Token | toys |
Token ID | 14958 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
hospital | +0.049 |
slams | +0.044 |
clinic | +0.040 |
mun | +0.039 |
cleans | +0.037 |
Neg logit contributions | |
ever | -0.054 |
bye | -0.053 |
red | -0.051 |
seven | -0.049 |
ago | -0.048 |
Token | for |
Token ID | 329 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
hospital | +0.034 |
slams | +0.029 |
clinic | +0.027 |
chores | +0.026 |
promises | +0.026 |
Neg logit contributions | |
red | -0.040 |
bye | -0.040 |
By | -0.039 |
seventeen | -0.036 |
hy | -0.035 |
Token | two |
Token ID | 734 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
bye | +0.028 |
red | +0.028 |
ever | +0.027 |
By | +0.025 |
ago | +0.024 |
Neg logit contributions | |
hospital | -0.030 |
slams | -0.027 |
chores | -0.026 |
clinic | -0.025 |
mistakes | -0.024 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
hospital | +0.079 |
slams | +0.071 |
clinic | +0.065 |
mun | +0.064 |
chores | +0.062 |
Neg logit contributions | |
bye | -0.079 |
ever | -0.079 |
red | -0.077 |
seven | -0.071 |
By | -0.071 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
bye | +0.142 |
By | +0.142 |
red | +0.142 |
ever | +0.140 |
seven | +0.132 |
Neg logit contributions | |
hospital | -0.130 |
slams | -0.116 |
clinic | -0.108 |
chores | -0.106 |
mun | -0.103 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
bye | +0.083 |
ever | +0.082 |
By | +0.076 |
red | +0.073 |
hy | +0.064 |
Neg logit contributions | |
hospital | -0.224 |
slams | -0.216 |
clinic | -0.200 |
mun | -0.199 |
promises | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
bye | +0.540 |
red | +0.539 |
By | +0.529 |
ever | +0.509 |
seven | +0.489 |
Neg logit contributions | |
hospital | -0.488 |
slams | -0.423 |
clinic | -0.408 |
chores | -0.404 |
mun | -0.384 |
Token | But |
Token ID | 887 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ever | +0.016 |
bye | +0.016 |
red | +0.016 |
ago | +0.014 |
seven | +0.014 |
Neg logit contributions | |
hospital | -0.021 |
slams | -0.019 |
clinic | -0.018 |
mun | -0.017 |
promises | -0.017 |
Token | you |
Token ID | 345 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
hospital | +0.110 |
slams | +0.099 |
clinic | +0.092 |
promises | +0.091 |
chores | +0.090 |
Neg logit contributions | |
red | -0.076 |
bye | -0.075 |
ever | -0.072 |
ago | -0.066 |
By | -0.065 |
Token | have |
Token ID | 423 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ever | +0.065 |
bye | +0.063 |
red | +0.062 |
seven | +0.057 |
ago | +0.057 |
Neg logit contributions | |
hospital | -0.075 |
slams | -0.068 |
clinic | -0.063 |
mun | -0.062 |
promises | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
hospital | +0.030 |
slams | +0.027 |
clinic | +0.025 |
chores | +0.025 |
promises | +0.024 |
Neg logit contributions | |
bye | -0.024 |
red | -0.024 |
ever | -0.022 |
By | -0.021 |
ring | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +9.25e-04 |
Pos logit contributions | |
bye | +0.043 |
red | +0.043 |
ever | +0.040 |
seven | +0.038 |
chie | +0.038 |
Neg logit contributions | |
hospital | -0.036 |
slams | -0.030 |
clinic | -0.029 |
chores | -0.026 |
cleans | -0.025 |
Token | cakes |
Token ID | 30849 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ever | +0.000 |
bye | +0.000 |
red | +0.000 |
seven | +0.000 |
ago | +0.000 |
Neg logit contributions | |
hospital | -0.000 |
slams | -0.000 |
clinic | -0.000 |
mun | -0.000 |
promises | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
bye | +0.096 |
red | +0.093 |
ever | +0.092 |
By | +0.087 |
seven | +0.086 |
Neg logit contributions | |
hospital | -0.087 |
slams | -0.077 |
clinic | -0.073 |
chores | -0.068 |
cleans | -0.067 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
hospital | +0.000 |
slams | +0.000 |
clinic | +0.000 |
mun | +0.000 |
chores | +0.000 |
Neg logit contributions | |
ever | -0.000 |
bye | -0.000 |
red | -0.000 |
seven | -0.000 |
ago | -0.000 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
ever | +0.136 |
bye | +0.134 |
red | +0.132 |
By | +0.122 |
seven | +0.122 |
Neg logit contributions | |
hospital | -0.142 |
slams | -0.129 |
clinic | -0.119 |
mun | -0.116 |
chores | -0.113 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
bye | +0.081 |
ever | +0.081 |
red | +0.071 |
By | +0.069 |
seven | +0.062 |
Neg logit contributions | |
hospital | -0.221 |
slams | -0.212 |
mun | -0.198 |
clinic | -0.198 |
cleans | -0.193 |
Token | and |
Token ID | 290 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
bye | +0.527 |
ever | +0.521 |
red | +0.520 |
By | +0.485 |
seven | +0.484 |
Neg logit contributions | |
hospital | -0.519 |
slams | -0.451 |
clinic | -0.433 |
chores | -0.418 |
mun | -0.410 |
Token | cand |
Token ID | 2658 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
clinic | +0.002 |
cleans | +0.002 |
chores | +0.002 |
Neg logit contributions | |
bye | -0.003 |
red | -0.003 |
ever | -0.003 |
By | -0.003 |
seven | -0.003 |
Token | ies |
Token ID | 444 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
bye | +0.171 |
ever | +0.164 |
red | +0.161 |
seven | +0.155 |
By | +0.155 |
Neg logit contributions | |
hospital | -0.127 |
slams | -0.114 |
promises | -0.107 |
chores | -0.107 |
clinic | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
bye | +0.129 |
red | +0.125 |
ever | +0.125 |
seven | +0.116 |
By | +0.115 |
Neg logit contributions | |
hospital | -0.133 |
slams | -0.118 |
clinic | -0.112 |
mun | -0.106 |
chores | -0.105 |
Token | fruits |
Token ID | 15921 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
clinic | +0.003 |
mun | +0.003 |
cleans | +0.003 |
Neg logit contributions | |
ever | -0.003 |
bye | -0.003 |
red | -0.003 |
By | -0.003 |
seven | -0.003 |
Token | Dad |
Token ID | 17415 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
hospital | +0.029 |
promises | +0.026 |
chores | +0.026 |
slams | +0.025 |
tells | +0.025 |
Neg logit contributions | |
ever | -0.020 |
hy | -0.020 |
bye | -0.020 |
red | -0.019 |
ago | -0.018 |
Token | ate |
Token ID | 15063 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
bye | +0.142 |
red | +0.136 |
ever | +0.135 |
ago | +0.131 |
By | +0.123 |
Neg logit contributions | |
hospital | -0.185 |
slams | -0.165 |
mun | -0.159 |
cleans | -0.154 |
clinic | -0.152 |
Token | their |
Token ID | 511 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ever | +0.057 |
bye | +0.053 |
red | +0.052 |
seven | +0.049 |
ago | +0.046 |
Neg logit contributions | |
hospital | -0.085 |
slams | -0.080 |
clinic | -0.075 |
mun | -0.072 |
cleans | -0.069 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ever | +0.069 |
bye | +0.068 |
red | +0.066 |
seven | +0.061 |
ago | +0.060 |
Neg logit contributions | |
hospital | -0.081 |
slams | -0.075 |
clinic | -0.069 |
mun | -0.067 |
cleans | -0.064 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ever | +0.134 |
bye | +0.133 |
red | +0.131 |
ago | +0.126 |
By | +0.124 |
Neg logit contributions | |
hospital | -0.128 |
slams | -0.115 |
mun | -0.105 |
clinic | -0.104 |
chores | -0.102 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.17e+00 |
Pos logit contributions | |
ever | +0.076 |
bye | +0.074 |
red | +0.067 |
By | +0.061 |
ago | +0.058 |
Neg logit contributions | |
hospital | -0.235 |
slams | -0.224 |
clinic | -0.209 |
mun | -0.209 |
promises | -0.204 |
Token | and |
Token ID | 290 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
bye | +0.535 |
red | +0.516 |
ever | +0.503 |
By | +0.493 |
ago | +0.490 |
Neg logit contributions | |
hospital | -0.517 |
slams | -0.456 |
chores | -0.433 |
mun | -0.421 |
clinic | -0.420 |
Token | then |
Token ID | 788 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
hospital | +0.030 |
slams | +0.027 |
mun | +0.026 |
promises | +0.025 |
cleans | +0.025 |
Neg logit contributions | |
bye | -0.025 |
red | -0.024 |
ever | -0.023 |
ago | -0.022 |
By | -0.022 |
Token | sat |
Token ID | 3332 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
bye | +0.007 |
ever | +0.007 |
red | +0.007 |
ago | +0.007 |
seven | +0.007 |
Neg logit contributions | |
hospital | -0.011 |
slams | -0.010 |
clinic | -0.009 |
mun | -0.009 |
cleans | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
hospital | +0.029 |
slams | +0.026 |
clinic | +0.024 |
mun | +0.024 |
promises | +0.024 |
Neg logit contributions | |
ever | -0.025 |
bye | -0.025 |
red | -0.024 |
ago | -0.022 |
By | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
hospital | +0.166 |
slams | +0.157 |
mun | +0.145 |
clinic | +0.145 |
cleans | +0.139 |
Neg logit contributions | |
ever | -0.109 |
bye | -0.103 |
red | -0.101 |
seven | -0.096 |
ago | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ever | +0.113 |
bye | +0.104 |
red | +0.103 |
ago | +0.095 |
seven | +0.092 |
Neg logit contributions | |
hospital | -0.192 |
slams | -0.183 |
mun | -0.169 |
mistakes | -0.167 |
arre | -0.164 |
Token | took |
Token ID | 1718 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
hospital | +0.009 |
slams | +0.008 |
clinic | +0.007 |
mun | +0.007 |
promises | +0.007 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.006 |
red | -0.006 |
seven | -0.005 |
ago | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
hospital | +0.052 |
slams | +0.048 |
clinic | +0.044 |
mun | +0.043 |
cleans | +0.041 |
Neg logit contributions | |
ever | -0.048 |
bye | -0.047 |
red | -0.046 |
seven | -0.043 |
ago | -0.041 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ever | +0.020 |
bye | +0.019 |
red | +0.019 |
ago | +0.018 |
seven | +0.018 |
Neg logit contributions | |
hospital | -0.016 |
slams | -0.014 |
clinic | -0.013 |
mun | -0.013 |
chores | -0.012 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ever | +0.140 |
bye | +0.138 |
red | +0.138 |
By | +0.131 |
ago | +0.130 |
Neg logit contributions | |
hospital | -0.134 |
slams | -0.119 |
clinic | -0.110 |
chores | -0.106 |
mun | -0.105 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
ever | +0.077 |
bye | +0.075 |
red | +0.068 |
By | +0.064 |
seven | +0.058 |
Neg logit contributions | |
hospital | -0.231 |
slams | -0.220 |
clinic | -0.205 |
mun | -0.204 |
promises | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
bye | +0.519 |
red | +0.508 |
ever | +0.502 |
By | +0.479 |
seven | +0.470 |
Neg logit contributions | |
hospital | -0.537 |
slams | -0.474 |
clinic | -0.445 |
chores | -0.444 |
promises | -0.427 |
Token | They |
Token ID | 1119 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
bye | +0.020 |
ever | +0.020 |
red | +0.019 |
ago | +0.018 |
seven | +0.018 |
Neg logit contributions | |
hospital | -0.028 |
slams | -0.026 |
mun | -0.024 |
clinic | -0.024 |
promises | -0.023 |
Token | l |
Token ID | 300 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
hospital | +0.082 |
slams | +0.075 |
clinic | +0.070 |
mun | +0.069 |
promises | +0.067 |
Neg logit contributions | |
ever | -0.055 |
bye | -0.054 |
red | -0.053 |
seven | -0.047 |
ago | -0.047 |
Token | icked |
Token ID | 9484 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
bye | +0.017 |
ever | +0.016 |
red | +0.014 |
seven | +0.014 |
By | +0.014 |
Neg logit contributions | |
hospital | -0.023 |
slams | -0.022 |
cleans | -0.020 |
mun | -0.020 |
clinic | -0.020 |
Token | them |
Token ID | 606 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ever | +0.140 |
red | +0.133 |
bye | +0.125 |
seven | +0.120 |
By | +0.111 |
Neg logit contributions | |
hospital | -0.204 |
slams | -0.187 |
clinic | -0.183 |
mun | -0.174 |
operating | -0.160 |
Token | different |
Token ID | 1180 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ever | +0.045 |
bye | +0.043 |
red | +0.042 |
seven | +0.039 |
ago | +0.039 |
Neg logit contributions | |
hospital | -0.055 |
slams | -0.051 |
clinic | -0.047 |
mun | -0.046 |
cleans | -0.044 |
Token | kinds |
Token ID | 6982 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
hospital | +0.114 |
slams | +0.106 |
clinic | +0.097 |
mun | +0.093 |
cleans | +0.091 |
Neg logit contributions | |
ever | -0.094 |
bye | -0.092 |
red | -0.090 |
ago | -0.082 |
seven | -0.082 |
Token | of |
Token ID | 286 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
bye | +0.105 |
red | +0.097 |
By | +0.095 |
seven | +0.094 |
rac | +0.089 |
Neg logit contributions | |
hospital | -0.116 |
slams | -0.103 |
mistakes | -0.094 |
promises | -0.092 |
mun | -0.091 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ever | +0.043 |
bye | +0.041 |
red | +0.040 |
seven | +0.037 |
ago | +0.037 |
Neg logit contributions | |
hospital | -0.058 |
slams | -0.054 |
clinic | -0.050 |
mun | -0.048 |
cleans | -0.047 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
bye | +0.143 |
red | +0.141 |
ever | +0.139 |
By | +0.136 |
seven | +0.132 |
Neg logit contributions | |
hospital | -0.131 |
slams | -0.115 |
mun | -0.107 |
chores | -0.106 |
clinic | -0.105 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
bye | +0.084 |
ever | +0.083 |
red | +0.075 |
By | +0.072 |
seven | +0.065 |
Neg logit contributions | |
hospital | -0.228 |
slams | -0.217 |
mun | -0.202 |
clinic | -0.201 |
promises | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
bye | +0.545 |
red | +0.523 |
ever | +0.504 |
By | +0.500 |
seven | +0.491 |
Neg logit contributions | |
hospital | -0.513 |
slams | -0.446 |
chores | -0.425 |
clinic | -0.410 |
mun | -0.409 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ever | +0.002 |
bye | +0.002 |
red | +0.002 |
ago | +0.002 |
seven | +0.002 |
Neg logit contributions | |
hospital | -0.004 |
slams | -0.004 |
mun | -0.004 |
clinic | -0.004 |
chores | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
hospital | +0.066 |
slams | +0.059 |
clinic | +0.055 |
mun | +0.052 |
chores | +0.052 |
Neg logit contributions | |
ever | -0.073 |
bye | -0.071 |
red | -0.071 |
seven | -0.065 |
ago | -0.064 |
Token | picked |
Token ID | 6497 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
hospital | +0.146 |
slams | +0.132 |
clinic | +0.120 |
mun | +0.119 |
promises | +0.114 |
Neg logit contributions | |
ever | -0.139 |
bye | -0.138 |
red | -0.134 |
ago | -0.125 |
seven | -0.124 |
Token | one |
Token ID | 530 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
ever | +0.003 |
bye | +0.003 |
red | +0.003 |
seven | +0.003 |
ago | +0.002 |
Neg logit contributions | |
hospital | -0.003 |
slams | -0.003 |
clinic | -0.002 |
mun | -0.002 |
cleans | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
hospital | +0.179 |
slams | +0.166 |
mun | +0.160 |
clinic | +0.153 |
mistakes | +0.150 |
Neg logit contributions | |
ever | -0.121 |
red | -0.112 |
ago | -0.104 |
bye | -0.100 |
hy | -0.099 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
hospital | +0.012 |
slams | +0.011 |
clinic | +0.010 |
mun | +0.010 |
cleans | +0.010 |
Neg logit contributions | |
ever | -0.009 |
bye | -0.009 |
red | -0.009 |
By | -0.008 |
seven | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ever | +0.014 |
red | +0.012 |
ago | +0.012 |
bye | +0.011 |
hy | +0.011 |
Neg logit contributions | |
hospital | -0.017 |
slams | -0.016 |
mun | -0.015 |
clinic | -0.014 |
cleans | -0.014 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
bye | +0.015 |
ever | +0.015 |
red | +0.014 |
By | +0.013 |
ago | +0.013 |
Neg logit contributions | |
hospital | -0.017 |
slams | -0.015 |
chores | -0.014 |
clinic | -0.014 |
cleans | -0.014 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ever | +0.133 |
bye | +0.133 |
red | +0.128 |
By | +0.121 |
seven | +0.119 |
Neg logit contributions | |
hospital | -0.135 |
slams | -0.123 |
clinic | -0.112 |
mun | -0.110 |
chores | -0.108 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
bye | +0.085 |
ever | +0.085 |
red | +0.077 |
By | +0.071 |
seven | +0.067 |
Neg logit contributions | |
hospital | -0.220 |
slams | -0.209 |
clinic | -0.194 |
mun | -0.193 |
promises | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
bye | +0.498 |
ever | +0.493 |
red | +0.482 |
seven | +0.446 |
By | +0.445 |
Neg logit contributions | |
hospital | -0.564 |
slams | -0.510 |
clinic | -0.471 |
mun | -0.461 |
chores | -0.454 |
Token | She |
Token ID | 1375 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
ever | +0.019 |
bye | +0.018 |
red | +0.018 |
ago | +0.018 |
seven | +0.017 |
Neg logit contributions | |
hospital | -0.026 |
slams | -0.024 |
mun | -0.023 |
clinic | -0.023 |
promises | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
hospital | +0.060 |
slams | +0.054 |
clinic | +0.050 |
mun | +0.049 |
chores | +0.048 |
Neg logit contributions | |
ever | -0.052 |
bye | -0.051 |
red | -0.050 |
seven | -0.046 |
ago | -0.046 |
Token | angry |
Token ID | 7954 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
hospital | +0.053 |
slams | +0.048 |
clinic | +0.042 |
mun | +0.041 |
chores | +0.040 |
Neg logit contributions | |
bye | -0.057 |
red | -0.054 |
ever | -0.053 |
By | -0.049 |
ago | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
bye | +0.008 |
ever | +0.008 |
red | +0.008 |
seven | +0.007 |
By | +0.007 |
Neg logit contributions | |
hospital | -0.008 |
slams | -0.007 |
clinic | -0.007 |
mun | -0.007 |
promises | -0.006 |
Token | offer |
Token ID | 2897 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
hospital | +0.001 |
slams | +0.001 |
mistakes | +0.001 |
clinic | +0.001 |
mun | +0.001 |
Neg logit contributions | |
ever | -0.001 |
bye | -0.001 |
red | -0.001 |
seven | -0.001 |
ago | -0.001 |
Token | them |
Token ID | 606 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ever | +0.082 |
bye | +0.079 |
red | +0.077 |
seven | +0.073 |
ago | +0.070 |
Neg logit contributions | |
hospital | -0.088 |
slams | -0.083 |
clinic | -0.075 |
mun | -0.073 |
cleans | -0.069 |
Token | their |
Token ID | 511 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ever | +0.077 |
bye | +0.075 |
red | +0.073 |
seven | +0.067 |
By | +0.064 |
Neg logit contributions | |
hospital | -0.124 |
slams | -0.115 |
clinic | -0.107 |
mun | -0.105 |
cleans | -0.102 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ever | +0.088 |
bye | +0.086 |
red | +0.081 |
seven | +0.078 |
ago | +0.076 |
Neg logit contributions | |
hospital | -0.106 |
slams | -0.099 |
mun | -0.090 |
clinic | -0.090 |
cleans | -0.085 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
red | +0.141 |
ago | +0.139 |
bye | +0.138 |
By | +0.138 |
ever | +0.137 |
Neg logit contributions | |
hospital | -0.111 |
slams | -0.098 |
promises | -0.090 |
clinic | -0.089 |
chores | -0.088 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
bye | +0.087 |
ever | +0.087 |
red | +0.079 |
By | +0.078 |
hy | +0.069 |
Neg logit contributions | |
hospital | -0.212 |
slams | -0.204 |
mun | -0.188 |
clinic | -0.187 |
promises | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
bye | +0.550 |
red | +0.543 |
ever | +0.531 |
By | +0.523 |
ago | +0.507 |
Neg logit contributions | |
hospital | -0.479 |
slams | -0.414 |
clinic | -0.393 |
chores | -0.392 |
promises | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
ever | +0.036 |
bye | +0.036 |
red | +0.035 |
seven | +0.032 |
ago | +0.032 |
Neg logit contributions | |
hospital | -0.038 |
slams | -0.035 |
clinic | -0.032 |
mun | -0.031 |
promises | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
ever | +0.005 |
bye | +0.005 |
red | +0.005 |
seven | +0.005 |
ago | +0.005 |
Neg logit contributions | |
hospital | -0.006 |
slams | -0.006 |
clinic | -0.005 |
mun | -0.005 |
promises | -0.005 |
Token | " |
Token ID | 1 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
red | +0.005 |
ever | +0.005 |
bye | +0.005 |
ring | +0.005 |
ago | +0.005 |
Neg logit contributions | |
hospital | -0.006 |
slams | -0.005 |
mun | -0.005 |
clinic | -0.005 |
cleans | -0.005 |
Token | Hi |
Token ID | 17250 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ever | +0.160 |
bye | +0.158 |
red | +0.155 |
