 |
got | -0.016 |
would | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
amusement | +0.092 |
films | +0.091 |
orchestra | +0.090 |
elderly | +0.088 |
Wheels | +0.088 |
Neg logit contributions | |
t | -0.072 |
don | -0.067 |
got | -0.067 |
wouldn | -0.067 |
fell | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
wouldn | +0.058 |
ried | +0.056 |
use | +0.054 |
never | +0.054 |
don | +0.053 |
Neg logit contributions | |
lions | -0.048 |
buildings | -0.048 |
monkeys | -0.048 |
jungle | -0.048 |
amusement | -0.047 |
Token | he |
Token ID | 339 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
amusement | +0.009 |
elderly | +0.009 |
films | +0.009 |
buildings | +0.009 |
moon | +0.009 |
Neg logit contributions | |
t | -0.008 |
wouldn | -0.008 |
use | -0.008 |
don | -0.008 |
w | -0.008 |
Token | got |
Token ID | 1392 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
t | +0.060 |
don | +0.051 |
ged | +0.051 |
w | +0.050 |
wouldn | +0.049 |
Neg logit contributions | |
elderly | -0.100 |
amusement | -0.095 |
jungle | -0.095 |
playground | -0.094 |
youngest | -0.094 |
Token | a |
Token ID | 257 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
t | +0.031 |
don | +0.030 |
wouldn | +0.029 |
w | +0.028 |
fell | +0.028 |
Neg logit contributions | |
elderly | -0.036 |
films | -0.033 |
amusement | -0.033 |
youngest | -0.032 |
younger | -0.032 |
Token | package |
Token ID | 5301 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
amusement | +0.090 |
films | +0.088 |
elderly | +0.086 |
orchestra | +0.085 |
Wheels | +0.083 |
Neg logit contributions | |
t | -0.141 |
don | -0.136 |
wouldn | -0.134 |
got | -0.133 |
fell | -0.132 |
Token | from |
Token ID | 422 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
don | +0.021 |
t | +0.019 |
wouldn | +0.019 |
w | +0.019 |
could | +0.018 |
Neg logit contributions | |
elderly | -0.046 |
amusement | -0.045 |
films | -0.044 |
orchestra | -0.043 |
moon | -0.043 |
Token | child |
Token ID | 1200 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
opl | +0.188 |
films | +0.185 |
orchestra | +0.185 |
sym | +0.183 |
campus | +0.177 |
Neg logit contributions | |
got | -0.246 |
don | -0.231 |
didn | -0.225 |
would | -0.224 |
had | -0.218 |
Token | opened |
Token ID | 4721 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
t | +0.001 |
don | +0.001 |
wouldn | +0.001 |
got | +0.001 |
fell | +0.001 |
Neg logit contributions | |
amusement | -0.003 |
films | -0.003 |
elderly | -0.003 |
orchestra | -0.003 |
Wheels | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
don | +0.011 |
got | +0.011 |
t | +0.011 |
it | +0.011 |
wouldn | +0.011 |
Neg logit contributions | |
amusement | -0.023 |
orchestra | -0.023 |
Wheels | -0.023 |
films | -0.023 |
elderly | -0.023 |
Token | dish |
Token ID | 9433 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
amusement | +0.202 |
orchestra | +0.200 |
films | +0.198 |
lions | +0.193 |
Wheels | +0.193 |
Neg logit contributions | |
t | -0.274 |
got | -0.262 |
don | -0.259 |
wouldn | -0.257 |
could | -0.253 |
Token | and |
Token ID | 290 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
elderly | +0.069 |
amusement | +0.069 |
films | +0.068 |
buildings | +0.066 |
orchestra | +0.066 |
Neg logit contributions | |
t | -0.071 |
don | -0.070 |
wouldn | -0.067 |
fell | -0.066 |
got | -0.065 |
Token | inside |
Token ID | 2641 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
t | +0.032 |
don | +0.028 |
wouldn | +0.027 |
w | +0.026 |
ever | +0.025 |
Neg logit contributions | |
amusement | -0.065 |
elderly | -0.064 |
films | -0.063 |
orchestra | -0.062 |
moon | -0.062 |
Token | was |
Token ID | 373 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
t | +0.040 |
don | +0.037 |
wouldn | +0.036 |
got | +0.035 |
fell | +0.034 |
Neg logit contributions | |
amusement | -0.111 |
films | -0.110 |
elderly | -0.109 |
orchestra | -0.109 |
Wheels | -0.107 |
Token | a |
Token ID | 257 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
got | +0.002 |
could | +0.002 |
wouldn | +0.002 |
fell | +0.002 |
t | +0.002 |
Neg logit contributions | |
films | -0.004 |
orchestra | -0.004 |
amusement | -0.004 |
Wheels | -0.004 |
buildings | -0.004 |
Token | long |
Token ID | 890 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
films | +0.108 |
buildings | +0.105 |
opl | +0.104 |
Wheels | +0.104 |
amusement | +0.103 |
Neg logit contributions | |
got | -0.131 |
would | -0.126 |
don | -0.126 |
fell | -0.123 |
could | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
films | +0.142 |
amusement | +0.142 |
orchestra | +0.140 |
Wheels | +0.139 |
elderly | +0.138 |
Neg logit contributions | |
t | -0.133 |
got | -0.132 |
don | -0.130 |
fell | -0.128 |
wouldn | -0.126 |
Token | string |
Token ID | 4731 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
films | +0.021 |
Wheels | +0.021 |
amusement | +0.020 |
orchestra | +0.020 |
lions | +0.020 |
Neg logit contributions | |
don | -0.028 |
got | -0.028 |
wouldn | -0.028 |
fell | -0.027 |
could | -0.027 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
t | +0.056 |
don | +0.051 |