ago | +0.149 |
seven | +0.137 |
Neg logit contributions | |
hospital | -0.192 |
slams | -0.172 |
mun | -0.165 |
clinic | -0.162 |
cleans | -0.155 |
Token | to |
Token ID | 284 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
ever | +0.041 |
bye | +0.034 |
red | +0.033 |
seven | +0.030 |
ago | +0.028 |
Neg logit contributions | |
hospital | -0.104 |
slams | -0.101 |
mun | -0.096 |
clinic | -0.095 |
promises | -0.090 |
Token | share |
Token ID | 2648 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.006 |
mun | +0.006 |
clinic | +0.006 |
cleans | +0.005 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.005 |
red | -0.005 |
seven | -0.005 |
ago | -0.004 |
Token | their |
Token ID | 511 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ever | +0.039 |
red | +0.036 |
bye | +0.036 |
seven | +0.035 |
ago | +0.033 |
Neg logit contributions | |
hospital | -0.057 |
slams | -0.052 |
clinic | -0.048 |
mun | -0.048 |
mistakes | -0.045 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ever | +0.084 |
bye | +0.083 |
red | +0.080 |
seven | +0.074 |
ago | +0.074 |
Neg logit contributions | |
hospital | -0.103 |
slams | -0.095 |
clinic | -0.087 |
mun | -0.085 |
cleans | -0.082 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ever | +0.128 |
bye | +0.126 |
red | +0.125 |
ago | +0.117 |
By | +0.116 |
Neg logit contributions | |
hospital | -0.135 |
slams | -0.122 |
clinic | -0.112 |
mun | -0.110 |
promises | -0.107 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.13e+00 |
Pos logit contributions | |
ever | +0.078 |
bye | +0.076 |
By | +0.070 |
red | +0.069 |
ago | +0.059 |
Neg logit contributions | |
hospital | -0.225 |
slams | -0.217 |
mun | -0.201 |
clinic | -0.200 |
promises | -0.200 |
Token | with |
Token ID | 351 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
bye | +0.527 |
red | +0.523 |
ever | +0.512 |
By | +0.498 |
ago | +0.489 |
Neg logit contributions | |
hospital | -0.517 |
slams | -0.460 |
clinic | -0.426 |
promises | -0.420 |
chores | -0.420 |
Token | their |
Token ID | 511 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ever | +0.018 |
bye | +0.018 |
red | +0.018 |
ago | +0.016 |
By | +0.016 |
Neg logit contributions | |
hospital | -0.019 |
slams | -0.017 |
clinic | -0.016 |
mun | -0.016 |
chores | -0.015 |
Token | friends |
Token ID | 2460 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ever | +0.087 |
red | +0.087 |
bye | +0.086 |
By | +0.078 |
ago | +0.077 |
Neg logit contributions | |
hospital | -0.098 |
slams | -0.088 |
clinic | -0.082 |
mun | -0.080 |
promises | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
hospital | +0.030 |
slams | +0.027 |
clinic | +0.025 |
mun | +0.025 |
promises | +0.024 |
Neg logit contributions | |
ever | -0.024 |
bye | -0.024 |
red | -0.023 |
seven | -0.021 |
ago | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
ever | +0.034 |
bye | +0.034 |
red | +0.033 |
seven | +0.031 |
ago | +0.031 |
Neg logit contributions | |
hospital | -0.041 |
slams | -0.037 |
clinic | -0.034 |
mun | -0.034 |
chores | -0.033 |
Token | your |
Token ID | 534 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
bye | +0.132 |
red | +0.127 |
ever | +0.127 |
By | +0.122 |
hy | +0.115 |
Neg logit contributions | |
hospital | -0.122 |
slams | -0.110 |
promises | -0.100 |
clinic | -0.098 |
chores | -0.098 |
Token | toys |
Token ID | 14958 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
ever | +0.037 |
bye | +0.036 |
red | +0.035 |
seven | +0.033 |
ago | +0.033 |
Neg logit contributions | |
hospital | -0.037 |
slams | -0.034 |
clinic | -0.031 |
mun | -0.030 |
cleans | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
hospital | +0.038 |
slams | +0.033 |
clinic | +0.030 |
chores | +0.030 |
promises | +0.030 |
Neg logit contributions | |
red | -0.038 |
bye | -0.038 |
By | -0.035 |
ever | -0.035 |
hy | -0.034 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
bye | +0.029 |
red | +0.029 |
ever | +0.028 |
By | +0.026 |
seven | +0.026 |
Neg logit contributions | |
hospital | -0.031 |
slams | -0.027 |
clinic | -0.025 |
chores | -0.025 |
mistakes | -0.024 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
bye | +0.141 |
red | +0.141 |
ever | +0.141 |
By | +0.136 |
seven | +0.131 |
Neg logit contributions | |
hospital | -0.134 |
slams | -0.119 |
clinic | -0.110 |
chores | -0.107 |
promises | -0.106 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.13e+00 |
Pos logit contributions | |
bye | +0.095 |
ever | +0.094 |
red | +0.086 |
By | +0.083 |
seven | +0.076 |
Neg logit contributions | |
hospital | -0.223 |
slams | -0.212 |
clinic | -0.196 |
mun | -0.194 |
promises | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
bye | +0.514 |
red | +0.511 |
ever | +0.495 |
By | +0.484 |
seven | +0.466 |
Neg logit contributions | |
hospital | -0.536 |
slams | -0.467 |
clinic | -0.443 |
chores | -0.436 |
promises | -0.420 |
Token | You |
Token ID | 921 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ever | +0.017 |
bye | +0.016 |
red | +0.016 |
ago | +0.015 |
seven | +0.015 |
Neg logit contributions | |
hospital | -0.022 |
slams | -0.020 |
mun | -0.018 |
clinic | -0.018 |
chores | -0.018 |
Token | will |
Token ID | 481 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
hospital | +0.086 |
slams | +0.079 |
clinic | +0.073 |
mun | +0.072 |
mistakes | +0.069 |
Neg logit contributions | |
ever | -0.068 |
bye | -0.064 |
red | -0.063 |
seven | -0.058 |
By | -0.057 |
Token | not |
Token ID | 407 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
hospital | +0.111 |
slams | +0.100 |
clinic | +0.093 |
mun | +0.089 |
chores | +0.088 |
Neg logit contributions | |
bye | -0.093 |
ever | -0.093 |
red | -0.093 |
seven | -0.084 |
ago | -0.084 |
Token | go |
Token ID | 467 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
ever | +0.081 |
bye | +0.079 |
red | +0.077 |
seven | +0.071 |
ago | +0.071 |
Neg logit contributions | |
hospital | -0.085 |
slams | -0.078 |
clinic | -0.072 |
mun | -0.071 |
cleans | -0.068 |
Token | you |
Token ID | 345 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
hospital | +0.167 |
slams | +0.154 |
clinic | +0.143 |
mun | +0.142 |
chores | +0.139 |
Neg logit contributions | |
ever | -0.100 |
bye | -0.100 |
red | -0.100 |
ago | -0.088 |
seven | -0.087 |
Token | want |
Token ID | 765 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
bye | +0.055 |
red | +0.054 |
ever | +0.053 |
By | +0.049 |
seven | +0.048 |
Neg logit contributions | |
hospital | -0.066 |
slams | -0.059 |
mun | -0.055 |
clinic | -0.055 |
promises | -0.054 |
Token | some |
Token ID | 617 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
red | +0.056 |
bye | +0.056 |
ever | +0.056 |
ago | +0.051 |
By | +0.051 |
Neg logit contributions | |
hospital | -0.076 |
slams | -0.068 |
clinic | -0.063 |
chores | -0.062 |
promises | -0.061 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
hospital | +0.175 |
slams | +0.157 |
clinic | +0.145 |
mun | +0.141 |
chores | +0.140 |
Neg logit contributions | |
ever | -0.161 |
red | -0.159 |
bye | -0.159 |
ago | -0.146 |
By | -0.144 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
red | +0.148 |
By | +0.146 |
ago | +0.145 |
bye | +0.142 |
ever | +0.140 |
Neg logit contributions | |
hospital | -0.105 |
slams | -0.089 |
chores | -0.084 |
promises | -0.083 |
mun | -0.083 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.13e+00 |
Pos logit contributions | |
ever | +0.079 |
bye | +0.079 |
By | +0.072 |
red | +0.070 |
seven | +0.061 |
Neg logit contributions | |
hospital | -0.217 |
slams | -0.210 |
mun | -0.194 |
clinic | -0.192 |
promises | -0.190 |
Token | ?" |
Token ID | 1701 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
red | +0.605 |
By | +0.589 |
bye | +0.577 |
ever | +0.568 |
ago | +0.568 |
Neg logit contributions | |
hospital | -0.436 |
chores | -0.360 |
slams | -0.358 |
clinic | -0.338 |
promises | -0.328 |
Token | Mia |
Token ID | 32189 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ever | +0.020 |
bye | +0.018 |
seven | +0.018 |
red | +0.017 |
ago | +0.017 |
Neg logit contributions | |
hospital | -0.035 |
slams | -0.033 |
clinic | -0.032 |
mun | -0.031 |
promises | -0.030 |
Token | says |
Token ID | 1139 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
hospital | +0.117 |
clinic | +0.103 |
chores | +0.102 |
slams | +0.101 |
treadmill | +0.098 |
Neg logit contributions | |
seven | -0.102 |
ever | -0.100 |
red | -0.097 |
ago | -0.097 |
bye | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ever | +0.001 |
bye | +0.001 |
red | +0.001 |
seven | +0.001 |
ago | +0.001 |
Neg logit contributions | |
hospital | -0.001 |
slams | -0.001 |
clinic | -0.001 |
mun | -0.001 |
promises | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
ever | +0.034 |
bye | +0.033 |
red | +0.032 |
seven | +0.030 |
ago | +0.030 |
Neg logit contributions | |
hospital | -0.039 |
slams | -0.036 |
clinic | -0.033 |
mun | -0.032 |
promises | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
hospital | +0.002 |
slams | +0.002 |
mun | +0.002 |
clinic | +0.002 |
promises | +0.002 |
Neg logit contributions | |
ever | -0.001 |
bye | -0.001 |
red | -0.001 |
ago | -0.001 |
seven | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ever | +0.042 |
bye | +0.041 |
red | +0.040 |
ago | +0.036 |
seven | +0.036 |
Neg logit contributions | |
hospital | -0.061 |
slams | -0.056 |
clinic | -0.052 |
mun | -0.051 |
cleans | -0.049 |
Token | delicious |
Token ID | 12625 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ever | +0.060 |
red | +0.056 |
bye | +0.056 |
seven | +0.054 |
ago | +0.052 |
Neg logit contributions | |
hospital | -0.070 |
slams | -0.068 |
clinic | -0.063 |
mun | -0.060 |
promises | -0.059 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ever | +0.021 |
red | +0.020 |
bye | +0.020 |
seven | +0.019 |
ago | +0.019 |
Neg logit contributions | |
hospital | -0.022 |
slams | -0.020 |
clinic | -0.018 |
mun | -0.017 |
cleans | -0.017 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
bye | +0.143 |
ever | +0.139 |
red | +0.138 |
By | +0.132 |
ago | +0.128 |
Neg logit contributions | |
hospital | -0.133 |
slams | -0.119 |
clinic | -0.107 |
mun | -0.107 |
chores | -0.105 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.13e+00 |
Pos logit contributions | |
bye | +0.108 |
ever | +0.107 |
red | +0.096 |
By | +0.095 |
seven | +0.088 |
Neg logit contributions | |
hospital | -0.205 |
slams | -0.195 |
clinic | -0.178 |
mun | -0.178 |
cleans | -0.173 |
Token | and |
Token ID | 290 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
bye | +0.540 |
red | +0.516 |
ever | +0.512 |
By | +0.493 |
seven | +0.481 |
Neg logit contributions | |
hospital | -0.526 |
slams | -0.468 |
clinic | -0.429 |
chores | -0.428 |
mun | -0.423 |
Token | y |
Token ID | 331 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
hospital | +0.027 |
slams | +0.025 |
mun | +0.023 |
clinic | +0.023 |
cleans | +0.022 |
Neg logit contributions | |
bye | -0.023 |
ever | -0.023 |
red | -0.022 |
By | -0.021 |
ago | -0.020 |
Token | ummy |
Token ID | 13513 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
hospital | +0.060 |
slams | +0.056 |
mistakes | +0.053 |
chores | +0.053 |
mun | +0.052 |
Neg logit contributions | |
ever | -0.035 |
bye | -0.035 |
seven | -0.033 |
red | -0.033 |
By | -0.032 |
Token | pops |
Token ID | 26384 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
ever | +0.131 |
red | +0.125 |
bye | +0.123 |
ago | +0.115 |
seven | +0.115 |
Neg logit contributions | |
hospital | -0.128 |
slams | -0.118 |
clinic | -0.107 |
mun | -0.102 |
cleans | -0.099 |
Token | icles |
Token ID | 2983 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
bye | +0.046 |
ever | +0.044 |
By | +0.043 |
red | +0.041 |
ago | +0.041 |
Neg logit contributions | |
hospital | -0.064 |
slams | -0.058 |
chores | -0.055 |
mun | -0.054 |
mistakes | -0.053 |
Token | They |
Token ID | 1119 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
ever | +0.036 |
bye | +0.036 |
red | +0.035 |
seven | +0.032 |
ago | +0.032 |
Neg logit contributions | |
hospital | -0.038 |
slams | -0.034 |
clinic | -0.031 |
mun | -0.030 |
cleans | -0.030 |
Token | lick |
Token ID | 36728 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
hospital | +0.056 |
slams | +0.051 |
clinic | +0.047 |
mun | +0.046 |
mistakes | +0.045 |
Neg logit contributions | |
ever | -0.053 |
bye | -0.051 |
red | -0.049 |
seven | -0.047 |
ago | -0.046 |
Token | their |
Token ID | 511 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ever | +0.065 |
red | +0.062 |
bye | +0.061 |
seven | +0.058 |
By | +0.054 |
Neg logit contributions | |
hospital | -0.089 |
slams | -0.082 |
clinic | -0.078 |
mun | -0.074 |
promises | -0.070 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ever | +0.095 |
bye | +0.093 |
red | +0.092 |
ago | +0.088 |
By | +0.086 |
Neg logit contributions | |
hospital | -0.096 |
slams | -0.085 |
chores | -0.079 |
mun | -0.078 |
clinic | -0.078 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ever | +0.139 |
bye | +0.138 |
red | +0.136 |
ago | +0.134 |
By | +0.131 |
Neg logit contributions | |
hospital | -0.125 |
slams | -0.112 |
mun | -0.103 |
clinic | -0.101 |
chores | -0.099 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
ever | +0.083 |
bye | +0.081 |
red | +0.072 |
By | +0.069 |
ago | +0.063 |
Neg logit contributions | |
hospital | -0.232 |
slams | -0.223 |
clinic | -0.206 |
mun | -0.206 |
promises | -0.202 |
Token | and |
Token ID | 290 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
bye | +0.525 |
ever | +0.517 |
red | +0.512 |
ago | +0.484 |
seven | +0.477 |
Neg logit contributions | |
hospital | -0.525 |
slams | -0.467 |
clinic | -0.433 |
chores | -0.424 |
mun | -0.423 |
Token | smile |
Token ID | 8212 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
bye | +0.001 |
red | +0.001 |
ever | +0.001 |
By | +0.001 |
ago | +0.001 |
Neg logit contributions | |
hospital | -0.001 |
slams | -0.001 |
clinic | -0.001 |
mun | -0.001 |
promises | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
bye | +0.272 |
ever | +0.268 |
red | +0.261 |
ago | +0.252 |
hy | +0.247 |
Neg logit contributions | |
hospital | -0.227 |
slams | -0.196 |
clinic | -0.186 |
chores | -0.185 |
promises | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ever | +0.036 |
bye | +0.035 |
red | +0.034 |
seven | +0.032 |
ago | +0.032 |
Neg logit contributions | |
hospital | -0.039 |
slams | -0.035 |
clinic | -0.032 |
mun | -0.032 |
promises | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ever | +0.008 |
bye | +0.008 |
red | +0.008 |
seven | +0.007 |
ago | +0.007 |
Neg logit contributions | |
hospital | -0.010 |
slams | -0.009 |
clinic | -0.008 |
mun | -0.008 |
promises | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
ever | +0.013 |
seven | +0.011 |
bye | +0.011 |
ago | +0.011 |
red | +0.010 |
Neg logit contributions | |
hospital | -0.030 |
slams | -0.028 |
mun | -0.027 |
clinic | -0.027 |
cleans | -0.026 |
Token | sand |
Token ID | 6450 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ever | +0.004 |
red | +0.004 |
bye | +0.004 |
ago | +0.004 |
By | +0.003 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.004 |
clinic | -0.004 |
mun | -0.004 |
chores | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
bye | +0.210 |
ever | +0.209 |
red | +0.208 |
By | +0.191 |
seven | +0.188 |
Neg logit contributions | |
hospital | -0.232 |
slams | -0.209 |
clinic | -0.194 |
mun | -0.190 |
promises | -0.183 |
Token | Then |
Token ID | 3244 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
mun | +0.002 |
promises | +0.002 |
clinic | +0.002 |
Neg logit contributions | |
red | -0.002 |
ever | -0.002 |
bye | -0.002 |
seven | -0.002 |
ago | -0.002 |
Token | P |
Token ID | 350 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ever | +0.032 |
bye | +0.031 |
red | +0.030 |
seven | +0.028 |
ago | +0.027 |
Neg logit contributions | |
hospital | -0.048 |
slams | -0.044 |
clinic | -0.041 |
mun | -0.040 |
cleans | -0.039 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
hospital | +0.182 |
slams | +0.161 |
clinic | +0.151 |
chores | +0.150 |
promises | +0.150 |
Neg logit contributions | |
ever | -0.177 |
bye | -0.172 |
red | -0.166 |
By | -0.160 |
seven | -0.158 |
Token | dad |
Token ID | 9955 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
bye | +0.458 |
red | +0.448 |
ever | +0.448 |
seven | +0.407 |
ago | +0.406 |
Neg logit contributions | |
hospital | -0.604 |
slams | -0.519 |
mun | -0.504 |
clinic | -0.491 |
chores | -0.479 |
Token | said |
Token ID | 531 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ever | +0.153 |
bye | +0.148 |
red | +0.146 |
seven | +0.133 |
ago | +0.132 |
Neg logit contributions | |
hospital | -0.210 |
slams | -0.194 |
clinic | -0.179 |
mun | -0.175 |
chores | -0.170 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
hospital | +0.016 |
slams | +0.013 |
chores | +0.013 |
mun | +0.013 |
clinic | +0.013 |
Neg logit contributions | |
bye | -0.017 |
red | -0.016 |
ever | -0.016 |
By | -0.015 |
seven | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.019 |
clinic | +0.018 |
mun | +0.017 |
cleans | +0.017 |
Neg logit contributions | |
bye | -0.019 |
ever | -0.019 |
red | -0.018 |
By | -0.016 |
ago | -0.016 |
Token | Let |
Token ID | 5756 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
hospital | +0.029 |
mun | +0.026 |
slams | +0.024 |
clinic | +0.024 |
arre | +0.023 |
Neg logit contributions | |
ever | -0.027 |
ago | -0.027 |
red | -0.026 |
bye | -0.026 |
hy | -0.025 |
Token | They |
Token ID | 2990 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
ever | +0.005 |
red | +0.005 |
bye | +0.005 |
ago | +0.004 |
seven | +0.004 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.004 |
clinic | -0.004 |
mun | -0.004 |
promises | -0.004 |
Token | bought |
Token ID | 5839 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
bye | +0.044 |
ever | +0.043 |
red | +0.042 |
ago | +0.039 |
By | +0.037 |
Neg logit contributions | |
hospital | -0.059 |
slams | -0.055 |
mun | -0.049 |
clinic | -0.049 |
cleans | -0.048 |
Token | two |
Token ID | 734 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
bye | +0.025 |
ever | +0.025 |
red | +0.024 |
seven | +0.024 |
By | +0.021 |
Neg logit contributions | |
hospital | -0.039 |
slams | -0.039 |
clinic | -0.036 |
mun | -0.035 |
arre | -0.033 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
hospital | +0.093 |
slams | +0.086 |
clinic | +0.079 |
mun | +0.077 |
cleans | +0.075 |
Neg logit contributions | |
ever | -0.071 |
bye | -0.069 |
red | -0.067 |
seven | -0.062 |
ago | -0.061 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
bye | +0.138 |
ever | +0.137 |
red | +0.134 |
By | +0.129 |
ago | +0.126 |
Neg logit contributions | |
hospital | -0.121 |
slams | -0.107 |
clinic | -0.099 |
chores | -0.099 |
mun | -0.098 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
ever | +0.075 |
bye | +0.073 |
red | +0.067 |
By | +0.059 |
seven | +0.057 |
Neg logit contributions | |
hospital | -0.226 |
slams | -0.214 |
clinic | -0.200 |
mun | -0.199 |
promises | -0.195 |
Token | and |
Token ID | 290 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
bye | +0.560 |
red | +0.548 |
ever | +0.543 |
By | +0.531 |
seven | +0.511 |
Neg logit contributions | |
hospital | -0.482 |
slams | -0.414 |
clinic | -0.394 |
chores | -0.393 |
promises | -0.383 |
Token | l |
Token ID | 300 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
hospital | +0.013 |
slams | +0.012 |
cleans | +0.011 |
chores | +0.011 |
clinic | +0.011 |
Neg logit contributions | |
bye | -0.013 |
ever | -0.012 |
red | -0.012 |
By | -0.011 |
ago | -0.011 |
Token | icked |
Token ID | 9484 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
bye | +0.015 |
ever | +0.014 |
red | +0.014 |
By | +0.013 |
seven | +0.013 |