wouldn | +0.049 |
could | +0.047 |
got | +0.047 |
Neg logit contributions | |
amusement | -0.136 |
films | -0.133 |
elderly | -0.133 |
orchestra | -0.132 |
Wheels | -0.130 |
Token | back |
Token ID | 736 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
t | +0.047 |
don | +0.046 |
wouldn | +0.045 |
w | +0.043 |
could | +0.042 |
Neg logit contributions | |
amusement | -0.110 |
elderly | -0.107 |
orchestra | -0.107 |
films | -0.107 |
buildings | -0.105 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
t | +0.018 |
wouldn | +0.017 |
don | +0.017 |
w | +0.016 |
could | +0.015 |
Neg logit contributions | |
elderly | -0.038 |
amusement | -0.038 |
buildings | -0.037 |
films | -0.037 |
orchestra | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
don | +0.026 |
got | +0.025 |
t | +0.024 |
fell | +0.024 |
wouldn | +0.024 |
Neg logit contributions | |
amusement | -0.047 |
films | -0.047 |
Wheels | -0.047 |
orchestra | -0.046 |
array | -0.046 |
Token | seat |
Token ID | 5852 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
umm | +0.124 |
andel | +0.120 |
films | +0.118 |
Wheels | +0.116 |
amusement | +0.114 |
Neg logit contributions | |
fell | -0.133 |
got | -0.131 |
would | -0.129 |
could | -0.129 |
never | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
t | +0.018 |
wouldn | +0.016 |
got | +0.016 |
don | +0.016 |
fell | +0.016 |
Neg logit contributions | |
amusement | -0.038 |
films | -0.038 |
orchestra | -0.037 |
Wheels | -0.036 |
elderly | -0.036 |
Token | laughing |
Token ID | 14376 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
t | +0.049 |
don | +0.044 |
w | +0.044 |
wouldn | +0.043 |
could | +0.042 |
Neg logit contributions | |
amusement | -0.064 |
elderly | -0.064 |
orchestra | -0.063 |
films | -0.062 |
playground | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
t | +0.007 |
got | +0.007 |
wouldn | +0.007 |
don | +0.007 |
could | +0.007 |
Neg logit contributions | |
amusement | -0.022 |
films | -0.022 |
Wheels | -0.022 |
orchestra | -0.021 |
elderly | -0.021 |
Token | smiling |
Token ID | 16755 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
t | +0.096 |
don | +0.090 |
wouldn | +0.089 |
got | +0.088 |
could | +0.087 |
Neg logit contributions | |
amusement | -0.081 |
films | -0.079 |
elderly | -0.079 |
orchestra | -0.078 |
Wheels | -0.076 |
Token | as |
Token ID | 355 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
t | +0.009 |
got | +0.009 |
wouldn | +0.009 |
could | +0.009 |
don | +0.009 |
Neg logit contributions | |
amusement | -0.021 |
films | -0.021 |
Wheels | -0.021 |
orchestra | -0.020 |
elderly | -0.020 |
Token | she |
Token ID | 673 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
t | +0.044 |
don | +0.042 |
wouldn | +0.040 |
could | +0.039 |
got | +0.039 |
Neg logit contributions | |
amusement | -0.140 |
films | -0.137 |
orchestra | -0.136 |
Wheels | -0.134 |
elderly | -0.134 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
t | +0.013 |
don | +0.013 |
got | +0.012 |
could | +0.012 |
fell | +0.012 |
Neg logit contributions | |
amusement | -0.021 |
orchestra | -0.021 |
array | -0.021 |
films | -0.021 |
Wheels | -0.020 |
Token | says |
Token ID | 1139 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
don | +0.030 |
t | +0.029 |
got | +0.029 |
wouldn | +0.028 |
fell | +0.028 |
Neg logit contributions | |
amusement | -0.045 |
films | -0.044 |
orchestra | -0.044 |
elderly | -0.043 |
array | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
t | +0.029 |
w | +0.029 |
wouldn | +0.029 |
got | +0.028 |
don | +0.028 |
Neg logit contributions | |
films | -0.028 |
elderly | -0.027 |
younger | -0.027 |
circles | -0.026 |
orchestra | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
elderly | +0.000 |
films | +0.000 |
circles | +0.000 |
Wheels | +0.000 |
amusement | +0.000 |
Neg logit contributions | |
wouldn | -0.000 |
t | -0.000 |
w | -0.000 |
got | -0.000 |
don | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
amusement | +0.065 |
films | +0.065 |
elderly | +0.064 |
Wheels | +0.063 |
orchestra | +0.063 |
Neg logit contributions | |
t | -0.039 |
wouldn | -0.038 |
don | -0.036 |
got | -0.036 |
fell | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
amusement | +0.094 |
films | +0.093 |
orchestra | +0.092 |
elderly | +0.091 |
Wheels | +0.090 |
Neg logit contributions | |
t | -0.040 |
don | -0.038 |
got | -0.036 |
fell | -0.035 |
could | -0.035 |
Token | A |
Token ID | 32 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
amusement | +0.006 |
elderly | +0.006 |
films | +0.006 |
orchestra | +0.006 |
Wheels | +0.006 |
Neg logit contributions | |
t | -0.003 |
wouldn | -0.003 |
don | -0.003 |
got | -0.002 |
fell | -0.002 |
Token | friend |
Token ID | 1545 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
amusement | +0.079 |
films | +0.075 |
Wheels | +0.073 |
orchestra | +0.072 |
elderly | +0.072 |
Neg logit contributions | |
t | -0.169 |
don | -0.164 |
got | -0.163 |
wouldn | -0.161 |
would | -0.161 |
Token | ? |
Token ID | 30 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
amusement | +0.013 |
films | +0.013 |
elderly | +0.013 |
orchestra | +0.013 |
lions | +0.013 |
Neg logit contributions | |
t | -0.008 |
wouldn | -0.007 |
don | -0.007 |
fell | -0.007 |
got | -0.007 |
Token | Like |
Token ID | 4525 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
amusement | +0.018 |
films | +0.018 |
orchestra | +0.018 |
elderly | +0.018 |
Wheels | +0.017 |
Neg logit contributions | |
t | -0.010 |
don | -0.010 |
wouldn | -0.009 |
got | -0.009 |
could | -0.009 |
Token | us |
Token ID | 514 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
don | +0.011 |
t | +0.010 |
ever | +0.010 |
got | +0.010 |
could | +0.010 |
Neg logit contributions | |
amusement | -0.021 |
orchestra | -0.021 |
array | -0.020 |
elderly | -0.020 |
youngest | -0.020 |
Token | went |
Token ID | 1816 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
t | +0.008 |
don | +0.007 |
wouldn | +0.007 |
got | +0.006 |
could | +0.006 |
Neg logit contributions | |
amusement | -0.026 |
films | -0.026 |
elderly | -0.026 |
orchestra | -0.026 |
Wheels | -0.026 |
Token | away |
Token ID | 1497 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
t | +0.057 |
don | +0.054 |
wouldn | +0.050 |
w | +0.050 |
could | +0.049 |
Neg logit contributions | |
amusement | -0.153 |
films | -0.152 |
elderly | -0.152 |
orchestra | -0.150 |
buildings | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
t | +0.037 |
don | +0.035 |
got | +0.034 |
wouldn | +0.034 |
fell | +0.034 |
Neg logit contributions | |
amusement | -0.069 |
films | -0.068 |
orchestra | -0.067 |
Wheels | -0.067 |
elderly | -0.066 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
t | +0.009 |
don | +0.009 |
could | +0.009 |
got | +0.009 |
wouldn | +0.009 |
Neg logit contributions | |
amusement | -0.019 |
films | -0.019 |
orchestra | -0.019 |
lions | -0.018 |
elephants | -0.018 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
amusement | +0.078 |
films | +0.077 |
elderly | +0.076 |
Wheels | +0.075 |
orchestra | +0.075 |
Neg logit contributions | |
t | -0.042 |
wouldn | -0.040 |
don | -0.040 |
got | -0.038 |
fell | -0.037 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
elderly | +0.044 |
films | +0.042 |
Wheels | +0.041 |
amusement | +0.041 |
moon | +0.041 |
Neg logit contributions | |
wouldn | -0.032 |
w | -0.031 |
t | -0.030 |
don | -0.030 |
ged | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
amusement | +0.054 |
films | +0.053 |
elderly | +0.052 |
orchestra | +0.051 |
Wheels | +0.051 |
Neg logit contributions | |
t | -0.047 |
wouldn | -0.045 |
don | -0.045 |
got | -0.043 |
fell | -0.043 |
Token | time |
Token ID | 640 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
amusement | +0.127 |
films | +0.124 |
elderly | +0.121 |
orchestra | +0.121 |
Wheels | +0.119 |
Neg logit contributions | |
t | -0.150 |
don | -0.144 |
wouldn | -0.143 |
got | -0.141 |
could | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
amusement | +0.002 |
lions | +0.002 |
playground | +0.002 |
films | +0.002 |
zoo | +0.002 |
Neg logit contributions | |
wouldn | -0.002 |
w | -0.002 |
would | -0.002 |
ged | -0.002 |
t | -0.002 |
Token | there |
Token ID | 612 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
elderly | +0.087 |
lions | +0.086 |
moon | +0.085 |
Wheels | +0.084 |
films | +0.084 |
Neg logit contributions | |
wouldn | -0.057 |
t | -0.055 |
use | -0.053 |
w | -0.049 |
don | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
t | +0.032 |
wouldn | +0.029 |
don | +0.028 |
w | +0.028 |
use | +0.028 |
Neg logit contributions | |
amusement | -0.063 |
playground | -0.061 |
Wheels | -0.060 |
films | -0.060 |
circles | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
amusement | +0.070 |
films | +0.069 |
orchestra | +0.069 |
elderly | +0.068 |
Wheels | +0.068 |
Neg logit contributions | |
t | -0.013 |
don | -0.012 |
got | -0.011 |
wouldn | -0.011 |
could | -0.010 |
Token | help |
Token ID | 1037 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
t | +0.007 |
don | +0.006 |
wouldn | +0.006 |
got | +0.006 |
could | +0.006 |
Neg logit contributions | |
amusement | -0.010 |
films | -0.010 |
elderly | -0.010 |
orchestra | -0.010 |
Wheels | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
got | +0.016 |
t | +0.014 |
don | +0.014 |
fell | +0.013 |
it | +0.013 |
Neg logit contributions | |
amusement | -0.048 |
orchestra | -0.047 |
unison | -0.046 |
sym | -0.046 |
elephants | -0.046 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
amusement | +0.106 |
orchestra | +0.103 |
array | +0.101 |
Wheels | +0.099 |
elephants | +0.098 |
Neg logit contributions | |
got | -0.085 |
don | -0.084 |
would | -0.083 |
wouldn | -0.082 |
t | -0.082 |
Token | my |
Token ID | 1820 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
t | +0.026 |
fell | +0.024 |
w | +0.024 |
wouldn | +0.024 |
don | +0.024 |
Neg logit contributions | |
elderly | -0.031 |
films | -0.030 |
youngest | -0.028 |
movies | -0.028 |
younger | -0.028 |
Token | in |
Token ID | 287 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
t | +0.054 |
w | +0.050 |
fell | +0.048 |
wouldn | +0.048 |
ever | +0.047 |