Neg logit contributions | |
hospital | -0.018 |
slams | -0.017 |
clinic | -0.016 |
mun | -0.015 |
chores | -0.015 |
Token | them |
Token ID | 606 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ever | +0.133 |
red | +0.128 |
bye | +0.120 |
seven | +0.117 |
By | +0.106 |
Neg logit contributions | |
hospital | -0.205 |
slams | -0.187 |
clinic | -0.184 |
mun | -0.177 |
operating | -0.164 |
Token | happily |
Token ID | 18177 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ever | +0.080 |
bye | +0.076 |
red | +0.075 |
seven | +0.068 |
By | +0.064 |
Neg logit contributions | |
hospital | -0.118 |
slams | -0.109 |
clinic | -0.102 |
mun | -0.102 |
cleans | -0.097 |
Token | toys |
Token ID | 14958 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
ever | +0.101 |
bye | +0.098 |
red | +0.093 |
ago | +0.089 |
seven | +0.088 |
Neg logit contributions | |
hospital | -0.094 |
slams | -0.087 |
mun | -0.079 |
clinic | -0.079 |
cleans | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
hospital | +0.044 |
slams | +0.039 |
clinic | +0.036 |
chores | +0.034 |
promises | +0.034 |
Neg logit contributions | |
bye | -0.039 |
red | -0.039 |
ever | -0.038 |
seven | -0.035 |
By | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
hospital | +0.010 |
slams | +0.009 |
clinic | +0.008 |
mun | +0.008 |
promises | +0.008 |
Neg logit contributions | |
ever | -0.008 |
bye | -0.008 |
red | -0.008 |
seven | -0.008 |
ago | -0.007 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ever | +0.101 |
bye | +0.096 |
red | +0.091 |
ago | +0.089 |
seven | +0.087 |
Neg logit contributions | |
hospital | -0.098 |
slams | -0.091 |
mun | -0.086 |
clinic | -0.084 |
cleans | -0.078 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
bye | +0.139 |
ever | +0.138 |
red | +0.137 |
By | +0.131 |
seven | +0.129 |
Neg logit contributions | |
hospital | -0.132 |
slams | -0.119 |
clinic | -0.108 |
mun | -0.103 |
chores | -0.103 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
bye | +0.116 |
ever | +0.115 |
By | +0.104 |
red | +0.102 |
seven | +0.095 |
Neg logit contributions | |
hospital | -0.194 |
slams | -0.187 |
clinic | -0.168 |
mun | -0.167 |
cleans | -0.163 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
bye | +0.504 |
ever | +0.487 |
red | +0.482 |
seven | +0.455 |
By | +0.448 |
Neg logit contributions | |
hospital | -0.563 |
slams | -0.506 |
clinic | -0.471 |
chores | -0.454 |
mun | -0.452 |
Token | and |
Token ID | 290 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
hospital | +0.009 |
slams | +0.008 |
clinic | +0.007 |
promises | +0.007 |
cleans | +0.007 |
Neg logit contributions | |
bye | -0.010 |
red | -0.009 |
ever | -0.009 |
By | -0.009 |
seven | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
hospital | +0.005 |
slams | +0.004 |
clinic | +0.004 |
chores | +0.004 |
cleans | +0.004 |
Neg logit contributions | |
bye | -0.004 |
red | -0.004 |
ever | -0.004 |
By | -0.004 |
seven | -0.003 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ever | +0.099 |
bye | +0.095 |
red | +0.091 |
ago | +0.088 |
seven | +0.087 |
Neg logit contributions | |
hospital | -0.098 |
slams | -0.090 |
mun | -0.084 |
clinic | -0.083 |
cleans | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
hospital | +0.016 |
slams | +0.014 |
clinic | +0.013 |
chores | +0.012 |
promises | +0.012 |
Neg logit contributions | |
bye | -0.014 |
red | -0.014 |
ever | -0.014 |
By | -0.013 |
seven | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
red | +0.091 |
ever | +0.089 |
bye | +0.087 |
By | +0.085 |
seven | +0.083 |
Neg logit contributions | |
hospital | -0.086 |
slams | -0.073 |
clinic | -0.068 |
mun | -0.062 |
promises | -0.060 |
Token | There |
Token ID | 1318 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ever | +0.003 |
bye | +0.003 |
red | +0.003 |
ago | +0.003 |
seven | +0.003 |
Neg logit contributions | |
hospital | -0.004 |
slams | -0.004 |
clinic | -0.004 |
mun | -0.004 |
promises | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
hospital | +0.012 |
slams | +0.011 |
clinic | +0.010 |
mun | +0.010 |
promises | +0.009 |
Neg logit contributions | |
ever | -0.009 |
bye | -0.009 |
red | -0.008 |
ago | -0.008 |
seven | -0.008 |
Token | many |
Token ID | 867 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
red | +0.042 |
bye | +0.041 |
ever | +0.040 |
ago | +0.038 |
By | +0.037 |
Neg logit contributions | |
hospital | -0.030 |
slams | -0.025 |
chores | -0.022 |
clinic | -0.022 |
mun | -0.022 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
hospital | +0.066 |
slams | +0.061 |
clinic | +0.057 |
mun | +0.054 |
cleans | +0.054 |
Neg logit contributions | |
ever | -0.054 |
bye | -0.051 |
red | -0.049 |
seven | -0.048 |
ago | -0.046 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
ever | +0.117 |
bye | +0.115 |
red | +0.112 |
seven | +0.100 |
By | +0.100 |
Neg logit contributions | |
hospital | -0.199 |
slams | -0.185 |
clinic | -0.172 |
mun | -0.170 |
promises | -0.165 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
red | +0.524 |
bye | +0.523 |
ever | +0.502 |
By | +0.487 |
seven | +0.475 |
Neg logit contributions | |
hospital | -0.540 |
slams | -0.471 |
clinic | -0.443 |
chores | -0.439 |
mun | -0.436 |
Token | p |
Token ID | 279 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
hospital | +0.026 |
slams | +0.023 |
clinic | +0.021 |
mun | +0.021 |
chores | +0.021 |
Neg logit contributions | |
bye | -0.021 |
ever | -0.020 |
red | -0.020 |
By | -0.018 |
ago | -0.018 |
Token | inks |
Token ID | 2973 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
hospital | +0.122 |
slams | +0.111 |
clinic | +0.097 |
mun | +0.095 |
chores | +0.091 |
Neg logit contributions | |
ever | -0.179 |
bye | -0.176 |
red | -0.173 |
By | -0.163 |
seven | -0.161 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
bye | +0.146 |
ever | +0.139 |
By | +0.135 |
red | +0.134 |
seven | +0.125 |
Neg logit contributions | |
hospital | -0.120 |
slams | -0.107 |
mun | -0.099 |
clinic | -0.098 |
cleans | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
hospital | +0.024 |
slams | +0.022 |
clinic | +0.020 |
mun | +0.019 |
promises | +0.019 |
Neg logit contributions | |
bye | -0.022 |
ever | -0.022 |
red | -0.022 |
By | -0.020 |
ago | -0.020 |
Token | took |
Token ID | 1718 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
hospital | +0.069 |
slams | +0.065 |
clinic | +0.063 |
chores | +0.061 |
mun | +0.061 |
Neg logit contributions | |
ever | -0.042 |
red | -0.038 |
bye | -0.037 |
seven | -0.035 |
By | -0.033 |
Token | away |
Token ID | 1497 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
hospital | +0.036 |
slams | +0.034 |
clinic | +0.033 |
mun | +0.032 |
cleans | +0.029 |
Neg logit contributions | |
ever | -0.028 |
red | -0.026 |
bye | -0.026 |
seven | -0.025 |
wind | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ever | +0.048 |
red | +0.044 |
bye | +0.042 |
seven | +0.041 |
than | +0.037 |
Neg logit contributions | |
hospital | -0.073 |
slams | -0.067 |
clinic | -0.065 |
mun | -0.065 |
mistakes | -0.062 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ever | +0.102 |
bye | +0.099 |
red | +0.097 |
ago | +0.091 |
seven | +0.091 |
Neg logit contributions | |
hospital | -0.097 |
slams | -0.088 |
clinic | -0.080 |
mun | -0.079 |
cleans | -0.075 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
bye | +0.152 |
red | +0.151 |
ever | +0.151 |
By | +0.150 |
ago | +0.143 |
Neg logit contributions | |
hospital | -0.128 |
slams | -0.112 |
clinic | -0.101 |
chores | -0.100 |
promises | -0.099 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
ever | +0.098 |
bye | +0.097 |
red | +0.089 |
By | +0.084 |
seven | +0.078 |
Neg logit contributions | |
hospital | -0.228 |
slams | -0.217 |
clinic | -0.200 |
mun | -0.198 |
promises | -0.194 |
Token | and |
Token ID | 290 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
bye | +0.546 |
red | +0.528 |
ever | +0.521 |
By | +0.507 |
seven | +0.499 |
Neg logit contributions | |
hospital | -0.512 |
slams | -0.447 |
clinic | -0.416 |
chores | -0.410 |
promises | -0.400 |
Token | made |
Token ID | 925 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.005 |
clinic | +0.005 |
mun | +0.005 |
cleans | +0.005 |
Neg logit contributions | |
bye | -0.005 |
ever | -0.004 |
red | -0.004 |
By | -0.004 |
seven | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ever | +0.054 |
bye | +0.050 |
red | +0.049 |
seven | +0.046 |
By | +0.043 |
Neg logit contributions | |
hospital | -0.074 |
slams | -0.072 |
clinic | -0.068 |
mun | -0.066 |
cleans | -0.062 |
Token | go |
Token ID | 467 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
ever | +0.094 |
bye | +0.085 |
red | +0.082 |
seven | +0.075 |
hy | +0.075 |
Neg logit contributions | |
hospital | -0.112 |
slams | -0.104 |
mun | -0.099 |
clinic | -0.099 |
cleans | -0.091 |
Token | back |
Token ID | 736 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
hospital | +0.056 |
slams | +0.051 |
mun | +0.047 |
clinic | +0.047 |
cleans | +0.046 |
Neg logit contributions | |
ever | -0.044 |
bye | -0.041 |
red | -0.041 |
ago | -0.038 |
seven | -0.038 |
Token | pond |
Token ID | 16723 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
bye | +0.004 |
ever | +0.004 |
seven | +0.004 |
By | +0.004 |
ago | +0.004 |
Neg logit contributions | |
slams | -0.004 |
hospital | -0.004 |
mun | -0.003 |
cleans | -0.003 |
arre | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
mun | +0.002 |
clinic | +0.002 |
cleans | +0.002 |
Neg logit contributions | |
ever | -0.002 |
bye | -0.002 |
red | -0.002 |
ago | -0.002 |
seven | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
bye | +0.013 |
ever | +0.013 |
red | +0.013 |
ago | +0.012 |
By | +0.012 |
Neg logit contributions | |
hospital | -0.013 |
slams | -0.012 |
clinic | -0.010 |
chores | -0.010 |
promises | -0.010 |
Token | ice |
Token ID | 4771 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ever | +0.085 |
bye | +0.084 |
red | +0.082 |
seven | +0.076 |
ago | +0.075 |
Neg logit contributions | |
hospital | -0.097 |
slams | -0.088 |
clinic | -0.081 |
mun | -0.079 |
promises | -0.077 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ever | +0.137 |
bye | +0.136 |
red | +0.134 |
By | +0.130 |
seven | +0.126 |
Neg logit contributions | |
hospital | -0.122 |
slams | -0.109 |
clinic | -0.099 |
mun | -0.097 |
chores | -0.096 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
ever | +0.082 |
bye | +0.081 |
red | +0.073 |
By | +0.070 |
hy | +0.062 |
Neg logit contributions | |
hospital | -0.216 |
slams | -0.207 |
clinic | -0.192 |
mun | -0.191 |
promises | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
bye | +0.545 |
red | +0.531 |
ever | +0.528 |
By | +0.497 |
seven | +0.495 |
Neg logit contributions | |
hospital | -0.512 |
slams | -0.445 |
clinic | -0.424 |
chores | -0.408 |
promises | -0.403 |
Token | But |
Token ID | 887 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ever | +0.014 |
bye | +0.014 |
red | +0.014 |
ago | +0.013 |
seven | +0.013 |
Neg logit contributions | |
hospital | -0.016 |
slams | -0.015 |
mun | -0.014 |
clinic | -0.014 |
promises | -0.013 |
Token | when |
Token ID | 618 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
hospital | +0.105 |
slams | +0.093 |
clinic | +0.083 |
chores | +0.081 |
promises | +0.081 |
Neg logit contributions | |
red | -0.088 |
bye | -0.087 |
ever | -0.082 |
hy | -0.077 |
ago | -0.076 |
Token | they |
Token ID | 484 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
hospital | +0.017 |
slams | +0.015 |
clinic | +0.013 |
chores | +0.013 |
promises | +0.013 |
Neg logit contributions | |
red | -0.015 |
bye | -0.015 |
ever | -0.014 |
ring | -0.013 |
ago | -0.013 |
Token | got |
Token ID | 1392 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
hospital | +0.009 |
slams | +0.008 |
mun | +0.007 |
clinic | +0.007 |
cleans | +0.007 |
Neg logit contributions | |
bye | -0.005 |
red | -0.005 |
ever | -0.005 |
ago | -0.005 |
seven | -0.005 |
Token | serve |
Token ID | 4691 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.006 |
clinic | +0.005 |
mun | +0.005 |
chores | +0.005 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.006 |
red | -0.006 |
ago | -0.005 |
seven | -0.005 |
Token | up |
Token ID | 510 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
hospital | +0.102 |
slams | +0.095 |
clinic | +0.087 |
mun | +0.085 |
cleans | +0.082 |
Neg logit contributions | |
ever | -0.084 |
bye | -0.081 |
red | -0.080 |
seven | -0.073 |
ago | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
hospital | +0.351 |
slams | +0.325 |
clinic | +0.302 |
mun | +0.298 |
cleans | +0.284 |
Neg logit contributions | |
ever | -0.247 |
bye | -0.234 |
red | -0.231 |
seven | -0.210 |
ago | -0.210 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
clinic | +0.003 |
mun | +0.003 |
cleans | +0.003 |
Neg logit contributions | |
ever | -0.003 |
bye | -0.003 |
red | -0.003 |
seven | -0.003 |
ago | -0.002 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
bye | +0.133 |
red | +0.133 |
ever | +0.132 |
By | +0.128 |
ago | +0.126 |
Neg logit contributions | |
hospital | -0.132 |
slams | -0.115 |
clinic | -0.108 |
mun | -0.105 |
chores | -0.105 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
ever | +0.091 |
bye | +0.090 |
By | +0.082 |
red | +0.081 |
seven | +0.073 |
Neg logit contributions | |
hospital | -0.216 |
slams | -0.206 |
mun | -0.191 |
clinic | -0.191 |
promises | -0.187 |
Token | and |
Token ID | 290 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
bye | +0.529 |
red | +0.520 |
By | +0.503 |
ever | +0.493 |
seven | +0.487 |
Neg logit contributions | |
hospital | -0.505 |
slams | -0.441 |
chores | -0.423 |
promises | -0.411 |
clinic | -0.410 |
Token | the |
Token ID | 262 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
hospital | +0.029 |
slams | +0.027 |
clinic | +0.025 |
mun | +0.024 |
promises | +0.023 |
Neg logit contributions | |
ever | -0.025 |
bye | -0.025 |
red | -0.024 |
seven | -0.022 |
ago | -0.022 |
Token | family |
Token ID | 1641 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.005 |
clinic | +0.005 |
mun | +0.005 |
cleans | +0.005 |
Neg logit contributions | |
ever | -0.005 |
bye | -0.005 |
red | -0.005 |
seven | -0.004 |
ago | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
bye | +0.083 |
red | +0.081 |
ever | +0.079 |
ago | +0.077 |
seven | +0.076 |
Neg logit contributions | |
hospital | -0.101 |
slams | -0.089 |
mun | -0.085 |
clinic | -0.084 |
cleans | -0.083 |
Token | so |
Token ID | 523 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
hospital | +0.070 |
slams | +0.062 |
clinic | +0.058 |
promises | +0.056 |
chores | +0.055 |
Neg logit contributions | |
bye | -0.065 |
red | -0.062 |
ever | -0.060 |
ago | -0.057 |
By | -0.057 |
Token | man |
Token ID | 582 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
hospital | +0.057 |
slams | +0.053 |
mun | +0.050 |
clinic | +0.050 |
mistakes | +0.048 |
Neg logit contributions | |
ever | -0.049 |
bye | -0.049 |
seven | -0.047 |
red | -0.047 |
By | -0.042 |
Token | gives |
Token ID | 3607 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ever | +0.099 |
seven | +0.098 |
red | +0.093 |
seventeen | +0.086 |
bye | +0.082 |
Neg logit contributions | |
hospital | -0.109 |
clinic | -0.094 |
basement | -0.093 |
slams | -0.092 |
mistakes | -0.091 |
Token | them |
Token ID | 606 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
hospital | +0.038 |
slams | +0.035 |
clinic | +0.032 |
mun | +0.031 |
promises | +0.030 |
Neg logit contributions | |
ever | -0.036 |
bye | -0.035 |
red | -0.035 |
seven | -0.032 |
ago | -0.032 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ever | +0.085 |
bye | +0.083 |
red | +0.081 |
seven | +0.075 |
By | +0.071 |
Neg logit contributions | |
hospital | -0.124 |
slams | -0.115 |
clinic | -0.107 |
mun | -0.105 |
cleans | -0.100 |
Token | cre |
Token ID | 1126 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
bye | +0.154 |
By | +0.151 |
ever | +0.148 |
ago | +0.147 |
red | +0.146 |
Neg logit contributions | |
hospital | -0.107 |
slams | -0.095 |
chores | -0.087 |
promises | -0.087 |
mun | -0.086 |
Token | ams |
Token ID | 4105 |
Feature activation | +8.10e+00 |
Pos logit contributions | |
bye | +0.107 |
ever | +0.107 |
red | +0.097 |
By | +0.095 |
hy | +0.086 |
Neg logit contributions | |
hospital | -0.214 |
slams | -0.206 |
clinic | -0.187 |
mun | -0.187 |
promises | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
bye | +0.548 |
ever | +0.531 |
red | +0.526 |
By | +0.520 |
ago | +0.498 |
Neg logit contributions | |
hospital | -0.486 |
slams | -0.428 |
chores | -0.402 |
promises | -0.400 |
clinic | -0.398 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ever | +0.025 |
bye | +0.025 |
red | +0.024 |
seven | +0.023 |
ago | +0.022 |
Neg logit contributions | |
hospital | -0.048 |
slams | -0.045 |
clinic | -0.042 |
mun | -0.042 |
chores | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
ever | +0.084 |
seven | +0.081 |
red | +0.079 |
bye | +0.071 |
than | +0.070 |
Neg logit contributions | |
hospital | -0.131 |
slams | -0.115 |
clinic | -0.113 |
mistakes | -0.110 |
basement | -0.110 |
Token | Mia |
Token ID | 32189 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ever | +0.003 |
bye | +0.003 |
red | +0.003 |
seven | +0.003 |
ago | +0.003 |
Neg logit contributions | |
hospital | -0.004 |
slams | -0.003 |
clinic | -0.003 |
mun | -0.003 |
chores | -0.003 |
Token | say |
Token ID | 910 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
hospital | +0.120 |
slams | +0.109 |
clinic | +0.102 |
mistakes | +0.099 |
mun | +0.098 |
Neg logit contributions | |
ever | -0.100 |
bye | -0.094 |
red | -0.092 |
seven | -0.089 |
By | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | +9.47e-03 |
Pos logit contributions | |
ever | +0.113 |
bye | +0.113 |
red | +0.111 |
seven | +0.102 |
ago | +0.100 |
Neg logit contributions | |
hospital | -0.149 |
slams | -0.135 |
clinic | -0.125 |
mun | -0.123 |
promises | -0.120 |
Token | They |
Token ID | 1119 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ever | +0.001 |
bye | +0.001 |
red | +0.000 |
ago | +0.000 |
seven | +0.000 |
Neg logit contributions | |
hospital | -0.001 |
slams | -0.001 |
mun | -0.001 |
clinic | -0.001 |
chores | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
hospital | +0.084 |
slams | +0.078 |
clinic | +0.073 |
mun | +0.071 |
chores | +0.069 |
Neg logit contributions | |
ever | -0.052 |
bye | -0.051 |
red | -0.049 |
seven | -0.045 |
ago | -0.044 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
bye | +0.202 |
red | +0.198 |
ever | +0.194 |
ago | +0.183 |
By | +0.175 |
Neg logit contributions | |
hospital | -0.238 |
slams | -0.209 |
clinic | -0.193 |
chores | -0.192 |
cleans | -0.190 |
Token | qu |
Token ID | 627 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
ever | +0.077 |
red | +0.065 |
bye | +0.065 |
ago | +0.064 |
than | +0.062 |
Neg logit contributions | |
hospital | -0.091 |
slams | -0.087 |
clinic | -0.080 |
mun | -0.077 |
treadmill | -0.075 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.82e+00 |
Pos logit contributions | |
hospital | +0.034 |
slams | +0.028 |
clinic | +0.024 |
chores | +0.021 |
cleans | +0.020 |
Neg logit contributions | |
red | -0.079 |
bye | -0.076 |
ever | -0.074 |
ring | -0.071 |
By | -0.070 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
hospital | +0.524 |
slams | +0.476 |
clinic | +0.434 |
mun | +0.430 |
promises | +0.413 |
Neg logit contributions | |
ever | -0.499 |
bye | -0.492 |
red | -0.481 |
seven | -0.446 |
ago | -0.445 |
Token | . |
Token ID | 13 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
hospital | +0.173 |
slams | +0.160 |
clinic | +0.148 |
mun | +0.145 |
cleans | +0.140 |
Neg logit contributions | |
ever | -0.136 |
bye | -0.131 |