Neg logit contributions | |
films | -0.073 |
elderly | -0.072 |
youngest | -0.068 |
movies | -0.068 |
Wheels | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
orchestra | +0.024 |
sym | +0.023 |
amusement | +0.023 |
array | +0.023 |
elephants | +0.023 |
Neg logit contributions | |
don | -0.014 |
got | -0.013 |
t | -0.013 |
ever | -0.012 |
could | -0.012 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
orchestra | +0.161 |
unison | +0.159 |
amusement | +0.157 |
array | +0.153 |
andel | +0.146 |
Neg logit contributions | |
got | -0.253 |
would | -0.244 |
will | -0.238 |
fell | -0.238 |
could | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
t | +0.017 |
don | +0.016 |
got | +0.016 |
wouldn | +0.016 |
fell | +0.016 |
Neg logit contributions | |
amusement | -0.031 |
orchestra | -0.031 |
films | -0.030 |
Wheels | -0.030 |
elderly | -0.030 |
Token | One |
Token ID | 1881 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
amusement | +0.020 |
orchestra | +0.020 |
films | +0.019 |
elderly | +0.019 |
lions | +0.019 |
Neg logit contributions | |
t | -0.014 |
don | -0.014 |
got | -0.013 |
could | -0.013 |
would | -0.013 |
Token | day |
Token ID | 1110 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
elderly | +0.072 |
films | +0.071 |
amusement | +0.069 |
moon | +0.067 |
Wheels | +0.066 |
Neg logit contributions | |
wouldn | -0.079 |
don | -0.079 |
t | -0.079 |
ged | -0.076 |
could | -0.074 |
Token | too |
Token ID | 1165 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
t | +0.049 |
don | +0.047 |
wouldn | +0.046 |
got | +0.046 |
could | +0.045 |
Neg logit contributions | |
amusement | -0.061 |
films | -0.060 |
orchestra | -0.059 |
elderly | -0.058 |
Wheels | -0.058 |
Token | short |
Token ID | 1790 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
t | +0.103 |
wouldn | +0.102 |
don | +0.100 |
ged | +0.099 |
got | +0.097 |
Neg logit contributions | |
elderly | -0.073 |
amusement | -0.069 |
films | -0.068 |
buildings | -0.067 |
Wheels | -0.066 |
Token | for |
Token ID | 329 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
t | +0.001 |
wouldn | +0.001 |
don | +0.001 |
got | +0.001 |
fell | +0.001 |
Neg logit contributions | |
amusement | -0.002 |
films | -0.002 |
elderly | -0.002 |
orchestra | -0.002 |
lions | -0.002 |
Token | me |
Token ID | 502 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
t | +0.013 |
don | +0.013 |
got | +0.012 |
wouldn | +0.012 |
fell | +0.012 |
Neg logit contributions | |
amusement | -0.025 |
films | -0.025 |
orchestra | -0.025 |
elderly | -0.024 |
Wheels | -0.024 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
t | +0.008 |
wouldn | +0.007 |
don | +0.007 |
got | +0.007 |
ged | +0.007 |
Neg logit contributions | |
elderly | -0.011 |
amusement | -0.011 |
lions | -0.011 |
films | -0.011 |
circles | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
t | +0.019 |
don | +0.017 |
could | +0.017 |
got | +0.016 |
wouldn | +0.016 |
Neg logit contributions | |
amusement | -0.038 |
orchestra | -0.037 |
films | -0.037 |
array | -0.036 |
elderly | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
amusement | +0.051 |
films | +0.050 |
orchestra | +0.050 |
elderly | +0.049 |
array | +0.049 |
Neg logit contributions | |
t | -0.022 |
don | -0.019 |
could | -0.018 |
got | -0.018 |
fell | -0.018 |
Token | He |
Token ID | 1544 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
films | +0.051 |
amusement | +0.050 |
orchestra | +0.049 |
elderly | +0.049 |
buildings | +0.048 |
Neg logit contributions | |
t | -0.041 |
don | -0.038 |
got | -0.037 |
could | -0.037 |
never | -0.036 |
Token | moved |
Token ID | 3888 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
t | +0.063 |
don | +0.059 |
wouldn | +0.052 |
w | +0.052 |
fell | +0.049 |
Neg logit contributions | |
amusement | -0.148 |
elderly | -0.147 |
Wheels | -0.144 |
orchestra | -0.144 |
films | -0.144 |
Token | on |
Token ID | 319 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
t | +0.046 |
don | +0.044 |
wouldn | +0.043 |
got | +0.042 |
fell | +0.042 |
Neg logit contributions | |
amusement | -0.075 |
films | -0.074 |
elderly | -0.073 |
orchestra | -0.072 |
Wheels | -0.071 |
Token | to |
Token ID | 284 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
t | +0.038 |
got | +0.037 |
don | +0.037 |
wouldn | +0.035 |
never | +0.035 |
Neg logit contributions | |
orchestra | -0.090 |
films | -0.089 |
amusement | -0.088 |
Wheels | -0.087 |
elderly | -0.085 |
Token | or |
Token ID | 393 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
t | +0.038 |
don | +0.035 |
wouldn | +0.034 |
got | +0.034 |
w | +0.034 |
Neg logit contributions | |
amusement | -0.055 |
elderly | -0.054 |
films | -0.054 |
orchestra | -0.053 |
Wheels | -0.053 |
Token | she |
Token ID | 673 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
t | +0.043 |
w | +0.038 |
don | +0.035 |
fell | +0.035 |
wouldn | +0.035 |
Neg logit contributions | |
elderly | -0.062 |
amusement | -0.061 |
lions | -0.060 |
films | -0.060 |
orchestra | -0.059 |
Token | would |
Token ID | 561 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
t | +0.047 |
don | +0.041 |
w | +0.040 |
ged | +0.039 |
use | +0.035 |
Neg logit contributions | |
amusement | -0.145 |
elderly | -0.145 |
lions | -0.143 |
monkeys | -0.142 |
elephants | -0.141 |
Token | have |
Token ID | 423 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
t | +0.061 |
ged | +0.057 |
w | +0.054 |
wouldn | +0.050 |
got | +0.048 |
Neg logit contributions | |
amusement | -0.176 |
elderly | -0.171 |
playground | -0.170 |
moon | -0.169 |
zoo | -0.168 |
Token | been |
Token ID | 587 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
t | +0.047 |
don | +0.043 |
wouldn | +0.042 |
got | +0.039 |
could | +0.039 |
Neg logit contributions | |
amusement | -0.110 |
elderly | -0.107 |
films | -0.106 |
lions | -0.104 |
buildings | -0.104 |
Token | his |
Token ID | 465 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
t | +0.038 |
don | +0.036 |
wouldn | +0.036 |
got | +0.035 |
could | +0.035 |
Neg logit contributions | |
amusement | -0.043 |
films | -0.042 |
elderly | -0.042 |
orchestra | -0.042 |
Wheels | -0.041 |
Token | lunch |
Token ID | 9965 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
amusement | +0.098 |
films | +0.098 |
orchestra | +0.093 |
Wheels | +0.091 |
buildings | +0.090 |
Neg logit contributions | |
don | -0.117 |
ever | -0.114 |
wouldn | -0.113 |
t | -0.112 |
would | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
t | +0.005 |
wouldn | +0.004 |
don | +0.004 |
got | +0.004 |
could | +0.004 |
Neg logit contributions | |
amusement | -0.008 |
films | -0.008 |
orchestra | -0.008 |
Wheels | -0.008 |
elderly | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
t | +0.007 |
don | +0.007 |
could | +0.007 |
wouldn | +0.006 |
got | +0.006 |
Neg logit contributions | |
amusement | -0.015 |
films | -0.015 |
orchestra | -0.015 |
elderly | -0.015 |
array | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
amusement | +0.056 |
films | +0.055 |
elderly | +0.055 |
Wheels | +0.054 |
orchestra | +0.054 |
Neg logit contributions | |
t | -0.033 |
wouldn | -0.033 |
don | -0.031 |
got | -0.031 |
fell | -0.030 |
Token | She |
Token ID | 3347 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
amusement | +0.064 |
films | +0.064 |
orchestra | +0.062 |
elderly | +0.062 |
Wheels | +0.061 |
Neg logit contributions | |
t | -0.050 |
don | -0.048 |
got | -0.047 |
wouldn | -0.046 |
could | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
w | +0.052 |
don | +0.048 |
ged | +0.048 |
t | +0.048 |
wouldn | +0.047 |
Neg logit contributions | |
elderly | -0.066 |
amusement | -0.063 |
playground | -0.060 |
buildings | -0.059 |
lions | -0.058 |
Token | wear |
Token ID | 5806 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
t | +0.031 |
wouldn | +0.029 |
don | +0.028 |
got | +0.027 |
could | +0.027 |
Neg logit contributions | |
amusement | -0.060 |
films | -0.059 |
elderly | -0.059 |
orchestra | -0.058 |
Wheels | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
t | +0.035 |
don | +0.033 |
wouldn | +0.032 |
got | +0.032 |
fell | +0.032 |
Neg logit contributions | |
amusement | -0.052 |
films | -0.051 |
elderly | -0.050 |
orchestra | -0.050 |
buildings | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
amusement | +0.013 |
films | +0.013 |
orchestra | +0.013 |
elderly | +0.012 |
array | +0.012 |
Neg logit contributions | |
t | -0.005 |
don | -0.005 |
could | -0.005 |
got | -0.005 |
wouldn | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
amusement | +0.062 |
films | +0.061 |
elderly | +0.061 |
Wheels | +0.061 |
orchestra | +0.060 |
Neg logit contributions | |
wouldn | -0.039 |
t | -0.038 |
don | -0.037 |
got | -0.036 |
fell | -0.036 |
Token | Ann |
Token ID | 18858 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
films | +0.063 |
amusement | +0.061 |
orchestra | +0.061 |
elderly | +0.060 |
array | +0.058 |
Neg logit contributions | |
t | -0.064 |
got | -0.060 |
could | -0.059 |
don | -0.059 |
would | -0.058 |
Token | was |
Token ID | 373 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
amusement | +0.099 |
films | +0.099 |
orchestra | +0.097 |
elderly | +0.096 |
Wheels | +0.096 |
Neg logit contributions | |
t | -0.034 |
got | -0.033 |
wouldn | -0.032 |
could | -0.031 |
don | -0.031 |
Token | so |
Token ID | 523 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
amusement | +0.004 |
films | +0.004 |
orchestra | +0.004 |
Wheels | +0.004 |
buildings | +0.004 |
Neg logit contributions | |
t | -0.003 |
got | -0.003 |
don | -0.002 |
wouldn | -0.002 |
fell | -0.002 |
Token | embarrassed |
Token ID | 21100 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
t | +0.022 |
wouldn | +0.021 |
don | +0.020 |
would | +0.020 |
could | +0.020 |
Neg logit contributions | |
elderly | -0.020 |
amusement | -0.019 |
films | -0.018 |
orchestra | -0.018 |
Wheels | -0.018 |
Token | that |
Token ID | 326 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
t | +0.002 |
don | +0.002 |
wouldn | +0.002 |
got | +0.002 |
fell | +0.002 |
Neg logit contributions | |
amusement | -0.004 |
films | -0.004 |
elderly | -0.004 |
orchestra | -0.003 |