red | -0.129 |
seven | -0.118 |
ago | -0.117 |
Token | To |
Token ID | 1675 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
hospital | +0.007 |
slams | +0.006 |
mun | +0.006 |
clinic | +0.006 |
chores | +0.006 |
Neg logit contributions | |
ever | -0.005 |
bye | -0.005 |
red | -0.005 |
ago | -0.005 |
seven | -0.004 |
Token | celebrate |
Token ID | 10648 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
hospital | +0.170 |
slams | +0.155 |
clinic | +0.143 |
mun | +0.140 |
promises | +0.135 |
Neg logit contributions | |
ever | -0.144 |
bye | -0.142 |
red | -0.139 |
seven | -0.127 |
ago | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ever | +0.018 |
bye | +0.018 |
red | +0.018 |
seven | +0.016 |
ago | +0.016 |
Neg logit contributions | |
hospital | -0.026 |
slams | -0.024 |
clinic | -0.022 |
mun | -0.022 |
promises | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ever | +0.015 |
bye | +0.014 |
red | +0.014 |
By | +0.013 |
ago | +0.013 |
Neg logit contributions | |
hospital | -0.016 |
slams | -0.015 |
mun | -0.013 |
clinic | -0.013 |
promises | -0.013 |
Token | They |
Token ID | 2990 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
ever | +0.012 |
bye | +0.012 |
red | +0.012 |
By | +0.011 |
seven | +0.011 |
Neg logit contributions | |
hospital | -0.019 |
slams | -0.017 |
clinic | -0.016 |
mun | -0.016 |
promises | -0.015 |
Token | learn |
Token ID | 2193 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ever | +0.053 |
bye | +0.051 |
red | +0.049 |
seven | +0.046 |
By | +0.046 |
Neg logit contributions | |
hospital | -0.059 |
slams | -0.054 |
clinic | -0.050 |
mun | -0.050 |
mistakes | -0.048 |
Token | that |
Token ID | 326 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
mun | +0.165 |
hospital | +0.165 |
slams | +0.161 |
clinic | +0.157 |
arre | +0.148 |
Neg logit contributions | |
ever | -0.075 |
bye | -0.070 |
red | -0.060 |
seven | -0.056 |
than | -0.056 |
Token | qu |
Token ID | 627 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
clinic | +0.003 |
mun | +0.003 |
treadmill | +0.002 |
Neg logit contributions | |
ever | -0.002 |
bye | -0.002 |
ago | -0.002 |
red | -0.002 |
than | -0.002 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.73e+00 |
Pos logit contributions | |
hospital | +0.044 |
slams | +0.039 |
clinic | +0.035 |
mun | +0.033 |
chores | +0.031 |
Neg logit contributions | |
red | -0.067 |
ever | -0.066 |
bye | -0.065 |
ago | -0.060 |
seven | -0.060 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
hospital | +0.581 |
slams | +0.533 |
clinic | +0.497 |
mun | +0.477 |
chores | +0.465 |
Neg logit contributions | |
ever | -0.437 |
bye | -0.426 |
red | -0.421 |
seven | -0.379 |
ago | -0.374 |
Token | is |
Token ID | 318 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
hospital | +0.137 |
slams | +0.125 |
clinic | +0.116 |
mun | +0.114 |
chores | +0.105 |
Neg logit contributions | |
ever | -0.153 |
bye | -0.146 |
red | -0.146 |
ago | -0.135 |
seven | -0.135 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
hospital | +0.088 |
slams | +0.083 |
mun | +0.077 |
clinic | +0.076 |
cleans | +0.069 |
Neg logit contributions | |
ever | -0.088 |
bye | -0.082 |
red | -0.079 |
seven | -0.079 |
By | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
hospital | +0.132 |
slams | +0.123 |
clinic | +0.114 |
mun | +0.111 |
chores | +0.106 |
Neg logit contributions | |
ever | -0.108 |
bye | -0.103 |
red | -0.102 |
ago | -0.094 |
seven | -0.090 |
Token | sharing |
Token ID | 7373 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
hospital | +0.005 |
slams | +0.005 |
clinic | +0.004 |
mun | +0.004 |
chores | +0.004 |
Neg logit contributions | |
ever | -0.004 |
bye | -0.004 |
red | -0.004 |
seven | -0.004 |
ago | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
hospital | +0.227 |
slams | +0.198 |
lim | +0.174 |
promises | +0.170 |
mistakes | +0.160 |
Neg logit contributions | |
bye | -0.351 |
red | -0.342 |
ever | -0.327 |
hy | -0.319 |
seventeen | -0.318 |
Token | saw |
Token ID | 2497 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
hospital | +0.023 |
slams | +0.021 |
mun | +0.019 |
promises | +0.018 |
clinic | +0.018 |
Neg logit contributions | |
ever | -0.021 |
bye | -0.020 |
red | -0.020 |
ago | -0.018 |
By | -0.018 |
Token | two |
Token ID | 734 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ever | +0.050 |
bye | +0.047 |
red | +0.046 |
seven | +0.043 |
ago | +0.042 |
Neg logit contributions | |
hospital | -0.075 |
slams | -0.071 |
clinic | -0.068 |
mun | -0.066 |
promises | -0.063 |
Token | birds |
Token ID | 10087 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
hospital | +0.107 |
slams | +0.100 |
clinic | +0.092 |
cleans | +0.088 |
promises | +0.087 |
Neg logit contributions | |
ever | -0.081 |
red | -0.072 |
seven | -0.072 |
bye | -0.072 |
ago | -0.070 |
Token | qu |
Token ID | 627 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
ever | +0.052 |
red | +0.049 |
bye | +0.048 |
ago | +0.046 |
seven | +0.043 |
Neg logit contributions | |
hospital | -0.068 |
slams | -0.062 |
clinic | -0.058 |
promises | -0.055 |
chores | -0.055 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
hospital | +0.064 |
slams | +0.057 |
clinic | +0.053 |
chores | +0.050 |
cleans | +0.050 |
Neg logit contributions | |
red | -0.064 |
ever | -0.063 |
bye | -0.062 |
seven | -0.057 |
ago | -0.056 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
hospital | +0.512 |
slams | +0.464 |
clinic | +0.425 |
mun | +0.413 |
promises | +0.400 |
Neg logit contributions | |
ever | -0.502 |
bye | -0.493 |
red | -0.485 |
seven | -0.447 |
ago | -0.446 |
Token | ! |
Token ID | 0 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
hospital | +0.172 |
slams | +0.159 |
clinic | +0.148 |
mun | +0.144 |
cleans | +0.141 |
Neg logit contributions | |
ever | -0.121 |
red | -0.116 |
bye | -0.115 |
seven | -0.103 |
ago | -0.103 |
Token | They |
Token ID | 1119 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ever | +0.087 |
bye | +0.085 |
red | +0.085 |
seven | +0.079 |
ago | +0.079 |
Neg logit contributions | |
hospital | -0.160 |
slams | -0.150 |
clinic | -0.139 |
chores | -0.138 |
mun | -0.136 |
Token | were |
Token ID | 547 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
hospital | +0.093 |
slams | +0.085 |
mun | +0.080 |
clinic | +0.078 |
cleans | +0.076 |
Neg logit contributions | |
bye | -0.061 |
ever | -0.060 |
red | -0.059 |
ago | -0.054 |
seven | -0.053 |
Token | squ |
Token ID | 2809 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ever | +0.044 |
bye | +0.044 |
red | +0.043 |
seven | +0.039 |
ago | +0.039 |
Neg logit contributions | |
hospital | -0.056 |
slams | -0.051 |
clinic | -0.047 |
mun | -0.046 |
promises | -0.045 |
Token | walking |
Token ID | 6155 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
hospital | +0.053 |
slams | +0.049 |
clinic | +0.046 |
mun | +0.046 |
promises | +0.045 |
Neg logit contributions | |
ever | -0.047 |
red | -0.042 |
seven | -0.040 |
ago | -0.040 |
bye | -0.040 |
Token | by |
Token ID | 416 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
hospital | +0.114 |
slams | +0.105 |
clinic | +0.097 |
mun | +0.095 |
cleans | +0.092 |
Neg logit contributions | |
ever | -0.089 |
bye | -0.087 |
red | -0.085 |
seven | -0.078 |
ago | -0.077 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
hospital | +0.037 |
slams | +0.034 |
clinic | +0.032 |
mun | +0.031 |
chores | +0.030 |
Neg logit contributions | |
ever | -0.028 |
red | -0.027 |
bye | -0.026 |
ago | -0.024 |
seven | -0.024 |
Token | them |
Token ID | 606 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ever | +0.060 |
red | +0.058 |
bye | +0.056 |
ago | +0.054 |
seven | +0.054 |
Neg logit contributions | |
hospital | -0.077 |
slams | -0.071 |
clinic | -0.068 |
mun | -0.065 |
promises | -0.063 |
Token | qu |
Token ID | 627 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
ever | +0.075 |
red | +0.061 |
ago | +0.057 |
bye | +0.055 |
hy | +0.054 |
Neg logit contributions | |
hospital | -0.130 |
slams | -0.124 |
clinic | -0.120 |
mun | -0.120 |
cleans | -0.116 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
hospital | +0.041 |
slams | +0.035 |
clinic | +0.032 |
chores | +0.028 |
cleans | +0.028 |
Neg logit contributions | |
red | -0.083 |
ever | -0.078 |
bye | -0.078 |
seven | -0.074 |
ring | -0.072 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
hospital | +0.514 |
slams | +0.466 |
clinic | +0.437 |
mun | +0.402 |
cleans | +0.401 |
Neg logit contributions | |
ever | -0.506 |
red | -0.495 |
bye | -0.486 |
seven | -0.445 |
ago | -0.438 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
hospital | +0.178 |
slams | +0.168 |
clinic | +0.159 |
mun | +0.158 |
cleans | +0.153 |
Neg logit contributions | |
ever | -0.109 |
red | -0.105 |
bye | -0.097 |
seven | -0.091 |
than | -0.086 |
Token | She |
Token ID | 1375 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
ever | +0.007 |
bye | +0.007 |
red | +0.007 |
ago | +0.007 |
seven | +0.007 |
Neg logit contributions | |
hospital | -0.010 |
slams | -0.009 |
clinic | -0.009 |
mun | -0.009 |
chores | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
hospital | +0.063 |
slams | +0.058 |
clinic | +0.054 |
mun | +0.053 |
chores | +0.052 |
Neg logit contributions | |
ever | -0.046 |
bye | -0.044 |
red | -0.044 |
seven | -0.040 |
By | -0.039 |
Token | very |
Token ID | 845 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
hospital | +0.056 |
slams | +0.051 |
clinic | +0.048 |
mun | +0.047 |
promises | +0.046 |
Neg logit contributions | |
ever | -0.048 |
red | -0.046 |
bye | -0.045 |
seven | -0.043 |
ago | -0.042 |
Token | said |
Token ID | 531 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
hospital | +0.064 |
slams | +0.059 |
clinic | +0.054 |
mun | +0.053 |
promises | +0.051 |
Neg logit contributions | |
ever | -0.053 |
bye | -0.052 |
red | -0.051 |
seven | -0.047 |
ago | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.020 |
clinic | +0.019 |
mun | +0.018 |
promises | +0.018 |
Neg logit contributions | |
ever | -0.011 |
red | -0.010 |
bye | -0.010 |
ago | -0.009 |
seven | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
hospital | +0.019 |
slams | +0.017 |
clinic | +0.016 |
mun | +0.016 |
cleans | +0.016 |
Neg logit contributions | |
bye | -0.015 |
ever | -0.015 |
red | -0.014 |
seven | -0.013 |
ago | -0.013 |
Token | Stop |
Token ID | 19485 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
hospital | +0.031 |
slams | +0.028 |
clinic | +0.026 |
mun | +0.026 |
promises | +0.025 |
Neg logit contributions | |
ever | -0.025 |
bye | -0.024 |
red | -0.024 |
ago | -0.022 |
seven | -0.022 |
Token | qu |
Token ID | 627 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
hospital | +0.163 |
slams | +0.147 |
clinic | +0.134 |
mun | +0.130 |
chores | +0.125 |
Neg logit contributions | |
ever | -0.182 |
bye | -0.178 |
red | -0.175 |
ago | -0.162 |
seven | -0.162 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
hospital | +0.033 |
slams | +0.027 |
clinic | +0.025 |
mun | +0.021 |
cleans | +0.021 |
Neg logit contributions | |
red | -0.078 |
bye | -0.076 |
ever | -0.075 |
seven | -0.072 |
ring | -0.071 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
hospital | +0.523 |
slams | +0.475 |
clinic | +0.437 |
mun | +0.424 |
promises | +0.410 |
Neg logit contributions | |
ever | -0.493 |
bye | -0.483 |
red | -0.476 |
seven | -0.438 |
ago | -0.435 |
Token | , |
Token ID | 11 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
hospital | +0.167 |
slams | +0.155 |
clinic | +0.144 |
mun | +0.142 |
promises | +0.136 |
Neg logit contributions | |
ever | -0.114 |
bye | -0.111 |
red | -0.109 |
seven | -0.099 |
ago | -0.098 |
Token | boys |
Token ID | 6510 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
hospital | +0.019 |
slams | +0.017 |
clinic | +0.015 |
mun | +0.015 |
promises | +0.015 |
Neg logit contributions | |
ever | -0.015 |
bye | -0.015 |
red | -0.015 |
ago | -0.014 |
seven | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.006 |
clinic | +0.006 |
mun | +0.005 |
chores | +0.005 |
Neg logit contributions | |
ever | -0.004 |
bye | -0.003 |
red | -0.003 |
ago | -0.003 |
seven | -0.003 |
Token | You |
Token ID | 921 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
bye | +0.004 |
ever | +0.004 |
red | +0.004 |
ago | +0.004 |
seven | +0.004 |
Neg logit contributions | |
hospital | -0.007 |
slams | -0.006 |
clinic | -0.006 |
mun | -0.006 |
chores | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
bye | +0.030 |
red | +0.030 |
ever | +0.028 |
ago | +0.028 |
seven | +0.027 |
Neg logit contributions | |
hospital | -0.027 |
slams | -0.025 |
chores | -0.022 |
cleans | -0.022 |
mun | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
hospital | +0.163 |
slams | +0.150 |
clinic | +0.141 |
mun | +0.138 |
promises | +0.133 |
Neg logit contributions | |
ever | -0.103 |
bye | -0.100 |
red | -0.097 |
ago | -0.088 |
seven | -0.088 |
Token | they |
Token ID | 484 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
hospital | +0.037 |
slams | +0.034 |
clinic | +0.032 |
mun | +0.031 |
cleans | +0.030 |
Neg logit contributions | |
ever | -0.026 |
bye | -0.025 |
red | -0.025 |
seven | -0.022 |
ago | -0.022 |
Token | never |
Token ID | 1239 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
hospital | +0.029 |
slams | +0.026 |
clinic | +0.024 |
mun | +0.024 |
cleans | +0.023 |
Neg logit contributions | |
ever | -0.020 |
bye | -0.020 |
red | -0.020 |
ago | -0.018 |
seven | -0.018 |
Token | qu |
Token ID | 627 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
ever | +0.161 |
bye | +0.157 |
red | +0.154 |
seven | +0.139 |
ago | +0.139 |
Neg logit contributions | |
hospital | -0.229 |
slams | -0.211 |
clinic | -0.196 |
mun | -0.192 |
chores | -0.186 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
hospital | +0.038 |
slams | +0.031 |
clinic | +0.028 |
chores | +0.025 |
tells | +0.025 |
Neg logit contributions | |
red | -0.085 |
ever | -0.078 |
bye | -0.077 |
ring | -0.075 |
By | -0.073 |
Token | led |
Token ID | 992 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
hospital | +0.720 |
slams | +0.670 |
clinic | +0.637 |
mun | +0.614 |
chores | +0.605 |
Neg logit contributions | |
ever | -0.300 |
bye | -0.287 |
red | -0.286 |
seven | -0.239 |
ago | -0.235 |
Token | again |
Token ID | 757 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ever | +0.238 |
bye | +0.223 |
red | +0.216 |
seven | +0.202 |
By | +0.198 |
Neg logit contributions | |
hospital | -0.243 |
slams | -0.226 |
clinic | -0.209 |
mun | -0.204 |
cleans | -0.198 |
Token | and |
Token ID | 290 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
hospital | +0.257 |
slams | +0.238 |
clinic | +0.219 |
mun | +0.215 |
cleans | +0.208 |
Neg logit contributions | |
ever | -0.198 |
bye | -0.190 |
red | -0.187 |
ago | -0.171 |
seven | -0.169 |
Token | played |
Token ID | 2826 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
hospital | +0.033 |
slams | +0.032 |
clinic | +0.030 |
mun | +0.029 |
chores | +0.028 |
Neg logit contributions | |
ever | -0.022 |
bye | -0.021 |
red | -0.020 |
By | -0.017 |
ago | -0.017 |
Token | together |
Token ID | 1978 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
slams | +0.040 |
hospital | +0.038 |
mun | +0.037 |
cleans | +0.036 |
clinic | +0.034 |
Neg logit contributions | |
ever | -0.028 |
bye | -0.024 |
than | -0.024 |
By | -0.023 |
red | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
bye | +0.026 |
red | +0.026 |
ever | +0.025 |
ago | +0.024 |
seven | +0.023 |
Neg logit contributions | |
hospital | -0.026 |
slams | -0.023 |
chores | -0.021 |
clinic | -0.021 |
mun | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
hospital | +0.166 |
slams | +0.156 |
clinic | +0.147 |
mun | +0.144 |
promises | +0.139 |
Neg logit contributions | |
ever | -0.096 |
bye | -0.087 |
red | -0.085 |
ago | -0.079 |
seven | -0.078 |
Token | they |
Token ID | 484 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
hospital | +0.037 |
slams | +0.037 |
clinic | +0.033 |
cleans | +0.032 |
mistakes | +0.031 |
Neg logit contributions | |
ever | -0.023 |
bye | -0.019 |
red | -0.018 |
By | -0.017 |
ago | -0.017 |
Token | never |
Token ID | 1239 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
hospital | +0.020 |
slams | +0.018 |
clinic | +0.017 |
mun | +0.017 |
cleans | +0.016 |
Neg logit contributions | |
bye | -0.015 |
ever | -0.015 |
red | -0.014 |
ago | -0.013 |
seven | -0.013 |
Token | qu |
Token ID | 627 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
bye | +0.157 |
ever | +0.156 |
red | +0.152 |
seven | +0.145 |
ago | +0.140 |
Neg logit contributions | |
hospital | -0.229 |
slams | -0.211 |
mun | -0.192 |
clinic | -0.192 |
cleans | -0.187 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
hospital | +0.033 |
slams | +0.027 |
clinic | +0.023 |
tells | +0.020 |
chores | +0.020 |
Neg logit contributions | |
red | -0.084 |
ever | -0.080 |
bye | -0.079 |
By | -0.075 |
ring | -0.075 |
Token | led |
Token ID | 992 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
hospital | +0.690 |
slams | +0.642 |
clinic | +0.603 |
mun | +0.592 |
promises | +0.578 |
Neg logit contributions | |
ever | -0.323 |
bye | -0.314 |
red | -0.306 |
seven | -0.268 |
ago | -0.266 |
Token | again |
Token ID | 757 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
ever | +0.241 |
bye | +0.237 |
red | +0.233 |
seven | +0.216 |
ago | +0.215 |
Neg logit contributions | |
hospital | -0.226 |
slams | -0.204 |
clinic | -0.186 |
mun | -0.181 |
promises | -0.175 |
Token | over |
Token ID | 625 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
hospital | +0.240 |
slams | +0.217 |
clinic | +0.202 |
mun | +0.197 |
promises | +0.192 |
Neg logit contributions | |
bye | -0.197 |
ever | -0.196 |
red | -0.192 |
seven | -0.177 |
ago | -0.174 |
Token | clothes |
Token ID | 8242 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
hospital | +0.188 |
slams | +0.174 |
clinic | +0.161 |
mun | +0.157 |
cleans | +0.152 |
Neg logit contributions | |
ever | -0.141 |
bye | -0.136 |
red | -0.133 |
ago | -0.122 |
seven | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
bye | +0.207 |
red | +0.203 |
ever | +0.203 |
seven | +0.194 |
By | +0.190 |
Neg logit contributions | |
hospital | -0.182 |
slams | -0.157 |
clinic | -0.146 |
mun | -0.138 |
promises | -0.136 |
Token | but |
Token ID | 475 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
hospital | +0.033 |
slams | +0.029 |
clinic | +0.027 |
mun | +0.027 |
promises | +0.026 |
Neg logit contributions | |
bye | -0.027 |
red | -0.027 |
ever | -0.027 |
By | -0.024 |
seven | -0.024 |
Token | today |
Token ID | 1909 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
hospital | +0.056 |
slams | +0.052 |
clinic | +0.047 |
mun | +0.046 |
promises | +0.046 |
Neg logit contributions | |
ever | -0.041 |
bye | -0.040 |
red | -0.040 |
By | -0.036 |
seven | -0.036 |
Token | they |
Token ID | 484 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
ever | +0.032 |
bye | +0.031 |
red | +0.030 |
ago | +0.027 |
seven | +0.027 |
Neg logit contributions | |
hospital | -0.045 |
slams | -0.041 |
clinic | -0.038 |
mun | -0.038 |
cleans | -0.037 |
Token | were |
Token ID | 547 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
hospital | +0.018 |
slams | +0.016 |
mun | +0.015 |
clinic | +0.015 |
cleans | +0.015 |
Neg logit contributions | |
bye | -0.012 |
red | -0.012 |
ever | -0.011 |
ago | -0.011 |
seven | -0.011 |
Token | qu |
Token ID | 627 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
ever | +0.046 |
bye | +0.042 |
red | +0.042 |
seven | +0.040 |
ago | +0.039 |
Neg logit contributions | |
hospital | -0.053 |
slams | -0.049 |
clinic | -0.045 |
mun | -0.044 |
cleans | -0.043 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
hospital | +0.037 |