Wheels | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
t | +0.019 |
don | +0.017 |
wouldn | +0.017 |
got | +0.016 |
could | +0.016 |
Neg logit contributions | |
amusement | -0.078 |
films | -0.077 |
orchestra | -0.077 |
elderly | -0.076 |
Wheels | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
amusement | +0.037 |
films | +0.037 |
orchestra | +0.036 |
Wheels | +0.036 |
elderly | +0.036 |
Neg logit contributions | |
t | -0.016 |
don | -0.015 |
got | -0.015 |
wouldn | -0.015 |
could | -0.015 |
Token | rude |
Token ID | 22066 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
t | +0.076 |
don | +0.071 |
wouldn | +0.071 |
got | +0.069 |
fell | +0.069 |
Neg logit contributions | |
elderly | -0.067 |
amusement | -0.067 |
films | -0.066 |
orchestra | -0.065 |
lions | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
amusement | +0.049 |
films | +0.048 |
orchestra | +0.048 |
elderly | +0.047 |
Wheels | +0.047 |
Neg logit contributions | |
t | -0.025 |
don | -0.024 |
got | -0.024 |
could | -0.023 |
wouldn | -0.023 |
Token | He |
Token ID | 679 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
could | +0.009 |
don | +0.009 |
t | +0.009 |
got | +0.008 |
fell | +0.008 |
Neg logit contributions | |
amusement | -0.024 |
orchestra | -0.024 |
array | -0.024 |
films | -0.023 |
flock | -0.023 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
t | +0.051 |
don | +0.042 |
wouldn | +0.040 |
w | +0.039 |
ged | +0.038 |
Neg logit contributions | |
amusement | -0.146 |
elderly | -0.146 |
lions | -0.142 |
orchestra | -0.142 |
films | -0.142 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
it | +0.004 |
got | +0.004 |
don | +0.004 |
could | +0.004 |
fell | +0.003 |
Neg logit contributions | |
array | -0.009 |
orchestra | -0.009 |
umm | -0.009 |
sym | -0.009 |
amusement | -0.009 |
Token | basket |
Token ID | 7988 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
orchestra | +0.184 |
films | +0.183 |
amusement | +0.176 |
unison | +0.174 |
array | +0.172 |
Neg logit contributions | |
don | -0.230 |
would | -0.220 |
got | -0.215 |
fell | -0.214 |
will | -0.214 |
Token | and |
Token ID | 290 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
t | +0.025 |
don | +0.024 |
wouldn | +0.023 |
got | +0.023 |
could | +0.022 |
Neg logit contributions | |
amusement | -0.043 |
elderly | -0.042 |
films | -0.042 |
orchestra | -0.041 |
Wheels | -0.041 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
t | +0.041 |
don | +0.038 |
wouldn | +0.037 |
got | +0.037 |
fell | +0.036 |
Neg logit contributions | |
amusement | -0.094 |
films | -0.093 |
elderly | -0.092 |
orchestra | -0.092 |
Wheels | -0.091 |
Token | to |
Token ID | 284 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
t | +0.028 |
don | +0.024 |
wouldn | +0.023 |
got | +0.022 |
fell | +0.022 |
Neg logit contributions | |
amusement | -0.142 |
films | -0.141 |
elderly | -0.139 |
orchestra | -0.139 |
Wheels | -0.138 |
Token | take |
Token ID | 1011 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
t | +0.060 |
wouldn | +0.057 |
don | +0.055 |
could | +0.054 |
fell | +0.053 |
Neg logit contributions | |
amusement | -0.112 |
elderly | -0.109 |
films | -0.108 |
orchestra | -0.107 |
Wheels | -0.106 |
Token | the |
Token ID | 262 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
t | +0.024 |
got | +0.023 |
don | +0.023 |
ever | +0.023 |
fell | +0.022 |
Neg logit contributions | |
amusement | -0.036 |
elderly | -0.036 |
orchestra | -0.036 |
films | -0.035 |
Wheels | -0.035 |
Token | parade |
Token ID | 16134 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
umm | +0.162 |
pasture | +0.158 |
opl | +0.153 |
array | +0.150 |
andel | +0.150 |
Neg logit contributions | |
t | -0.227 |
don | -0.220 |
got | -0.218 |
ever | -0.214 |
would | -0.207 |
Token | was |
Token ID | 373 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
t | +0.017 |
don | +0.016 |
got | +0.016 |
wouldn | +0.016 |
could | +0.015 |
Neg logit contributions | |
amusement | -0.046 |
films | -0.046 |
orchestra | -0.045 |
elderly | -0.045 |
Wheels | -0.044 |
Token | over |
Token ID | 625 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
t | +0.018 |
don | +0.017 |
got | +0.017 |
wouldn | +0.017 |
fell | +0.017 |
Neg logit contributions | |
amusement | -0.029 |
films | -0.029 |
orchestra | -0.028 |
elderly | -0.028 |
Wheels | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
t | +0.003 |
don | +0.003 |
wouldn | +0.003 |
got | +0.003 |
could | +0.002 |
Neg logit contributions | |
amusement | -0.006 |
films | -0.006 |
elderly | -0.006 |
orchestra | -0.006 |
Wheels | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -9.50e+00 |
Pos logit contributions | |
don | +0.019 |
it | +0.019 |
got | +0.018 |
could | +0.017 |
they | +0.017 |
Neg logit contributions | |
orchestra | -0.042 |
amusement | -0.042 |
array | -0.041 |
films | -0.041 |
andel | -0.040 |
Token | little |
Token ID | 1310 |
Feature activation | -8.14e+00 |
Pos logit contributions | |
opl | +0.194 |
umm | +0.177 |
andel | +0.173 |
pasture | +0.171 |
ami | +0.168 |
Neg logit contributions | |
got | -0.200 |