slams | +0.031 |
clinic | +0.027 |
cleans | +0.025 |
promises | +0.024 |
Neg logit contributions | |
red | -0.087 |
ever | -0.086 |
bye | -0.085 |
By | -0.080 |
seven | -0.080 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
hospital | +0.523 |
slams | +0.476 |
mun | +0.442 |
clinic | +0.430 |
mistakes | +0.418 |
Neg logit contributions | |
bye | -0.474 |
ever | -0.472 |
red | -0.456 |
ago | -0.428 |
seven | -0.428 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
hospital | +0.164 |
slams | +0.150 |
clinic | +0.139 |
mun | +0.136 |
promises | +0.132 |
Neg logit contributions | |
ever | -0.128 |
bye | -0.125 |
red | -0.123 |
seven | -0.112 |
ago | -0.112 |
Token | Jenna |
Token ID | 45377 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
hospital | +0.012 |
slams | +0.011 |
clinic | +0.010 |
mun | +0.010 |
promises | +0.009 |
Neg logit contributions | |
ever | -0.010 |
bye | -0.009 |
red | -0.009 |
seven | -0.009 |
ago | -0.008 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ever | +0.134 |
bye | +0.131 |
red | +0.129 |
seven | +0.117 |
ago | +0.117 |
Neg logit contributions | |
hospital | -0.178 |
slams | -0.163 |
clinic | -0.151 |
mun | -0.148 |
chores | -0.144 |
Token | to |
Token ID | 284 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
ever | +0.054 |
bye | +0.048 |
red | +0.046 |
seven | +0.042 |
ago | +0.040 |
Neg logit contributions | |
hospital | -0.104 |
slams | -0.101 |
clinic | -0.094 |
mun | -0.092 |
cleans | -0.089 |
Token | " |
Token ID | 366 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
clinic | +0.003 |
mun | +0.003 |
promises | +0.003 |
Neg logit contributions | |
ever | -0.002 |
bye | -0.002 |
red | -0.002 |
ago | -0.002 |
seven | -0.002 |
Token | Why |
Token ID | 5195 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
hospital | +0.029 |
mun | +0.026 |
slams | +0.025 |
clinic | +0.024 |
mistakes | +0.023 |
Neg logit contributions | |
ever | -0.025 |
ago | -0.024 |
red | -0.024 |
bye | -0.023 |
seven | -0.023 |
Token | are |
Token ID | 389 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
hospital | +0.253 |
slams | +0.231 |
clinic | +0.213 |
mun | +0.209 |
promises | +0.202 |
Neg logit contributions | |
ever | -0.211 |
bye | -0.207 |
red | -0.203 |
seven | -0.186 |
ago | -0.185 |
Token | you |
Token ID | 345 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
red | +0.004 |
bye | +0.003 |
ever | +0.003 |
ago | +0.003 |
By | +0.003 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.004 |
chores | -0.004 |
mun | -0.004 |
clinic | -0.004 |
Token | qu |
Token ID | 627 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
ever | +0.059 |
red | +0.054 |
bye | +0.054 |
ago | +0.053 |
seven | +0.052 |
Neg logit contributions | |
hospital | -0.062 |
slams | -0.056 |
clinic | -0.054 |
mun | -0.053 |
cleans | -0.050 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
hospital | +0.033 |
slams | +0.026 |
clinic | +0.024 |
cleans | +0.020 |
mun | +0.020 |
Neg logit contributions | |
red | -0.083 |
bye | -0.081 |
ever | -0.080 |
seven | -0.076 |
ring | -0.075 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
hospital | +0.475 |
slams | +0.429 |
mun | +0.390 |
clinic | +0.383 |
promises | +0.372 |
Neg logit contributions | |
ever | -0.526 |
bye | -0.523 |
red | -0.507 |
ago | -0.479 |
seven | -0.478 |
Token | ? |
Token ID | 30 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
hospital | +0.137 |
slams | +0.120 |
clinic | +0.110 |
chores | +0.104 |
mun | +0.104 |
Neg logit contributions | |
ever | -0.149 |
bye | -0.147 |
red | -0.145 |
By | -0.137 |
ago | -0.135 |
Token | You |
Token ID | 921 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
hospital | +0.047 |
slams | +0.042 |
mun | +0.040 |
clinic | +0.040 |
chores | +0.040 |
Neg logit contributions | |
ever | -0.026 |
red | -0.025 |
bye | -0.025 |
ago | -0.023 |
seven | -0.023 |
Token | can |
Token ID | 460 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
hospital | +0.088 |
slams | +0.080 |
clinic | +0.077 |
mun | +0.075 |
mistakes | +0.072 |
Neg logit contributions | |
ever | -0.070 |
bye | -0.064 |
red | -0.063 |
seven | -0.059 |
ago | -0.058 |
Token | share |
Token ID | 2648 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
hospital | +0.077 |
slams | +0.071 |
clinic | +0.066 |
mun | +0.065 |
promises | +0.063 |
Neg logit contributions | |
ever | -0.064 |
bye | -0.060 |
red | -0.057 |
seven | -0.054 |
By | -0.053 |
Token | he |
Token ID | 339 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hospital | +0.031 |
slams | +0.028 |
mun | +0.026 |
clinic | +0.026 |
chores | +0.026 |
Neg logit contributions | |
red | -0.018 |
bye | -0.017 |
ever | -0.017 |
ago | -0.016 |
hy | -0.015 |
Token | found |
Token ID | 1043 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ever | +0.048 |
bye | +0.047 |
red | +0.046 |
seven | +0.041 |
ago | +0.041 |
Neg logit contributions | |
hospital | -0.086 |
slams | -0.080 |
clinic | -0.074 |
mun | -0.073 |
chores | -0.072 |
Token | a |
Token ID | 257 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
bye | +0.130 |
ever | +0.129 |
red | +0.128 |
ago | +0.120 |
By | +0.116 |
Neg logit contributions | |
hospital | -0.140 |
slams | -0.122 |
clinic | -0.112 |
mun | -0.109 |
promises | -0.109 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
hospital | +0.022 |
slams | +0.021 |
mun | +0.019 |
clinic | +0.019 |
promises | +0.019 |
Neg logit contributions | |
ever | -0.015 |
bye | -0.014 |
seven | -0.013 |
red | -0.013 |
ago | -0.013 |
Token | qu |
Token ID | 627 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
hospital | +0.095 |
slams | +0.092 |
mun | +0.085 |
chores | +0.085 |
cleans | +0.084 |
Neg logit contributions | |
ever | -0.073 |
red | -0.063 |
ago | -0.063 |
bye | -0.062 |
hy | -0.058 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
hospital | +0.061 |
slams | +0.055 |
clinic | +0.051 |
cleans | +0.049 |
chores | +0.049 |
Neg logit contributions | |
red | -0.054 |
bye | -0.053 |
ever | -0.053 |
seven | -0.047 |
By | -0.047 |
Token | lling |
Token ID | 2680 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
hospital | +0.450 |
slams | +0.402 |
mun | +0.364 |
clinic | +0.357 |
promises | +0.343 |
Neg logit contributions | |
bye | -0.550 |
ever | -0.548 |
red | -0.531 |
ago | -0.503 |
seven | -0.503 |
Token | with |
Token ID | 351 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
hospital | +0.082 |
slams | +0.075 |
clinic | +0.068 |
mun | +0.066 |
chores | +0.066 |
Neg logit contributions | |
bye | -0.068 |
ever | -0.065 |
red | -0.063 |
By | -0.060 |
seven | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
bye | +0.028 |
ever | +0.027 |
red | +0.027 |
ago | +0.025 |
seven | +0.025 |
Neg logit contributions | |
hospital | -0.030 |
slams | -0.027 |
mun | -0.025 |
clinic | -0.025 |
chores | -0.025 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.020 |
clinic | +0.018 |
mun | +0.018 |
promises | +0.017 |
Neg logit contributions | |
ever | -0.015 |
bye | -0.015 |
red | -0.014 |
seven | -0.014 |
By | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
ever | +0.002 |
red | +0.002 |
bye | +0.002 |
ago | +0.002 |
hy | +0.002 |
Neg logit contributions | |
hospital | -0.004 |
slams | -0.003 |
clinic | -0.003 |
cleans | -0.003 |
mun | -0.003 |
Token | says |
Token ID | 1139 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
hospital | +0.050 |
clinic | +0.045 |
chores | +0.045 |
arre | +0.043 |
basement | +0.042 |
Neg logit contributions | |
ever | -0.040 |
seven | -0.039 |
bye | -0.034 |
ago | -0.033 |
hy | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ever | +0.003 |
bye | +0.003 |
red | +0.002 |
ago | +0.002 |
seven | +0.002 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.005 |
clinic | -0.005 |
mun | -0.005 |
promises | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
hospital | +0.009 |
slams | +0.009 |
clinic | +0.008 |
mun | +0.008 |
promises | +0.008 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.006 |
red | -0.006 |
seven | -0.005 |
ago | -0.005 |
Token | Stop |
Token ID | 19485 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.019 |
mun | +0.018 |
clinic | +0.017 |
promises | +0.017 |
Neg logit contributions | |
ever | -0.019 |
red | -0.018 |
bye | -0.018 |
ago | -0.017 |
seven | -0.016 |
Token | qu |
Token ID | 627 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
hospital | +0.180 |
slams | +0.163 |
clinic | +0.148 |
mun | +0.147 |
promises | +0.142 |
Neg logit contributions | |
bye | -0.163 |
ever | -0.162 |
red | -0.160 |
seven | -0.148 |
By | -0.145 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
hospital | +0.047 |
slams | +0.042 |
clinic | +0.039 |
cleans | +0.036 |
mun | +0.036 |
Neg logit contributions | |
red | -0.060 |
bye | -0.060 |
ever | -0.057 |
ring | -0.055 |
ay | -0.054 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
hospital | +0.503 |
slams | +0.455 |
clinic | +0.417 |
mun | +0.404 |
promises | +0.390 |
Neg logit contributions | |
ever | -0.509 |
bye | -0.500 |
red | -0.492 |
seven | -0.454 |
ago | -0.451 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
hospital | +0.165 |
slams | +0.154 |
clinic | +0.143 |
mun | +0.142 |
cleans | +0.136 |
Neg logit contributions | |
ever | -0.116 |
bye | -0.112 |
red | -0.109 |
seven | -0.100 |
ago | -0.098 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
hospital | +0.011 |
slams | +0.010 |
promises | +0.009 |
mun | +0.009 |
clinic | +0.008 |
Neg logit contributions | |
red | -0.010 |
bye | -0.010 |
ever | -0.010 |
ago | -0.009 |
seven | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ever | +0.109 |
bye | +0.108 |
red | +0.107 |
seven | +0.099 |
By | +0.098 |
Neg logit contributions | |
hospital | -0.121 |
slams | -0.109 |
clinic | -0.100 |
mun | -0.098 |
promises | -0.097 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ever | +0.001 |
bye | +0.001 |
red | +0.001 |
ago | +0.001 |
seven | +0.001 |
Neg logit contributions | |
hospital | -0.001 |
slams | -0.001 |
clinic | -0.001 |
mun | -0.001 |
promises | -0.001 |
Token | Sharing |
Token ID | 36644 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
bye | +0.010 |
ever | +0.010 |
red | +0.009 |
ago | +0.009 |
seven | +0.009 |
Neg logit contributions | |
hospital | -0.012 |
slams | -0.011 |
mun | -0.011 |
clinic | -0.010 |
chores | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
hospital | +0.202 |
slams | +0.189 |
clinic | +0.180 |
mun | +0.166 |
chores | +0.160 |
Neg logit contributions | |
ever | -0.172 |
red | -0.162 |
bye | -0.157 |
than | -0.143 |
ago | -0.142 |
Token | better |
Token ID | 1365 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
hospital | +0.061 |
slams | +0.058 |
clinic | +0.053 |
mun | +0.051 |
cleans | +0.047 |
Neg logit contributions | |
ever | -0.063 |
bye | -0.058 |
red | -0.058 |
seven | -0.056 |
By | -0.054 |
Token | than |
Token ID | 621 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
hospital | +0.312 |
slams | +0.293 |
clinic | +0.277 |
promises | +0.277 |
mistakes | +0.273 |
Neg logit contributions | |
bye | -0.072 |
red | -0.070 |
ever | -0.066 |
seven | -0.058 |
By | -0.055 |
Token | qu |
Token ID | 627 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
ever | +0.413 |
bye | +0.401 |
red | +0.396 |
ago | +0.365 |
seven | +0.363 |
Neg logit contributions | |
hospital | -0.448 |
slams | -0.408 |
clinic | -0.376 |
mun | -0.367 |
promises | -0.354 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
hospital | +0.031 |
slams | +0.025 |
clinic | +0.020 |
mun | +0.016 |
cleans | +0.015 |
Neg logit contributions | |
red | -0.096 |
ever | -0.095 |
bye | -0.094 |
ago | -0.089 |
seven | -0.088 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
hospital | +0.476 |
slams | +0.429 |
mun | +0.391 |
clinic | +0.384 |
promises | +0.374 |
Neg logit contributions | |
ever | -0.522 |
bye | -0.520 |
red | -0.502 |
seven | -0.476 |
By | -0.473 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
hospital | +0.161 |
slams | +0.148 |
clinic | +0.136 |
mun | +0.134 |
promises | +0.130 |
Neg logit contributions | |
ever | -0.127 |
bye | -0.125 |
red | -0.122 |
seven | -0.112 |
ago | -0.111 |
Token | They |
Token ID | 1119 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ever | +0.009 |
bye | +0.009 |
red | +0.008 |
ago | +0.008 |
seven | +0.008 |
Neg logit contributions | |
hospital | -0.012 |
slams | -0.011 |
clinic | -0.010 |
mun | -0.010 |
chores | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
hospital | +0.094 |
slams | +0.087 |
clinic | +0.080 |
mun | +0.079 |
promises | +0.077 |
Neg logit contributions | |
ever | -0.061 |
bye | -0.060 |
red | -0.059 |
ago | -0.053 |
seven | -0.053 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
hospital | +0.012 |
slams | +0.011 |
clinic | +0.011 |
mun | +0.010 |
promises | +0.010 |
Neg logit contributions | |
ever | -0.008 |
bye | -0.008 |
red | -0.008 |
seven | -0.007 |
ago | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ever | +0.064 |
bye | +0.062 |
red | +0.062 |
ago | +0.056 |
seven | +0.056 |
Neg logit contributions | |
hospital | -0.085 |
slams | -0.078 |
clinic | -0.072 |
mun | -0.071 |
chores | -0.068 |
Token | they |
Token ID | 484 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
hospital | +0.025 |
slams | +0.023 |
mun | +0.020 |
clinic | +0.020 |
cleans | +0.020 |
Neg logit contributions | |
bye | -0.021 |
red | -0.020 |
ever | -0.020 |
ago | -0.018 |
seven | -0.018 |
Token | both |
Token ID | 1111 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
hospital | +0.022 |
slams | +0.020 |
clinic | +0.018 |
mun | +0.018 |
cleans | +0.018 |
Neg logit contributions | |
bye | -0.014 |
ever | -0.014 |
red | -0.014 |
ago | -0.013 |
seven | -0.012 |
Token | stopped |
Token ID | 5025 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
bye | +0.104 |
red | +0.098 |
ago | +0.094 |
ever | +0.094 |
By | +0.093 |
Neg logit contributions | |
hospital | -0.134 |
slams | -0.125 |
mun | -0.111 |
cleans | -0.109 |
tells | -0.106 |
Token | qu |
Token ID | 627 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
ever | +0.057 |
red | +0.049 |
than | +0.048 |
ago | +0.048 |
bye | +0.047 |
Neg logit contributions | |
hospital | -0.062 |
slams | -0.058 |
clinic | -0.055 |
mun | -0.051 |
cleans | -0.050 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
hospital | +0.037 |
slams | +0.032 |
clinic | +0.029 |
mun | +0.027 |
chores | +0.026 |
Neg logit contributions | |
red | -0.074 |
bye | -0.072 |
ever | -0.071 |
By | -0.067 |
ring | -0.066 |
Token | lling |
Token ID | 2680 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
hospital | +0.501 |
slams | +0.453 |
clinic | +0.411 |
mun | +0.408 |
promises | +0.390 |
Neg logit contributions | |
ever | -0.504 |
bye | -0.499 |
red | -0.486 |
seven | -0.454 |
ago | -0.453 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
hospital | +0.080 |
slams | +0.073 |
clinic | +0.067 |
mun | +0.065 |
promises | +0.064 |
Neg logit contributions | |
bye | -0.069 |
ever | -0.069 |
red | -0.067 |
seven | -0.062 |
By | -0.062 |
Token | look |
Token ID | 804 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
hospital | +0.011 |
slams | +0.010 |
clinic | +0.010 |
mun | +0.010 |
cleans | +0.009 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.005 |
red | -0.005 |
seven | -0.005 |
By | -0.005 |
Token | at |
Token ID | 379 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
hospital | +0.085 |
slams | +0.080 |
clinic | +0.077 |
mun | +0.077 |
cleans | +0.071 |
Neg logit contributions | |
ever | -0.048 |
bye | -0.044 |
red | -0.043 |
seven | -0.043 |
than | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ever | +0.051 |
bye | +0.046 |
red | +0.046 |
seven | +0.039 |
than | +0.039 |
Neg logit contributions | |
hospital | -0.099 |
slams | -0.093 |
clinic | -0.091 |
mun | -0.089 |
chores | -0.084 |
Token | wished |
Token ID | 16555 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
hospital | +0.027 |
slams | +0.024 |
clinic | +0.022 |
mun | +0.021 |
promises | +0.021 |
Neg logit contributions | |
ever | -0.028 |
bye | -0.028 |
red | -0.027 |
seven | -0.025 |
ago | -0.025 |
Token | they |
Token ID | 484 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ever | +0.042 |
bye | +0.042 |
red | +0.040 |
seven | +0.036 |
ago | +0.036 |
Neg logit contributions | |
hospital | -0.072 |
slams | -0.066 |
clinic | -0.062 |
mun | -0.061 |
chores | -0.059 |
Token | had |
Token ID | 550 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
hospital | +0.020 |
slams | +0.018 |
lim | +0.017 |
cleans | +0.016 |
chores | +0.016 |
Neg logit contributions | |
bye | -0.012 |
seventeen | -0.012 |
red | -0.012 |
ago | -0.011 |
seven | -0.011 |
Token | never |
Token ID | 1239 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
bye | +0.164 |
red | +0.161 |
ago | +0.158 |
ever | +0.154 |
seven | +0.153 |
Neg logit contributions | |
hospital | -0.235 |
slams | -0.209 |
promises | -0.194 |
cleans | -0.193 |
chores | -0.193 |
Token | qu |
Token ID | 627 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
bye | +0.155 |
seven | +0.151 |
red | +0.150 |
ever | +0.146 |
ago | +0.145 |
Neg logit contributions | |
hospital | -0.222 |
slams | -0.199 |
cleans | -0.184 |
mun | -0.181 |
promises | -0.179 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
hospital | +0.034 |
slams | +0.027 |
clinic | +0.024 |
mun | +0.021 |
tells | +0.020 |
Neg logit contributions | |
red | -0.089 |
ever | -0.086 |
bye | -0.084 |
ring | -0.080 |
By | -0.080 |
Token | led |
Token ID | 992 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
hospital | +0.647 |
slams | +0.598 |
mun | +0.566 |
mistakes | +0.546 |
promises | +0.543 |
Neg logit contributions | |
bye | -0.350 |
ever | -0.339 |
red | -0.318 |
seven | -0.313 |
ago | -0.311 |
Token | . |
Token ID | 13 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
bye | +0.217 |
red | +0.211 |
ever | +0.211 |
seven | +0.196 |
By | +0.195 |
Neg logit contributions | |
hospital | -0.249 |
slams | -0.224 |
clinic | -0.204 |
promises | -0.201 |
mun | -0.198 |
Token | They |
Token ID | 1119 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
mun | +0.003 |
clinic | +0.003 |
chores | +0.003 |
Neg logit contributions | |
ever | -0.002 |
bye | -0.002 |
red | -0.002 |
ago | -0.002 |
seven | -0.002 |
Token | missed |
Token ID | 6825 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
hospital | +0.108 |
slams | +0.101 |
clinic | +0.098 |
mun | +0.096 |
chores | +0.092 |
Neg logit contributions | |
ever | -0.068 |
bye | -0.062 |
red | -0.061 |
By | -0.056 |
seven | -0.054 |
Token | their |
Token ID | 511 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
hospital | +0.001 |
slams | +0.001 |
clinic | +0.001 |
mun | +0.001 |
uddle | +0.001 |
Neg logit contributions | |
ever | -0.001 |
than | -0.001 |
red | -0.001 |
bye | -0.001 |
ago | -0.001 |
Token | lively |
Token ID | 29696 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
hospital | +0.031 |
slams | +0.028 |
clinic | +0.026 |
mun | +0.026 |
promises | +0.025 |
Neg logit contributions | |
ever | -0.023 |
bye | -0.022 |
red | -0.022 |
seven | -0.020 |
ago | -0.020 |
Token | sound |
Token ID | 2128 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
ever | +0.063 |
bye | +0.063 |
red | +0.059 |
seven | +0.057 |
ago | +0.056 |
Neg logit contributions | |
hospital | -0.057 |
slams | -0.055 |
clinic | -0.048 |
mun | -0.048 |
cleans | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
bye | +0.005 |
red | +0.004 |
ever | +0.004 |
ago | +0.004 |
seven | +0.004 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.004 |
clinic | -0.004 |
mistakes | -0.003 |
mun | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
hospital | +0.013 |
slams | +0.012 |
mun | +0.011 |
clinic | +0.011 |
chores | +0.011 |
Neg logit contributions | |
ever | -0.009 |
red | -0.009 |
bye | -0.009 |
ago | -0.008 |
seven | -0.008 |
Token | qu |
Token ID | 627 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
ever | +0.008 |
bye | +0.008 |
red | +0.008 |
seven | +0.008 |
wind | +0.008 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.005 |
clinic | -0.004 |
mun | -0.004 |
cleans | -0.004 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
hospital | +0.052 |
slams | +0.046 |
clinic | +0.042 |
mun | +0.040 |
chores | +0.039 |
Neg logit contributions | |
ever | -0.066 |
bye | -0.065 |
red | -0.065 |
seven | -0.060 |
By | -0.059 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
hospital | +0.484 |
slams | +0.435 |
mun | +0.397 |
clinic | +0.392 |
promises | +0.377 |
Neg logit contributions | |
ever | -0.514 |
bye | -0.511 |
red | -0.497 |
ago | -0.468 |
seven | -0.466 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
hospital | +0.155 |
slams | +0.143 |
clinic | +0.132 |
mun | +0.129 |
chores | +0.125 |
Neg logit contributions | |
ever | -0.122 |
bye | -0.119 |
red | -0.117 |
seven | -0.106 |
ago | -0.106 |
Token | and |
Token ID | 290 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ever | +0.066 |
bye | +0.066 |
red | +0.064 |
seven | +0.059 |
ago | +0.059 |
Neg logit contributions | |
hospital | -0.072 |
slams | -0.065 |
clinic | -0.060 |
mun | -0.059 |
promises | -0.057 |
Token | they |
Token ID | 484 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
hospital | +0.023 |
slams | +0.021 |
clinic | +0.020 |
mun | +0.019 |
chores | +0.019 |
Neg logit contributions | |
ever | -0.015 |
bye | -0.014 |
red | -0.014 |
seven | -0.013 |
By | -0.012 |
Token | heard |
Token ID | 2982 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
hospital | +0.016 |
slams | +0.015 |
clinic | +0.014 |
mun | +0.014 |
cleans | +0.013 |
Neg logit contributions | |
bye | -0.011 |
ever | -0.011 |
red | -0.011 |
ago | -0.010 |
seven | -0.010 |
Token | together |
Token ID | 1978 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
slams | +0.045 |
hospital | +0.044 |
mun | +0.041 |
clinic | +0.040 |
cleans | +0.040 |
Neg logit contributions | |
ever | -0.034 |
By | -0.030 |
bye | -0.030 |
seven | -0.029 |
than | -0.028 |
Token | happily |
Token ID | 18177 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
hospital | +0.054 |
slams | +0.051 |
clinic | +0.047 |
mun | +0.046 |
cleans | +0.046 |
Neg logit contributions | |
ever | -0.039 |
bye | -0.036 |
red | -0.036 |
seven | -0.033 |
By | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
bye | +0.142 |
red | +0.138 |
ever | +0.131 |
seven | +0.129 |
ago | +0.127 |
Neg logit contributions | |
hospital | -0.219 |
slams | -0.197 |
clinic | -0.188 |
mun | -0.185 |
promises | -0.178 |
Token | never |
Token ID | 1239 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
hospital | +0.035 |
slams | +0.033 |
clinic | +0.031 |
mun | +0.030 |
chores | +0.029 |
Neg logit contributions | |
ever | -0.018 |
bye | -0.017 |
red | -0.017 |
seven | -0.015 |
ago | -0.015 |
Token | qu |
Token ID | 627 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
bye | +0.155 |
ever | +0.153 |
red | +0.149 |
seven | +0.143 |
ago | +0.138 |
Neg logit contributions | |
hospital | -0.223 |
slams | -0.205 |
mun | -0.188 |
clinic | -0.186 |
cleans | -0.181 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
hospital | +0.034 |
slams | +0.028 |
clinic | +0.025 |
mun | +0.021 |
chores | +0.021 |
Neg logit contributions | |
red | -0.084 |
ever | -0.080 |
bye | -0.079 |
By | -0.075 |
ring | -0.075 |
Token | lled |
Token ID | 3353 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
hospital | +0.670 |
slams | +0.623 |
mun | +0.580 |
clinic | +0.579 |
promises | +0.561 |
Neg logit contributions | |
ever | -0.330 |
bye | -0.327 |
red | -0.311 |
ago | -0.283 |
seven | -0.283 |
Token | again |
Token ID | 757 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
ever | +0.122 |
bye | +0.118 |
red | +0.116 |
seven | +0.108 |
ago | +0.107 |
Neg logit contributions | |
hospital | -0.103 |
slams | -0.093 |
clinic | -0.085 |
mun | -0.082 |
cleans | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-04 |
Pos logit contributions | |
hospital | +0.246 |
slams | +0.223 |
clinic | +0.206 |
mun | +0.200 |
promises | +0.196 |
Neg logit contributions | |
bye | -0.210 |
ever | -0.207 |
red | -0.203 |
seven | -0.188 |
By | -0.186 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ever | +0.000 |
bye | +0.000 |
red | +0.000 |
By | +0.000 |
ago | +0.000 |
Neg logit contributions | |
hospital | -0.000 |
slams | -0.000 |
clinic | -0.000 |
mun | -0.000 |
chores | -0.000 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
hospital | +0.198 |
slams | +0.180 |
clinic | +0.165 |
mun | +0.162 |
promises | +0.156 |
Neg logit contributions | |
ever | -0.176 |
bye | -0.173 |
red | -0.170 |
seven | -0.157 |
ago | -0.156 |
Token | One |
Token ID | 3198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.005 |
mun | +0.005 |
clinic | +0.005 |
chores | +0.005 |
Neg logit contributions | |
red | -0.007 |
ever | -0.007 |
bye | -0.007 |
ago | -0.006 |
hy | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
ever | +0.007 |
bye | +0.007 |
red | +0.006 |
seven | +0.006 |
ago | +0.006 |
Neg logit contributions | |
hospital | -0.013 |
slams | -0.012 |
clinic | -0.012 |
mun | -0.011 |
cleans | -0.011 |
Token | they |
Token ID | 484 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
bye | +0.037 |
red | +0.036 |
ever | +0.035 |
hy | +0.034 |
ring | +0.034 |
Neg logit contributions | |
hospital | -0.036 |
slams | -0.032 |
mun | -0.030 |
chores | -0.029 |
cleans | -0.028 |
Token | were |
Token ID | 547 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.019 |
mun | +0.018 |
clinic | +0.018 |
cleans | +0.017 |
Neg logit contributions | |
bye | -0.015 |
red | -0.014 |
ever | -0.014 |
ago | -0.013 |
seven | -0.013 |
Token | qu |
Token ID | 627 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
ever | +0.039 |
seven | +0.034 |
red | +0.034 |
bye | +0.034 |
ago | +0.033 |
Neg logit contributions | |
hospital | -0.042 |
slams | -0.040 |
cleans | -0.038 |
promises | -0.037 |
clinic | -0.037 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
hospital | +0.035 |
slams | +0.031 |
clinic | +0.026 |
cleans | +0.026 |
tells | +0.024 |
Neg logit contributions | |
red | -0.081 |
bye | -0.079 |
ever | -0.077 |
ring | -0.074 |
seven | -0.073 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
hospital | +0.522 |
slams | +0.475 |
clinic | +0.444 |
mun | +0.412 |
cleans | +0.412 |
Neg logit contributions | |
ever | -0.492 |
red | -0.480 |
bye | -0.475 |
seven | -0.431 |
ago | -0.425 |
Token | over |
Token ID | 625 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
hospital | +0.174 |
slams | +0.164 |
clinic | +0.154 |
mun | +0.150 |
cleans | +0.148 |
Neg logit contributions | |
ever | -0.111 |
red | -0.106 |
bye | -0.104 |
seven | -0.093 |
ago | -0.090 |
Token | who |
Token ID | 508 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
hospital | +0.194 |
slams | +0.178 |
clinic | +0.164 |
mun | +0.161 |
promises | +0.156 |
Neg logit contributions | |
ever | -0.151 |
bye | -0.147 |
red | -0.144 |
seven | -0.132 |
ago | -0.132 |
Token | should |
Token ID | 815 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
hospital | +0.051 |
slams | +0.047 |
clinic | +0.044 |
mun | +0.043 |
chores | +0.042 |
Neg logit contributions | |
ever | -0.031 |
bye | -0.030 |
red | -0.029 |
ago | -0.026 |
seven | -0.026 |
Token | have |
Token ID | 423 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
hospital | +0.158 |
slams | +0.149 |
mun | +0.141 |
clinic | +0.138 |
cleans | +0.132 |
Neg logit contributions | |
ever | -0.129 |
bye | -0.119 |
red | -0.113 |
ago | -0.105 |
hy | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
hospital | +0.078 |
slams | +0.070 |
clinic | +0.065 |
mun | +0.062 |
chores | +0.062 |
Neg logit contributions | |
bye | -0.069 |
ever | -0.066 |
red | -0.065 |
By | -0.063 |
seven | -0.060 |
Token | The |
Token ID | 383 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
hospital | +0.013 |
slams | +0.012 |
clinic | +0.011 |
mun | +0.011 |
chores | +0.011 |
Neg logit contributions | |
ever | -0.007 |
bye | -0.007 |
red | -0.007 |
seven | -0.006 |
ago | -0.006 |
Token | bears |
Token ID | 13062 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
ever | +0.001 |
red | +0.001 |
bye | +0.001 |
By | +0.001 |
ago | +0.001 |
Neg logit contributions | |
hospital | -0.001 |
slams | -0.001 |
clinic | -0.001 |
mun | -0.001 |
chores | -0.001 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
hospital | +0.065 |
slams | +0.060 |
clinic | +0.056 |
mun | +0.055 |
chores | +0.054 |
Neg logit contributions | |
ever | -0.036 |
bye | -0.034 |
red | -0.034 |
seven | -0.030 |
ago | -0.030 |
Token | qu |
Token ID | 627 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
ever | +0.066 |
red | +0.060 |
bye | +0.057 |
ago | +0.056 |
seven | +0.054 |
Neg logit contributions | |
hospital | -0.081 |
slams | -0.076 |
clinic | -0.070 |
mun | -0.066 |
cleans | -0.065 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
hospital | +0.054 |
slams | +0.048 |
clinic | +0.044 |
chores | +0.042 |
promises | +0.041 |
Neg logit contributions | |
red | -0.063 |
bye | -0.059 |
ever | -0.057 |
ring | -0.055 |
seven | -0.054 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
hospital | +0.484 |
slams | +0.436 |
clinic | +0.397 |
mun | +0.388 |
promises | +0.373 |
Neg logit contributions | |
ever | -0.522 |
bye | -0.514 |
red | -0.505 |
seven | -0.468 |
ago | -0.467 |
Token | and |
Token ID | 290 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
hospital | +0.161 |
slams | +0.149 |
clinic | +0.137 |
mun | +0.134 |
cleans | +0.130 |
Neg logit contributions | |
ever | -0.125 |
bye | -0.121 |
red | -0.120 |
seven | -0.109 |
ago | -0.107 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
hospital | +0.025 |
slams | +0.023 |
clinic | +0.022 |
chores | +0.021 |
mun | +0.021 |
Neg logit contributions | |
ever | -0.016 |
bye | -0.015 |
red | -0.015 |
seven | -0.014 |
ago | -0.013 |
Token | him |
Token ID | 683 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ever | +0.020 |
bye | +0.019 |
red | +0.019 |
seven | +0.017 |
ago | +0.017 |
Neg logit contributions | |
hospital | -0.027 |
slams | -0.026 |
clinic | -0.024 |
mun | -0.023 |
cleans | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
ever | +0.126 |
red | +0.107 |
bye | +0.106 |
seven | +0.105 |
ago | +0.103 |
Neg logit contributions | |
hospital | -0.155 |
slams | -0.147 |
mun | -0.133 |
clinic | -0.131 |
arre | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
hospital | +0.052 |
slams | +0.048 |
clinic | +0.044 |
promises | +0.042 |
cleans | +0.042 |
Neg logit contributions | |
ever | -0.042 |
ago | -0.039 |
red | -0.038 |
bye | -0.034 |
hy | -0.034 |
Token | their |
Token ID | 511 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.020 |
clinic | +0.018 |
promises | +0.017 |
mun | +0.017 |
Neg logit contributions | |
ever | -0.018 |
bye | -0.017 |
red | -0.017 |
ago | -0.016 |
seven | -0.016 |
Token | children |
Token ID | 1751 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ever | +0.080 |
bye | +0.075 |
red | +0.072 |
seven | +0.071 |
ago | +0.071 |
Neg logit contributions | |
hospital | -0.081 |
slams | -0.078 |
clinic | -0.069 |
mun | -0.068 |
cleans | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
ever | +0.087 |
ago | +0.079 |
red | +0.077 |
bye | +0.069 |
hy | +0.066 |
Neg logit contributions | |
hospital | -0.135 |
slams | -0.124 |
clinic | -0.117 |
mun | -0.112 |
cleans | -0.111 |
Token | qu |
Token ID | 627 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
hospital | +0.023 |
slams | +0.022 |
clinic | +0.020 |
mun | +0.019 |
promises | +0.019 |
Neg logit contributions | |
ever | -0.018 |
red | -0.016 |
bye | -0.016 |
ago | -0.016 |
seven | -0.015 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
hospital | +0.043 |
slams | +0.038 |
clinic | +0.035 |
cleans | +0.032 |
chores | +0.032 |
Neg logit contributions | |
red | -0.064 |
bye | -0.061 |
ever | -0.061 |
seven | -0.057 |
ago | -0.056 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
hospital | +0.522 |
slams | +0.476 |
clinic | +0.446 |
cleans | +0.409 |
promises | +0.406 |
Neg logit contributions | |
ever | -0.491 |
red | -0.479 |
bye | -0.471 |
seven | -0.430 |
ago | -0.424 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-03 |
Pos logit contributions | |
hospital | +0.169 |
slams | +0.158 |
clinic | +0.149 |
mun | +0.144 |
cleans | +0.140 |
Neg logit contributions | |
red | -0.110 |
ever | -0.109 |
bye | -0.102 |
seven | -0.093 |
ago | -0.091 |
Token | |
Token ID | 220 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ever | +0.000 |
bye | +0.000 |
red | +0.000 |
ago | +0.000 |
seven | +0.000 |
Neg logit contributions | |
hospital | -0.000 |
slams | -0.000 |
clinic | -0.000 |
mun | -0.000 |
promises | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
hospital | +0.036 |
slams | +0.033 |
clinic | +0.030 |
mun | +0.030 |
promises | +0.029 |
Neg logit contributions | |
ever | -0.024 |
bye | -0.023 |
red | -0.023 |
ago | -0.021 |
By | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
ever | +0.001 |
bye | +0.001 |
red | +0.001 |
seven | +0.001 |
ago | +0.001 |
Neg logit contributions | |
hospital | -0.002 |
slams | -0.002 |
clinic | -0.001 |
mun | -0.001 |
promises | -0.001 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ever | +0.026 |
bye | +0.024 |
red | +0.023 |
By | +0.022 |
seven | +0.022 |
Neg logit contributions | |
hospital | -0.027 |
slams | -0.026 |
clinic | -0.025 |
mun | -0.024 |
promises | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
hospital | +0.157 |
slams | +0.151 |
clinic | +0.144 |
mun | +0.141 |
chores | +0.136 |
Neg logit contributions | |
ever | -0.093 |
red | -0.085 |
bye | -0.082 |
ago | -0.073 |
than | -0.073 |
Token | apologized |
Token ID | 22893 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hospital | +0.033 |
slams | +0.031 |
clinic | +0.030 |
mun | +0.029 |
chores | +0.028 |
Neg logit contributions | |
ever | -0.026 |
bye | -0.025 |
red | -0.024 |
By | -0.022 |
seven | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
hospital | +0.110 |
slams | +0.105 |
clinic | +0.100 |
mun | +0.099 |
cleans | +0.093 |
Neg logit contributions | |
ever | -0.056 |
red | -0.052 |
bye | -0.052 |
than | -0.044 |
seven | -0.043 |
Token | qu |
Token ID | 627 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
ever | +0.019 |
red | +0.017 |
bye | +0.017 |
ago | +0.016 |
By | +0.016 |
Neg logit contributions | |
hospital | -0.024 |
slams | -0.022 |
clinic | -0.021 |
mun | -0.021 |
cleans | -0.019 |
Token | arre |
Token ID | 9624 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
hospital | +0.040 |
slams | +0.034 |
clinic | +0.032 |
mun | +0.026 |
cleans | +0.026 |
Neg logit contributions | |
red | -0.080 |
bye | -0.077 |
ever | -0.077 |
ring | -0.070 |
seven | -0.070 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
hospital | +0.519 |
slams | +0.473 |
clinic | +0.444 |
mun | +0.412 |
cleans | +0.406 |
Neg logit contributions | |
ever | -0.494 |
red | -0.483 |
bye | -0.481 |
seven | -0.430 |
ago | -0.424 |
Token | . |
Token ID | 13 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
hospital | +0.175 |
slams | +0.164 |
clinic | +0.158 |
mun | +0.154 |
cleans | +0.147 |
Neg logit contributions | |
ever | -0.111 |
red | -0.107 |
bye | -0.102 |
seven | -0.088 |
ago | -0.088 |
Token | " |
Token ID | 366 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
hospital | +0.007 |
slams | +0.007 |
clinic | +0.006 |
mun | +0.006 |
chores | +0.006 |
Neg logit contributions | |
ever | -0.005 |
bye | -0.005 |
red | -0.005 |
ago | -0.004 |
seven | -0.004 |
Token | I |
Token ID | 40 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
hospital | +0.049 |
slams | +0.045 |
clinic | +0.042 |
mun | +0.042 |
promises | +0.041 |
Neg logit contributions | |
ever | -0.029 |
bye | -0.029 |
red | -0.028 |
ago | -0.026 |
seven | -0.025 |
Token | 'm |
Token ID | 1101 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ever | +0.037 |
bye | +0.030 |
By | +0.027 |
red | +0.026 |
t | +0.026 |
Neg logit contributions | |
hospital | -0.048 |
slams | -0.048 |
clinic | -0.045 |
basement | -0.042 |
chores | -0.041 |
Token | for |
Token ID | 329 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
ever | +0.009 |
bye | +0.009 |
red | +0.009 |
seven | +0.008 |
ago | +0.008 |
Neg logit contributions | |
hospital | -0.014 |
slams | -0.013 |
clinic | -0.013 |
mun | -0.012 |
cleans | -0.012 |
Token | an |
Token ID | 281 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
ever | +0.023 |
bye | +0.021 |
red | +0.021 |
ago | +0.020 |
seven | +0.020 |
Neg logit contributions | |
hospital | -0.024 |
slams | -0.023 |
clinic | -0.021 |
mun | -0.021 |
cleans | -0.020 |
Token | answer |
Token ID | 3280 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
hospital | +0.063 |
slams | +0.062 |
mun | +0.060 |
cleans | +0.056 |
clinic | +0.056 |
Neg logit contributions | |
ever | -0.055 |
bye | -0.054 |
red | -0.050 |
seven | -0.048 |
ago | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
hospital | +0.055 |
slams | +0.050 |
clinic | +0.047 |
mun | +0.044 |
promises | +0.044 |
Neg logit contributions | |
bye | -0.043 |
ever | -0.042 |
red | -0.042 |
By | -0.039 |
seven | -0.038 |
Token | Before |
Token ID | 7413 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
hospital | +0.004 |
slams | +0.004 |
mun | +0.004 |
clinic | +0.004 |
chores | +0.003 |
Neg logit contributions | |
bye | -0.003 |
ever | -0.003 |
red | -0.003 |
ago | -0.003 |
seven | -0.003 |
Token | long |
Token ID | 890 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
red | +0.035 |
bye | +0.033 |
ever | +0.029 |
ring | +0.029 |
seven | +0.027 |
Neg logit contributions | |
hospital | -0.064 |
slams | -0.057 |
chores | -0.054 |
lim | -0.053 |
clinic | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
bye | +0.289 |
By | +0.272 |
ever | +0.271 |
red | +0.267 |
seven | +0.261 |
Neg logit contributions | |
hospital | -0.266 |
slams | -0.236 |
chores | -0.213 |
promises | -0.211 |
clinic | -0.207 |
Token | Bill |
Token ID | 3941 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
hospital | +0.029 |
slams | +0.025 |
chores | +0.023 |
mun | +0.022 |
promises | +0.022 |
Neg logit contributions | |
red | -0.024 |
ago | -0.022 |
ever | -0.021 |
bye | -0.020 |
ring | -0.020 |
Token | noticed |
Token ID | 6810 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ever | +0.165 |
bye | +0.163 |
red | +0.159 |
seven | +0.144 |
ago | +0.144 |
Neg logit contributions | |
hospital | -0.249 |
slams | -0.229 |
clinic | -0.213 |
mun | -0.208 |
promises | -0.203 |
Token | that |
Token ID | 326 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
ever | +0.020 |
bye | +0.019 |
red | +0.018 |
ago | +0.017 |
seven | +0.016 |
Neg logit contributions | |
hospital | -0.031 |
slams | -0.030 |
clinic | -0.028 |
mun | -0.027 |
promises | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
hospital | +0.005 |
slams | +0.005 |
clinic | +0.004 |
mun | +0.004 |
cleans | +0.004 |
Neg logit contributions | |
ever | -0.003 |
bye | -0.003 |
red | -0.002 |
ago | -0.002 |
seven | -0.002 |
Token | es |
Token ID | 274 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
bye | +0.127 |
ever | +0.125 |
red | +0.123 |
seven | +0.114 |
ago | +0.114 |
Neg logit contributions | |
hospital | -0.141 |
slams | -0.126 |
clinic | -0.117 |
mun | -0.115 |
promises | -0.112 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
hospital | +0.104 |
slams | +0.093 |
mun | +0.087 |
clinic | +0.086 |
cleans | +0.083 |
Neg logit contributions | |