don | -0.190 |
could | -0.186 |
had | -0.182 |
fell | -0.181 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
opl | +0.194 |
icious | +0.189 |
films | +0.189 |
andel | +0.187 |
unison | +0.185 |
Neg logit contributions | |
got | -0.140 |
don | -0.132 |
fell | -0.127 |
could | -0.127 |
tried | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
t | +0.014 |
don | +0.013 |
wouldn | +0.013 |
got | +0.013 |
fell | +0.013 |
Neg logit contributions | |
amusement | -0.040 |
films | -0.040 |
orchestra | -0.039 |
elderly | -0.039 |
Wheels | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
got | +0.018 |
don | +0.017 |
fell | +0.017 |
could | +0.017 |
wouldn | +0.017 |
Neg logit contributions | |
array | -0.041 |
amusement | -0.041 |
films | -0.041 |
umm | -0.041 |
Wheels | -0.041 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
umm | +0.120 |
opl | +0.118 |
andel | +0.114 |
amusement | +0.113 |
array | +0.112 |
Neg logit contributions | |
got | -0.092 |
could | -0.092 |
would | -0.092 |
ever | -0.091 |
don | -0.089 |
Token | they |
Token ID | 484 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
amusement | +0.113 |
films | +0.111 |
orchestra | +0.110 |
elderly | +0.109 |
Wheels | +0.107 |
Neg logit contributions | |
t | -0.090 |
don | -0.085 |
wouldn | -0.084 |
got | -0.083 |
could | -0.082 |
Token | could |
Token ID | 714 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
t | +0.060 |
don | +0.048 |
w | +0.048 |
wouldn | +0.047 |
ged | +0.047 |
Neg logit contributions | |
amusement | -0.172 |
films | -0.168 |
lions | -0.168 |
orchestra | -0.167 |
elderly | -0.166 |
Token | play |
Token ID | 711 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
t | +0.126 |
w | +0.123 |
ged | +0.121 |
wouldn | +0.114 |
don | +0.108 |
Neg logit contributions | |
films | -0.214 |
amusement | -0.214 |
elderly | -0.209 |
orchestra | -0.209 |
playground | -0.207 |
Token | together |
Token ID | 1978 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
t | +0.033 |
don | +0.031 |
wouldn | +0.030 |
got | +0.029 |
could | +0.029 |
Neg logit contributions | |
amusement | -0.079 |
films | -0.078 |
elderly | -0.077 |
orchestra | -0.077 |
Wheels | -0.076 |
Token | with |
Token ID | 351 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
t | +0.065 |
don | +0.062 |
wouldn | +0.060 |
got | +0.060 |
could | +0.059 |
Neg logit contributions | |
amusement | -0.127 |
films | -0.125 |
elderly | -0.124 |
orchestra | -0.124 |
Wheels | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
elderly | +0.004 |
orchestra | +0.004 |
amusement | +0.004 |
Wheels | +0.004 |
array | +0.004 |
Neg logit contributions | |
don | -0.002 |
ever | -0.002 |
could | -0.002 |
it | -0.002 |
never | -0.002 |
Token | cars |
Token ID | 5006 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
amusement | +0.156 |
andel | +0.152 |
orchestra | +0.151 |
array | +0.150 |
films | +0.150 |
Neg logit contributions | |
don | -0.226 |
would | -0.223 |
will | -0.219 |
wouldn | -0.209 |
can | -0.208 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
t | +0.015 |
don | +0.014 |
wouldn | +0.014 |
got | +0.014 |
could | +0.014 |
Neg logit contributions | |
amusement | -0.030 |
films | -0.029 |
orchestra | -0.029 |
elderly | -0.029 |
Wheels | -0.029 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
t | +0.016 |
don | +0.016 |
could | +0.016 |
got | +0.015 |
wouldn | +0.014 |
Neg logit contributions | |
amusement | -0.034 |
orchestra | -0.034 |
elderly | -0.033 |
films | -0.033 |
array | -0.033 |
Token | thought |
Token ID | 1807 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
t | +0.025 |
don | +0.023 |
wouldn | +0.022 |
got | +0.021 |
fell | +0.021 |
Neg logit contributions | |
amusement | -0.068 |
films | -0.067 |
elderly | -0.067 |
orchestra | -0.067 |
Wheels | -0.066 |
Token | about |
Token ID | 546 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
t | +0.043 |
don | +0.041 |
wouldn | +0.040 |
got | +0.038 |
could | +0.038 |
Neg logit contributions | |
amusement | -0.138 |
orchestra | -0.134 |
films | -0.134 |
elderly | -0.133 |
Wheels | -0.132 |
Token | |
Token ID | 220 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
t | +0.015 |
don | +0.014 |
could | +0.014 |
got | +0.013 |
wouldn | +0.013 |
Neg logit contributions | |
amusement | -0.026 |
films | -0.026 |
orchestra | -0.026 |
elderly | -0.025 |
array | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
t | +0.004 |
wouldn | +0.004 |
don | +0.004 |
got | +0.004 |
fell | +0.004 |
Neg logit contributions | |
amusement | -0.007 |
elderly | -0.007 |
films | -0.007 |
Wheels | -0.007 |
buildings | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
elderly | +0.040 |
amusement | +0.040 |
Wheels | +0.039 |
films | +0.039 |
circles | +0.039 |
Neg logit contributions | |
wouldn | -0.028 |
t | -0.026 |
don | -0.026 |
got | -0.025 |
would | -0.025 |
Token | Everyone |
Token ID | 16190 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
amusement | +0.039 |
films | +0.039 |
orchestra | +0.038 |
elderly | +0.037 |
Wheels | +0.036 |
Neg logit contributions | |