bye | -0.083 |
ever | -0.081 |
red | -0.078 |
seven | -0.074 |
ago | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ever | +0.064 |
bye | +0.062 |
red | +0.061 |
seven | +0.056 |
ago | +0.055 |
Neg logit contributions | |
hospital | -0.088 |
slams | -0.081 |
clinic | -0.075 |
mun | -0.073 |
cleans | -0.071 |
Token | wizard |
Token ID | 18731 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
ever | +0.011 |
red | +0.011 |
bye | +0.011 |
ago | +0.010 |
By | +0.010 |
Neg logit contributions | |
hospital | -0.011 |
slams | -0.010 |
clinic | -0.009 |
promises | -0.009 |
chores | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ever | +0.024 |
bye | +0.024 |
red | +0.024 |
ago | +0.022 |
seven | +0.022 |
Neg logit contributions | |
hospital | -0.028 |
slams | -0.026 |
clinic | -0.024 |
mun | -0.023 |
promises | -0.023 |
Token | thanked |
Token ID | 26280 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
hospital | +0.022 |
slams | +0.021 |
clinic | +0.019 |
mun | +0.019 |
chores | +0.018 |
Neg logit contributions | |
ever | -0.015 |
bye | -0.014 |
red | -0.014 |
seven | -0.013 |
ago | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ever | +0.239 |
bye | +0.234 |
red | +0.230 |
seven | +0.210 |
ago | +0.209 |
Neg logit contributions | |
hospital | -0.297 |
slams | -0.273 |
clinic | -0.251 |
mun | -0.246 |
promises | -0.238 |
Token | . |
Token ID | 13 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
ever | +0.091 |
bye | +0.082 |
red | +0.079 |
seven | +0.073 |
ago | +0.068 |
Neg logit contributions | |
hospital | -0.173 |
slams | -0.168 |
mun | -0.155 |
cleans | -0.151 |
clinic | -0.149 |
Token | They |
Token ID | 1119 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ever | +0.005 |
bye | +0.005 |
red | +0.005 |
ago | +0.004 |
seven | +0.004 |
Neg logit contributions | |
hospital | -0.006 |
slams | -0.005 |
clinic | -0.005 |
mun | -0.005 |
chores | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
hospital | +0.082 |
slams | +0.074 |
mun | +0.068 |
clinic | +0.067 |
promises | +0.066 |
Neg logit contributions | |
bye | -0.065 |
ever | -0.064 |
red | -0.064 |
ago | -0.060 |
seven | -0.058 |
Token | now |
Token ID | 783 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
bye | +0.047 |
red | +0.047 |
ago | +0.043 |
ever | +0.042 |
By | +0.041 |
Neg logit contributions | |
hospital | -0.046 |
slams | -0.040 |
promises | -0.036 |
clinic | -0.035 |
chores | -0.035 |
Token | And |
Token ID | 843 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
bye | +0.002 |
ever | +0.002 |
red | +0.002 |
By | +0.002 |
ago | +0.002 |
Neg logit contributions | |
hospital | -0.002 |
slams | -0.002 |
clinic | -0.002 |
mun | -0.002 |
chores | -0.002 |
Token | they |
Token ID | 484 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
hospital | +0.058 |
slams | +0.054 |
clinic | +0.050 |
mun | +0.049 |
cleans | +0.048 |
Neg logit contributions | |
ever | -0.039 |
bye | -0.038 |
red | -0.037 |
ago | -0.033 |
seven | -0.033 |
Token | all |
Token ID | 477 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
hospital | +0.005 |
slams | +0.004 |
mun | +0.004 |
clinic | +0.004 |
promises | +0.004 |
Neg logit contributions | |
bye | -0.005 |
red | -0.005 |
ever | -0.005 |
ago | -0.005 |
seven | -0.005 |
Token | lived |
Token ID | 5615 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
hospital | +0.081 |
slams | +0.074 |
clinic | +0.068 |
mun | +0.067 |
cleans | +0.065 |
Neg logit contributions | |
ever | -0.064 |
bye | -0.063 |
red | -0.062 |
seven | -0.057 |
ago | -0.057 |
Token | happily |
Token ID | 18177 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
ever | +0.043 |
bye | +0.042 |
red | +0.041 |
seven | +0.038 |
By | +0.038 |
Neg logit contributions | |
hospital | -0.044 |
slams | -0.041 |
clinic | -0.037 |
mun | -0.036 |
cleans | -0.035 |
Token | ever |
Token ID | 1683 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
red | +0.037 |
seventeen | +0.036 |
bye | +0.034 |
seven | +0.031 |
hire | +0.028 |
Neg logit contributions | |
hospital | -0.314 |
slams | -0.288 |
mun | -0.287 |
clinic | -0.287 |
promises | -0.279 |
Token | after |
Token ID | 706 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
red | +0.348 |
bye | +0.347 |
ever | +0.335 |
boat | +0.326 |
seventeen | +0.323 |
Neg logit contributions | |
hospital | -0.453 |
slams | -0.386 |
clinic | -0.371 |
mistakes | -0.361 |
mun | -0.357 |
Token | . |
Token ID | 13 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
ever | +0.035 |
bye | +0.032 |
red | +0.031 |
ago | +0.030 |
By | +0.028 |
Neg logit contributions | |
hospital | -0.050 |
slams | -0.047 |
clinic | -0.043 |
mun | -0.042 |
cleans | -0.041 |
Token | The |
Token ID | 383 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ever | +0.002 |
bye | +0.002 |
red | +0.002 |
seven | +0.002 |
ago | +0.002 |
Neg logit contributions | |
hospital | -0.002 |
slams | -0.002 |
clinic | -0.002 |
mun | -0.002 |
promises | -0.002 |
Token | end |
Token ID | 886 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ever | +0.006 |
red | +0.006 |
bye | +0.006 |
ago | +0.005 |
seven | +0.005 |
Neg logit contributions | |
hospital | -0.007 |
slams | -0.007 |
clinic | -0.006 |
mun | -0.006 |
chores | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
hospital | +0.026 |
slams | +0.024 |
mun | +0.023 |
clinic | +0.022 |
chores | +0.022 |
Neg logit contributions | |
ever | -0.013 |
bye | -0.012 |
red | -0.011 |
By | -0.011 |
than | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
hospital | +0.134 |
slams | +0.123 |
clinic | +0.114 |
promises | +0.109 |
chores | +0.109 |
Neg logit contributions | |
red | -0.096 |
ever | -0.095 |
bye | -0.093 |
ago | -0.089 |
By | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
hospital | +0.016 |
mun | +0.015 |
slams | +0.015 |
arre | +0.015 |
clinic | +0.014 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.005 |
seven | -0.005 |
Dad | -0.004 |
red | -0.004 |
Token | classroom |
Token ID | 15806 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
slams | +0.001 |
hospital | +0.001 |
mun | +0.001 |
clinic | +0.001 |
cleans | +0.001 |
Neg logit contributions | |
ever | -0.001 |
bye | -0.001 |
seven | -0.001 |
wind | -0.001 |
By | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
hospital | +0.138 |
slams | +0.126 |
clinic | +0.117 |
mun | +0.116 |
cleans | +0.112 |
Neg logit contributions | |
ever | -0.107 |
bye | -0.103 |
red | -0.101 |
ago | -0.094 |
seven | -0.093 |
Token | They |
Token ID | 1119 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
ever | +0.032 |
bye | +0.032 |
red | +0.031 |
ago | +0.030 |
seven | +0.029 |
Neg logit contributions | |
hospital | -0.040 |
slams | -0.036 |
mun | -0.034 |
clinic | -0.033 |
promises | -0.032 |
Token | smile |
Token ID | 8212 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
hospital | +0.070 |
slams | +0.064 |
clinic | +0.060 |
mun | +0.059 |
mistakes | +0.059 |
Neg logit contributions | |
ever | -0.057 |
bye | -0.054 |
red | -0.051 |
seven | -0.050 |
ago | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
bye | +0.270 |
ever | +0.269 |
red | +0.263 |
seven | +0.246 |
hy | +0.244 |
Neg logit contributions | |
hospital | -0.252 |
slams | -0.219 |
clinic | -0.206 |
promises | -0.201 |
cleans | -0.197 |
Token | say |
Token ID | 910 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
hospital | +0.000 |
slams | +0.000 |
clinic | +0.000 |
mun | +0.000 |
promises | +0.000 |
Neg logit contributions | |
red | -0.000 |
ever | -0.000 |
bye | -0.000 |
ago | -0.000 |
seven | -0.000 |
Token | hello |
Token ID | 23748 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
hospital | +0.056 |
slams | +0.051 |
clinic | +0.048 |
mun | +0.047 |
chores | +0.046 |
Neg logit contributions | |
ever | -0.039 |
bye | -0.039 |
red | -0.038 |
ago | -0.034 |
seven | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ever | +0.026 |
red | +0.026 |
bye | +0.026 |
seven | +0.024 |
ago | +0.024 |
Neg logit contributions | |
hospital | -0.029 |
slams | -0.026 |
clinic | -0.025 |
promises | -0.023 |
mun | -0.023 |
Token | their |
Token ID | 511 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
hospital | +0.015 |
slams | +0.014 |
mun | +0.013 |
clinic | +0.013 |
mistakes | +0.013 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.006 |
red | -0.005 |
seven | -0.005 |
By | -0.004 |
Token | swing |
Token ID | 9628 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
hospital | +0.008 |
slams | +0.007 |
clinic | +0.007 |
mun | +0.007 |
mistakes | +0.006 |
Neg logit contributions | |
ever | -0.009 |
bye | -0.009 |
red | -0.009 |
seven | -0.008 |
ago | -0.008 |
Token | high |
Token ID | 1029 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
hospital | +0.138 |
slams | +0.128 |
clinic | +0.113 |
chores | +0.111 |
mun | +0.110 |
Neg logit contributions | |
bye | -0.130 |
ever | -0.130 |
red | -0.129 |
ago | -0.120 |
By | -0.117 |
Token | and |
Token ID | 290 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
ever | +0.167 |
bye | +0.164 |
red | +0.160 |
seven | +0.147 |
ago | +0.146 |
Neg logit contributions | |
hospital | -0.215 |
slams | -0.196 |
clinic | -0.182 |
mun | -0.178 |
promises | -0.173 |
Token | feel |
Token ID | 1254 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
red | +0.005 |
bye | +0.005 |
ever | +0.005 |
ago | +0.005 |
By | +0.005 |
Neg logit contributions | |
hospital | -0.004 |
slams | -0.004 |
clinic | -0.004 |
mun | -0.003 |
chores | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
hospital | +0.043 |
slams | +0.039 |
clinic | +0.036 |
mun | +0.036 |
promises | +0.035 |
Neg logit contributions | |
ever | -0.032 |
bye | -0.031 |
red | -0.031 |
ago | -0.028 |
seven | -0.028 |
Token | wind |
Token ID | 2344 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
red | +0.009 |
ever | +0.008 |
bye | +0.008 |
ago | +0.007 |
By | +0.006 |
Neg logit contributions | |
hospital | -0.026 |
slams | -0.024 |
clinic | -0.023 |
mun | -0.022 |
chores | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
bye | +0.324 |
ever | +0.307 |
red | +0.304 |
seven | +0.292 |
ago | +0.291 |
Neg logit contributions | |
hospital | -0.351 |
slams | -0.319 |
mun | -0.292 |
clinic | -0.288 |
cleans | -0.282 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ever | +0.027 |
bye | +0.026 |
red | +0.026 |
seven | +0.024 |
ago | +0.024 |
Neg logit contributions | |
hospital | -0.040 |
slams | -0.037 |
mun | -0.034 |
clinic | -0.034 |
promises | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ever | +0.008 |
bye | +0.007 |
By | +0.007 |
red | +0.007 |
ago | +0.006 |
Neg logit contributions | |
hospital | -0.012 |
slams | -0.012 |
clinic | -0.010 |
mun | -0.010 |
promises | -0.010 |
Token | " |
Token ID | 1 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ever | +0.008 |
red | +0.007 |
bye | +0.007 |
ago | +0.006 |
seven | +0.006 |
Neg logit contributions | |
hospital | -0.014 |
slams | -0.013 |
clinic | -0.012 |
mun | -0.012 |
chores | -0.011 |
Token | OK |
Token ID | 11380 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
ever | +0.159 |
red | +0.158 |
bye | +0.152 |
ago | +0.151 |
hy | +0.136 |
Neg logit contributions | |
hospital | -0.201 |
slams | -0.183 |
mun | -0.174 |
clinic | -0.171 |
chores | -0.163 |
Token | want |
Token ID | 765 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
ever | +0.016 |
bye | +0.015 |
red | +0.014 |
ago | +0.013 |
seven | +0.013 |
Neg logit contributions | |
hospital | -0.020 |
slams | -0.019 |
clinic | -0.018 |
mun | -0.018 |
mistakes | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
ever | +0.043 |
bye | +0.040 |
red | +0.036 |
seven | +0.034 |
ago | +0.032 |
Neg logit contributions | |
hospital | -0.088 |
slams | -0.085 |
mun | -0.080 |
clinic | -0.079 |
cleans | -0.075 |
Token | see |
Token ID | 766 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
hospital | +0.005 |
slams | +0.005 |
clinic | +0.004 |
mun | +0.004 |
promises | +0.004 |
Neg logit contributions | |
ever | -0.003 |
bye | -0.003 |
red | -0.003 |
seven | -0.003 |
ago | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
ever | +0.101 |
bye | +0.095 |
seven | +0.089 |
red | +0.087 |
ago | +0.082 |
Neg logit contributions | |
hospital | -0.136 |
slams | -0.131 |
mun | -0.123 |
clinic | -0.120 |
arre | -0.117 |
Token | animals |
Token ID | 4695 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ever | +0.004 |
bye | +0.004 |
seven | +0.004 |
ago | +0.004 |
red | +0.004 |
Neg logit contributions | |
hospital | -0.004 |
slams | -0.004 |
mun | -0.004 |
clinic | -0.004 |
cleans | -0.004 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
hospital | +0.031 |
slams | +0.029 |
clinic | +0.027 |
mun | +0.026 |
promises | +0.025 |
Neg logit contributions | |
ever | -0.023 |
bye | -0.023 |
red | -0.022 |
seven | -0.020 |
ago | -0.020 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ever | +0.167 |
bye | +0.162 |
red | +0.157 |
seven | +0.152 |
ago | +0.151 |
Neg logit contributions | |
hospital | -0.221 |
slams | -0.203 |
mun | -0.193 |
clinic | -0.193 |
mistakes | -0.185 |
Token | and |
Token ID | 290 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
hospital | +0.174 |
slams | +0.160 |
clinic | +0.149 |
mun | +0.145 |
chores | +0.143 |
Neg logit contributions | |
ever | -0.126 |
red | -0.122 |
bye | -0.122 |
seven | -0.110 |
ago | -0.108 |
Token | Sam |
Token ID | 3409 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
hospital | +0.003 |
slams | +0.003 |
clinic | +0.002 |
promises | +0.002 |
chores | +0.002 |
Neg logit contributions | |
ever | -0.002 |
bye | -0.002 |
red | -0.002 |
By | -0.002 |
ago | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
hospital | +0.046 |
slams | +0.042 |
clinic | +0.039 |
mun | +0.038 |
promises | +0.037 |
Neg logit contributions | |
ever | -0.036 |
bye | -0.035 |
red | -0.034 |
seven | -0.031 |
ago | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
hospital | +0.007 |
slams | +0.007 |
clinic | +0.006 |
mun | +0.006 |
cleans | +0.006 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.005 |
red | -0.005 |
ago | -0.005 |
seven | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hospital | +0.023 |
slams | +0.022 |
clinic | +0.021 |
chores | +0.020 |
mun | +0.020 |
Neg logit contributions | |
ever | -0.015 |
bye | -0.014 |
red | -0.014 |
By | -0.012 |
seven | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.019 |
clinic | +0.017 |
mun | +0.017 |
chores | +0.017 |
Neg logit contributions | |
bye | -0.018 |
ever | -0.017 |
red | -0.017 |
seven | -0.016 |
ago | -0.016 |
Token | � |
Token ID | 6184 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
hospital | +0.027 |
slams | +0.024 |
clinic | +0.023 |
mun | +0.022 |
cleans | +0.022 |
Neg logit contributions | |
bye | -0.021 |
ever | -0.021 |
red | -0.020 |
seven | -0.018 |
ago | -0.018 |
Token | � |
Token ID | 95 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
hospital | +0.154 |
slams | +0.141 |
mun | +0.133 |
clinic | +0.131 |
promises | +0.128 |
Neg logit contributions | |
bye | -0.107 |
ever | -0.107 |
red | -0.103 |
seven | -0.095 |
By | -0.095 |
Token | € |
Token ID | 26391 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
bye | +0.013 |
ever | +0.013 |
red | +0.013 |
seven | +0.012 |
By | +0.012 |
Neg logit contributions | |
hospital | -0.017 |
slams | -0.015 |
mun | -0.014 |
clinic | -0.014 |
chores | -0.014 |
Token | � |
Token ID | 129 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
hospital | +0.042 |
slams | +0.038 |
clinic | +0.036 |
mun | +0.035 |
cleans | +0.034 |
Neg logit contributions | |
red | -0.045 |
ever | -0.044 |
bye | -0.044 |
seven | -0.041 |
ago | -0.039 |
Token | � |
Token ID | 241 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
ever | +0.097 |
bye | +0.097 |
red | +0.094 |
seven | +0.086 |
ago | +0.085 |
Neg logit contributions | |
hospital | -0.131 |
slams | -0.120 |
clinic | -0.111 |
mun | -0.110 |
cleans | -0.106 |
Token | I |
Token ID | 40 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
red | +0.026 |
bye | +0.026 |
ever | +0.025 |
seven | +0.024 |
ago | +0.023 |
Neg logit contributions | |
hospital | -0.034 |
slams | -0.030 |
mun | -0.029 |
clinic | -0.029 |
chores | -0.027 |
Token | care |
Token ID | 1337 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ever | +0.046 |
bye | +0.043 |
red | +0.041 |
By | +0.040 |
seven | +0.038 |
Neg logit contributions | |
hospital | -0.055 |
slams | -0.052 |
clinic | -0.046 |
mun | -0.045 |
mistakes | -0.045 |
Token | about |
Token ID | 546 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ever | +0.115 |
bye | +0.111 |
red | +0.111 |
ago | +0.102 |
seven | +0.101 |
Neg logit contributions | |
hospital | -0.146 |
slams | -0.134 |
clinic | -0.125 |
mun | -0.123 |
promises | -0.118 |
Token | you |
Token ID | 345 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hospital | +0.130 |
slams | +0.121 |
clinic | +0.112 |
mun | +0.110 |
cleans | +0.106 |
Neg logit contributions | |
ever | -0.092 |
bye | -0.088 |
red | -0.086 |
ago | -0.079 |
seven | -0.079 |
Token | You |
Token ID | 921 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ever | +0.104 |
bye | +0.103 |
red | +0.100 |
seven | +0.091 |
ago | +0.091 |
Neg logit contributions | |
hospital | -0.143 |
slams | -0.131 |
clinic | -0.121 |
mun | -0.119 |
chores | -0.116 |
Token | can |
Token ID | 460 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
hospital | +0.069 |
slams | +0.062 |
clinic | +0.057 |
mun | +0.056 |
promises | +0.055 |
Neg logit contributions | |
bye | -0.065 |
ever | -0.065 |
red | -0.064 |
ago | -0.059 |
seven | -0.058 |
Token | come |
Token ID | 1282 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
hospital | +0.089 |
slams | +0.080 |
clinic | +0.075 |
mun | +0.073 |
chores | +0.071 |
Neg logit contributions | |
ever | -0.071 |
bye | -0.071 |
red | -0.070 |
ago | -0.064 |
seven | -0.064 |
Token | with |
Token ID | 351 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ever | +0.041 |
bye | +0.040 |
red | +0.040 |
ago | +0.036 |
seven | +0.036 |
Neg logit contributions | |
hospital | -0.057 |
slams | -0.052 |
clinic | -0.049 |
mun | -0.047 |
promises | -0.046 |
Token | me |
Token ID | 502 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
ever | +0.023 |
bye | +0.022 |
red | +0.022 |
ago | +0.020 |
By | +0.020 |
Neg logit contributions | |
hospital | -0.028 |
slams | -0.025 |
clinic | -0.023 |
mun | -0.022 |
promises | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e-03 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.005 |
mun | +0.005 |
clinic | +0.005 |
cleans | +0.005 |
Neg logit contributions | |
ever | -0.004 |
bye | -0.004 |
red | -0.004 |
seven | -0.003 |
ago | -0.003 |
Token | â |
Token ID | 22940 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
ever | +0.000 |
bye | +0.000 |
red | +0.000 |
seven | +0.000 |
ago | +0.000 |
Neg logit contributions | |
hospital | -0.000 |
slams | -0.000 |
mun | -0.000 |
clinic | -0.000 |
chores | -0.000 |
Token | € |
Token ID | 26391 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
hospital | +0.226 |
slams | +0.208 |
clinic | +0.190 |
mun | +0.185 |
promises | +0.182 |
Neg logit contributions | |
ever | -0.187 |
red | -0.174 |
bye | -0.174 |
ago | -0.165 |
seven | -0.162 |
Token |
|
Token ID | 198 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
hospital | +0.047 |
slams | +0.043 |
clinic | +0.040 |
mun | +0.039 |
promises | +0.037 |
Neg logit contributions | |
ever | -0.045 |
red | -0.044 |
bye | -0.043 |
seven | -0.040 |
ago | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
ever | +0.003 |
bye | +0.003 |
red | +0.003 |
By | +0.003 |
seven | +0.003 |
Neg logit contributions | |
hospital | -0.004 |
slams | -0.004 |
clinic | -0.004 |
mun | -0.003 |
promises | -0.003 |
Token | So |