t | -0.051 |
don | -0.049 |
got | -0.048 |
wouldn | -0.048 |
could | -0.047 |
Token | in |
Token ID | 287 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
t | +0.024 |
don | +0.023 |
wouldn | +0.022 |
w | +0.021 |
fell | +0.020 |
Neg logit contributions | |
amusement | -0.056 |
elderly | -0.054 |
films | -0.054 |
orchestra | -0.054 |
lions | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
orchestra | +0.046 |
array | +0.046 |
amusement | +0.046 |
elderly | +0.045 |
films | +0.045 |
Neg logit contributions | |
got | -0.028 |
t | -0.027 |
fell | -0.027 |
don | -0.027 |
ever | -0.026 |
Token | park |
Token ID | 3952 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
orchestra | +0.149 |
array | +0.148 |
films | +0.147 |
andel | +0.145 |
umm | +0.143 |
Neg logit contributions | |
got | -0.267 |
fell | -0.244 |
tried | -0.239 |
never | -0.236 |
t | -0.235 |
Token | was |
Token ID | 373 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
t | +0.024 |
don | +0.022 |
got | +0.022 |
wouldn | +0.022 |
fell | +0.021 |
Neg logit contributions | |
amusement | -0.072 |
films | -0.072 |
orchestra | -0.071 |
elderly | -0.071 |
Wheels | -0.070 |
Token | so |
Token ID | 523 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
t | +0.032 |
got | +0.032 |
fell | +0.031 |
don | +0.031 |
never | +0.030 |
Neg logit contributions | |
films | -0.052 |
amusement | -0.051 |
orchestra | -0.051 |
Wheels | -0.050 |
buildings | -0.050 |
Token | excited |
Token ID | 6568 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
t | +0.048 |
don | +0.045 |
wouldn | +0.045 |
got | +0.044 |
could | +0.044 |
Neg logit contributions | |
amusement | -0.049 |
films | -0.048 |
elderly | -0.047 |
orchestra | -0.047 |
Wheels | -0.046 |
Token | ! |
Token ID | 0 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
t | +0.007 |
don | +0.007 |
wouldn | +0.007 |
fell | +0.007 |
w | +0.007 |
Neg logit contributions | |
amusement | -0.013 |
films | -0.012 |
elderly | -0.012 |
buildings | -0.012 |
orchestra | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -9.89e+00 |
Pos logit contributions | |
t | +0.035 |
don | +0.033 |
wouldn | +0.032 |
got | +0.032 |
fell | +0.032 |
Neg logit contributions | |
amusement | -0.048 |
films | -0.047 |
orchestra | -0.046 |
elderly | -0.046 |
Wheels | -0.045 |
Token | milk |
Token ID | 7545 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
amusement | +0.182 |
orchestra | +0.178 |
lions | +0.169 |
films | +0.168 |
elephants | +0.166 |
Neg logit contributions | |
t | -0.220 |
got | -0.213 |
don | -0.210 |
would | -0.208 |
wouldn | -0.207 |
Token | and |
Token ID | 290 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
t | +0.026 |
don | +0.025 |
wouldn | +0.023 |
got | +0.023 |
fell | +0.023 |
Neg logit contributions | |
elderly | -0.045 |
films | -0.045 |
amusement | -0.045 |
buildings | -0.044 |
Wheels | -0.043 |
Token | cereal |
Token ID | 33158 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
t | +0.065 |
don | +0.055 |
w | +0.052 |
wouldn | +0.051 |
cannot | +0.050 |
Neg logit contributions | |
elderly | -0.106 |
amusement | -0.106 |
films | -0.104 |
buildings | -0.104 |
moon | -0.103 |
Token | with |
Token ID | 351 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
don | +0.052 |
t | +0.052 |
w | +0.051 |
use | +0.049 |
cannot | +0.048 |
Neg logit contributions | |
elderly | -0.077 |
films | -0.075 |
buildings | -0.075 |
circles | -0.074 |
playground | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -8.98e+00 |
Pos logit contributions | |
orchestra | +0.008 |
amusement | +0.008 |
films | +0.008 |
Wheels | +0.008 |
elderly | +0.008 |
Neg logit contributions | |
got | -0.004 |
could | -0.004 |
fell | -0.004 |
don | -0.004 |
t | -0.004 |
Token | spoon |
Token ID | 24556 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
amusement | +0.166 |
orchestra | +0.159 |
films | +0.156 |
Wheels | +0.148 |
lions | +0.147 |
Neg logit contributions | |
don | -0.199 |
t | -0.196 |
wouldn | -0.193 |
would | -0.192 |
got | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
t | +0.026 |
don | +0.025 |
wouldn | +0.024 |
w | +0.023 |
got | +0.023 |
Neg logit contributions | |
amusement | -0.036 |
elderly | -0.036 |
films | -0.036 |
circles | -0.035 |
Wheels | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
t | +0.021 |
don | +0.020 |
could | +0.020 |
wouldn | +0.020 |
got | +0.020 |
Neg logit contributions | |
amusement | -0.033 |
films | -0.032 |
orchestra | -0.032 |
elderly | -0.032 |
array | -0.031 |
Token | sprinkled |
Token ID | 49692 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
t | +0.077 |
don | +0.068 |
wouldn | +0.063 |
w | +0.061 |
ged | +0.059 |
Neg logit contributions | |
amusement | -0.168 |
elderly | -0.167 |
films | -0.165 |
Wheels | -0.163 |
orchestra | -0.163 |
Token | some |
Token ID | 617 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
t | +0.023 |
wouldn | +0.022 |
don | +0.022 |
fell | +0.021 |
got | +0.020 |
Neg logit contributions | |
films | -0.031 |
amusement | -0.031 |
elderly | -0.030 |
circles | -0.030 |
Wheels | -0.030 |