Token ID | 2396 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ever | +0.004 |
bye | +0.003 |
red | +0.003 |
ago | +0.003 |
seven | +0.003 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.004 |
clinic | -0.004 |
mun | -0.004 |
chores | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
hospital | +0.080 |
slams | +0.074 |
clinic | +0.068 |
mun | +0.066 |
promises | +0.065 |
Neg logit contributions | |
ever | -0.064 |
bye | -0.063 |
red | -0.062 |
seven | -0.057 |
ago | -0.056 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
hospital | +0.028 |
slams | +0.025 |
clinic | +0.023 |
mun | +0.023 |
chores | +0.023 |
Neg logit contributions | |
red | -0.024 |
bye | -0.023 |
ever | -0.023 |
seven | -0.021 |
By | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
ever | +0.039 |
bye | +0.031 |
red | +0.028 |
seven | +0.025 |
ago | +0.025 |
Neg logit contributions | |
hospital | -0.102 |
slams | -0.100 |
clinic | -0.094 |
mun | -0.093 |
cleans | -0.090 |
Token | see |
Token ID | 766 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.006 |
clinic | +0.005 |
mun | +0.005 |
cleans | +0.005 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.006 |
red | -0.006 |
seven | -0.006 |
ago | -0.006 |
Token | everything |
Token ID | 2279 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ever | +0.083 |
than | +0.076 |
seven | +0.073 |
wind | +0.071 |
bye | +0.070 |
Neg logit contributions | |
hospital | -0.131 |
slams | -0.126 |
clinic | -0.123 |
arre | -0.116 |
mun | -0.115 |
Token | ! |
Token ID | 0 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
hospital | +0.118 |
slams | +0.108 |
clinic | +0.104 |
mun | +0.100 |
cleans | +0.097 |
Neg logit contributions | |
ever | -0.086 |
bye | -0.078 |
red | -0.076 |
seven | -0.071 |
ago | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
bye | +0.100 |
ever | +0.096 |
ago | +0.091 |
red | +0.089 |
seven | +0.088 |
Neg logit contributions | |
hospital | -0.133 |
slams | -0.129 |
mun | -0.121 |
cleans | -0.116 |
clinic | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
hospital | +0.010 |
slams | +0.010 |
clinic | +0.009 |
cleans | +0.008 |
mun | +0.008 |
Neg logit contributions | |
ever | -0.007 |
bye | -0.006 |
red | -0.006 |
By | -0.006 |
ago | -0.006 |
Token | One |
Token ID | 3198 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
hospital | +0.010 |
slams | +0.009 |
cleans | +0.008 |
clinic | +0.008 |
promises | +0.008 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.006 |
By | -0.006 |
seven | -0.005 |
red | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ever | +0.003 |
bye | +0.003 |
red | +0.003 |
seven | +0.002 |
ago | +0.002 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.005 |
clinic | -0.004 |
mun | -0.004 |
chores | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
bye | +0.031 |
ever | +0.031 |
red | +0.030 |
seven | +0.028 |
ago | +0.028 |
Neg logit contributions | |
hospital | -0.036 |
slams | -0.033 |
mun | -0.030 |
clinic | -0.030 |
chores | -0.029 |
Token | anymore |
Token ID | 7471 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
bye | +0.116 |
ever | +0.115 |
red | +0.111 |
By | +0.105 |
ago | +0.104 |
Neg logit contributions | |
hospital | -0.118 |
slams | -0.107 |
clinic | -0.097 |
promises | -0.094 |
mistakes | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
hospital | +0.235 |
slams | +0.209 |
mun | +0.194 |
clinic | +0.190 |
mistakes | +0.184 |
Neg logit contributions | |
bye | -0.214 |
red | -0.210 |
ever | -0.204 |
seven | -0.201 |
By | -0.196 |
Token | They |
Token ID | 1119 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
hospital | +0.029 |
slams | +0.027 |
clinic | +0.025 |
mun | +0.024 |
chores | +0.024 |
Neg logit contributions | |
ever | -0.023 |
bye | -0.022 |
red | -0.021 |
ago | -0.020 |
seven | -0.020 |
Token | ignored |
Token ID | 9514 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
hospital | +0.066 |
slams | +0.062 |
clinic | +0.058 |
mun | +0.057 |
chores | +0.055 |
Neg logit contributions | |
ever | -0.044 |
bye | -0.042 |
red | -0.040 |
seven | -0.037 |
By | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
hospital | +0.029 |
slams | +0.028 |
clinic | +0.027 |
mun | +0.026 |
cleans | +0.025 |
Neg logit contributions | |
ever | -0.016 |
red | -0.016 |
bye | -0.016 |
seven | -0.013 |
ago | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ever | +0.038 |
bye | +0.035 |
red | +0.034 |
ago | +0.031 |
than | +0.030 |
Neg logit contributions | |
hospital | -0.047 |
slams | -0.046 |
mun | -0.043 |
clinic | -0.042 |
cleans | -0.040 |
Token | cried |
Token ID | 16896 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
hospital | +0.008 |
slams | +0.008 |
clinic | +0.007 |
mun | +0.007 |
chores | +0.007 |
Neg logit contributions | |
ever | -0.005 |
bye | -0.005 |
red | -0.005 |
seven | -0.004 |
ago | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ever | +0.017 |
red | +0.016 |
bye | +0.016 |
seven | +0.014 |
ago | +0.014 |
Neg logit contributions | |
hospital | -0.026 |
slams | -0.025 |
clinic | -0.023 |
mun | -0.023 |
promises | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ever | +0.010 |
bye | +0.010 |
red | +0.010 |
ago | +0.009 |
By | +0.009 |
Neg logit contributions | |
hospital | -0.013 |
slams | -0.012 |
mun | -0.011 |
clinic | -0.011 |
promises | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ever | +0.018 |
bye | +0.017 |
red | +0.016 |
By | +0.016 |
ago | +0.016 |
Neg logit contributions | |
hospital | -0.024 |
slams | -0.022 |
mun | -0.020 |
clinic | -0.020 |
promises | -0.020 |
Token | Their |
Token ID | 14574 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
ever | +0.016 |
bye | +0.016 |
red | +0.015 |
By | +0.014 |
seven | +0.014 |
Neg logit contributions | |
hospital | -0.028 |
slams | -0.026 |
clinic | -0.024 |
mun | -0.024 |
promises | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
hospital | +0.026 |
slams | +0.024 |
mun | +0.022 |
clinic | +0.022 |
chores | +0.021 |
Neg logit contributions | |
bye | -0.023 |
ever | -0.022 |
red | -0.022 |
ago | -0.021 |
By | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
hospital | +0.033 |
slams | +0.029 |
clinic | +0.028 |
mun | +0.027 |
cleans | +0.026 |
Neg logit contributions | |
bye | -0.030 |
ever | -0.029 |
red | -0.028 |
ago | -0.025 |
seven | -0.025 |
Token | We |
Token ID | 1135 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
hospital | +0.033 |
mun | +0.032 |
slams | +0.028 |
arre | +0.028 |
clinic | +0.027 |
Neg logit contributions | |
ago | -0.030 |
ever | -0.030 |
red | -0.029 |
bye | -0.028 |
seven | -0.027 |
Token | were |
Token ID | 547 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
ever | +0.030 |
bye | +0.029 |
red | +0.028 |
seven | +0.026 |
ago | +0.026 |
Neg logit contributions | |
hospital | -0.037 |
slams | -0.034 |
clinic | -0.032 |
mun | -0.031 |
promises | -0.030 |
Token | just |
Token ID | 655 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ever | +0.049 |
bye | +0.045 |
red | +0.044 |
seven | +0.043 |
ago | +0.042 |
Neg logit contributions | |
hospital | -0.057 |
slams | -0.053 |
clinic | -0.049 |
mun | -0.048 |
cleans | -0.047 |
Token | cleaning |
Token ID | 12724 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
hospital | +0.037 |
slams | +0.033 |
clinic | +0.031 |
mun | +0.030 |
promises | +0.029 |
Neg logit contributions | |
ever | -0.034 |
bye | -0.033 |
red | -0.033 |
seven | -0.030 |
ago | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
hospital | +0.219 |
slams | +0.200 |
clinic | +0.184 |
mun | +0.180 |
cleans | +0.173 |
Neg logit contributions | |
ever | -0.199 |
bye | -0.194 |
red | -0.191 |
seven | -0.177 |
ago | -0.176 |
Token | beach |
Token ID | 10481 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ever | +0.023 |
bye | +0.022 |
seven | +0.021 |
ago | +0.021 |
wind | +0.020 |
Neg logit contributions | |
slams | -0.018 |
hospital | -0.018 |
mun | -0.017 |
cleans | -0.015 |
clinic | -0.015 |
Token | ! |
Token ID | 0 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
bye | +0.077 |
ever | +0.077 |
red | +0.076 |
By | +0.070 |
seven | +0.068 |
Neg logit contributions | |
hospital | -0.112 |
slams | -0.102 |
clinic | -0.095 |
mun | -0.092 |
promises | -0.091 |
Token | It |
Token ID | 632 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ever | +0.090 |
bye | +0.088 |
red | +0.085 |
seven | +0.077 |
ago | +0.076 |
Neg logit contributions | |
hospital | -0.154 |
slams | -0.142 |
clinic | -0.132 |
mun | -0.131 |
chores | -0.128 |
Token | is |
Token ID | 318 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ever | +0.050 |
bye | +0.046 |
red | +0.045 |
seven | +0.043 |
By | +0.042 |
Neg logit contributions | |
hospital | -0.041 |
slams | -0.037 |
clinic | -0.035 |
mun | -0.033 |
chores | -0.033 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.005 |
clinic | +0.005 |
promises | +0.005 |
chores | +0.005 |
Neg logit contributions | |
red | -0.005 |
bye | -0.005 |
ever | -0.005 |
ago | -0.004 |
seven | -0.004 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
red | +0.026 |
bye | +0.025 |
ever | +0.025 |
By | +0.023 |
seven | +0.023 |
Neg logit contributions | |
hospital | -0.029 |
slams | -0.026 |
clinic | -0.024 |
promises | -0.023 |
mun | -0.023 |
Token | Sara |
Token ID | 24799 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
ever | +0.221 |
bye | +0.219 |
red | +0.217 |
ago | +0.199 |
seven | +0.196 |
Neg logit contributions | |
hospital | -0.193 |
slams | -0.172 |
clinic | -0.155 |
mun | -0.148 |
promises | -0.145 |
Token | said |
Token ID | 531 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
ever | +0.023 |
red | +0.022 |
bye | +0.022 |
seven | +0.020 |
By | +0.019 |
Neg logit contributions | |
hospital | -0.037 |
slams | -0.034 |
clinic | -0.032 |
chores | -0.032 |
mun | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
hospital | +0.001 |
slams | +0.001 |
clinic | +0.001 |
mun | +0.001 |
promises | +0.001 |
Neg logit contributions | |
ever | -0.001 |
bye | -0.001 |
red | -0.001 |
seven | -0.001 |
ago | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
ever | +0.023 |
bye | +0.022 |
red | +0.022 |
seven | +0.020 |
ago | +0.020 |
Neg logit contributions | |
hospital | -0.027 |
slams | -0.025 |
clinic | -0.023 |
mun | -0.022 |
promises | -0.021 |
Token | did |
Token ID | 750 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
hospital | +0.059 |
slams | +0.054 |
clinic | +0.052 |
chores | +0.051 |
mistakes | +0.051 |
Neg logit contributions | |
ever | -0.035 |
red | -0.033 |
bye | -0.032 |
seven | -0.030 |
By | -0.029 |
Token | not |
Token ID | 407 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ever | +0.028 |
seven | +0.020 |
than | +0.019 |
bye | +0.018 |
By | +0.017 |
Neg logit contributions | |
mun | -0.068 |
hospital | -0.068 |
arre | -0.066 |
clinic | -0.064 |
slams | -0.064 |
Token | want |
Token ID | 765 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
bye | +0.069 |
ever | +0.068 |
red | +0.068 |
ago | +0.062 |
seven | +0.062 |
Neg logit contributions | |
hospital | -0.089 |
slams | -0.081 |
clinic | -0.075 |
mun | -0.073 |
chores | -0.072 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ever | +0.045 |
bye | +0.043 |
red | +0.042 |
seven | +0.038 |
ago | +0.037 |
Neg logit contributions | |
hospital | -0.081 |
slams | -0.076 |
clinic | -0.071 |
mun | -0.070 |
promises | -0.068 |
Token | to |
Token ID | 284 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
ever | +0.022 |
bye | +0.022 |
red | +0.021 |
seven | +0.019 |
ago | +0.019 |
Neg logit contributions | |
hospital | -0.034 |
slams | -0.031 |
clinic | -0.029 |
mun | -0.028 |
promises | -0.028 |
Token | little |
Token ID | 1310 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
hospital | +0.028 |
slams | +0.027 |
mistakes | +0.025 |
cleans | +0.024 |
promises | +0.024 |
Neg logit contributions | |
ever | -0.016 |
bye | -0.016 |
seven | -0.015 |
By | -0.015 |
wind | -0.014 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
hospital | +0.024 |
slams | +0.022 |
clinic | +0.020 |
mun | +0.020 |
chores | +0.020 |
Neg logit contributions | |
ever | -0.019 |
bye | -0.019 |
red | -0.017 |
seven | -0.017 |
ago | -0.016 |
Token | called |
Token ID | 1444 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.019 |
chores | +0.017 |
mun | +0.017 |
clinic | +0.017 |
Neg logit contributions | |
ever | -0.027 |
bye | -0.026 |
red | -0.025 |
ago | -0.024 |
seven | -0.024 |
Token | Lori |
Token ID | 43741 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
hospital | +0.044 |
slams | +0.040 |
clinic | +0.036 |
mun | +0.035 |
cleans | +0.034 |
Neg logit contributions | |
ever | -0.049 |
bye | -0.048 |
red | -0.047 |
seven | -0.044 |
By | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
hospital | +0.193 |
slams | +0.176 |
clinic | +0.163 |
mun | +0.159 |
promises | +0.154 |
Neg logit contributions | |
ever | -0.159 |
bye | -0.155 |
red | -0.152 |
seven | -0.140 |
ago | -0.139 |
Token | She |
Token ID | 1375 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ever | +0.001 |
bye | +0.001 |
red | +0.001 |
seven | +0.001 |
ago | +0.001 |
Neg logit contributions | |
hospital | -0.001 |
slams | -0.001 |
clinic | -0.001 |
mun | -0.001 |
promises | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
hospital | +0.071 |
slams | +0.063 |
mun | +0.057 |
clinic | +0.056 |
cleans | +0.055 |
Neg logit contributions | |
bye | -0.062 |
red | -0.062 |
ever | -0.060 |
ago | -0.059 |
seven | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
ever | +0.004 |
bye | +0.004 |
red | +0.003 |
seven | +0.003 |
ago | +0.003 |
Neg logit contributions | |
hospital | -0.007 |
slams | -0.007 |
clinic | -0.007 |
mun | -0.007 |
promises | -0.006 |
Token | go |
Token ID | 467 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.005 |
mun | +0.005 |
clinic | +0.005 |
mistakes | +0.005 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.005 |
red | -0.005 |
seven | -0.005 |
ago | -0.005 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
hospital | +0.081 |
slams | +0.076 |
mun | +0.071 |
clinic | +0.070 |
mistakes | +0.068 |
Neg logit contributions | |
ever | -0.051 |
bye | -0.048 |
red | -0.044 |
seven | -0.043 |
ago | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
hospital | +0.151 |
slams | +0.140 |
clinic | +0.129 |
mun | +0.127 |
cleans | +0.125 |
Neg logit contributions | |
ever | -0.105 |
bye | -0.098 |
red | -0.096 |
seven | -0.089 |
ago | -0.088 |
Token | they |
Token ID | 484 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
hospital | +0.010 |
slams | +0.009 |
clinic | +0.008 |
mun | +0.008 |
mistakes | +0.008 |
Neg logit contributions | |
ever | -0.009 |
bye | -0.008 |
red | -0.008 |
seven | -0.007 |
ago | -0.007 |
Token | both |
Token ID | 1111 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
hospital | +0.008 |
slams | +0.007 |
clinic | +0.007 |
mun | +0.007 |
chores | +0.006 |
Neg logit contributions | |
ever | -0.006 |
bye | -0.006 |
red | -0.005 |
ago | -0.005 |
seven | -0.005 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
bye | +0.099 |
ever | +0.097 |
red | +0.095 |
By | +0.089 |
ago | +0.088 |
Neg logit contributions | |
hospital | -0.155 |
slams | -0.143 |
clinic | -0.130 |
mun | -0.130 |
cleans | -0.128 |
Token | the |
Token ID | 262 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ever | +0.114 |
bye | +0.110 |
red | +0.108 |
seven | +0.100 |
ago | +0.099 |
Neg logit contributions | |
hospital | -0.138 |
slams | -0.127 |
clinic | -0.117 |
mun | -0.114 |
cleans | -0.110 |
Token | sweet |
Token ID | 6029 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ever | +0.014 |
bye | +0.014 |
red | +0.013 |
seven | +0.012 |
By | +0.012 |
Neg logit contributions | |
hospital | -0.016 |
slams | -0.015 |
clinic | -0.014 |
mun | -0.013 |
cleans | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ever | +0.093 |
bye | +0.092 |
red | +0.090 |
seven | +0.083 |
ago | +0.083 |
Neg logit contributions | |
hospital | -0.092 |
slams | -0.083 |
clinic | -0.076 |
mun | -0.074 |
promises | -0.071 |
Token | juicy |
Token ID | 35075 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
hospital | +0.027 |
slams | +0.025 |
clinic | +0.023 |
mun | +0.022 |
promises | +0.022 |
Neg logit contributions | |
ever | -0.022 |
bye | -0.021 |
red | -0.021 |
seven | -0.019 |
ago | -0.019 |
Token | fruit |
Token ID | 8234 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ever | +0.193 |
bye | +0.190 |
red | +0.187 |
ago | +0.173 |
seven | +0.173 |
Neg logit contributions | |
hospital | -0.181 |
slams | -0.163 |
clinic | -0.148 |
mun | -0.146 |
promises | -0.140 |
Token | together |
Token ID | 1978 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
bye | +0.014 |
red | +0.013 |
ever | +0.013 |
By | +0.012 |
ago | +0.012 |
Neg logit contributions | |
hospital | -0.012 |
slams | -0.011 |
clinic | -0.010 |
mun | -0.009 |
promises | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
hospital | +0.041 |
slams | +0.037 |
clinic | +0.034 |
mun | +0.034 |
promises | +0.033 |
Neg logit contributions | |
bye | -0.039 |
ever | -0.037 |
red | -0.037 |
seven | -0.035 |
By | -0.035 |
Token | |
Token ID | 220 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
hospital | +0.001 |
slams | +0.001 |
mun | +0.001 |
clinic | +0.001 |
chores | +0.001 |
Neg logit contributions | |
bye | -0.001 |
ever | -0.001 |
red | -0.001 |
By | -0.001 |
ago | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
hospital | +0.085 |
slams | +0.078 |
clinic | +0.071 |
chores | +0.069 |
promises | +0.069 |
Neg logit contributions | |
bye | -0.075 |
ever | -0.074 |
red | -0.074 |
By | -0.068 |
ago | -0.066 |
Token | But |
Token ID | 887 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ever | +0.019 |
bye | +0.018 |
red | +0.018 |
seven | +0.016 |
ago | +0.016 |
Neg logit contributions | |
hospital | -0.026 |
slams | -0.024 |
clinic | -0.022 |
mun | -0.022 |
chores | -0.021 |
Token | remember |
Token ID | 3505 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
hospital | +0.112 |
slams | +0.103 |
clinic | +0.096 |
mun | +0.094 |
cleans | +0.091 |
Neg logit contributions | |
ever | -0.077 |
bye | -0.074 |
red | -0.073 |
seven | -0.066 |
ago | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
ever | +0.039 |
bye | +0.037 |
red | +0.035 |
ago | +0.034 |
seven | +0.032 |
Neg logit contributions | |
hospital | -0.068 |
slams | -0.063 |
mun | -0.060 |
clinic | -0.059 |
promises | -0.056 |
Token | always |
Token ID | 1464 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
hospital | +0.007 |
slams | +0.007 |
clinic | +0.006 |
mun | +0.006 |
cleans | +0.006 |
Neg logit contributions | |
ever | -0.005 |
bye | -0.005 |
red | -0.004 |
ago | -0.004 |
seven | -0.004 |
Token | wash |
Token ID | 13502 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ever | +0.105 |
bye | +0.098 |
red | +0.096 |
ago | +0.092 |
seven | +0.091 |
Neg logit contributions | |
hospital | -0.119 |
slams | -0.107 |
clinic | -0.099 |
mun | -0.099 |
cleans | -0.093 |
Token | your |
Token ID | 534 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
hospital | +0.228 |
slams | +0.209 |
clinic | +0.196 |
mun | +0.191 |
cleans | +0.180 |
Neg logit contributions | |
ever | -0.181 |
bye | -0.174 |
red | -0.173 |
seven | -0.161 |
ago | -0.157 |
Token | apples |
Token ID | 22514 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ever | +0.027 |
bye | +0.026 |
red | +0.026 |
seven | +0.023 |
ago | +0.023 |
Neg logit contributions | |
hospital | -0.047 |
slams | -0.044 |
mun | -0.041 |
clinic | -0.041 |
cleans | -0.039 |
Token | before |
Token ID | 878 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
bye | +0.115 |
red | +0.113 |
ever | +0.110 |
By | +0.105 |
seven | +0.102 |
Neg logit contributions | |
hospital | -0.124 |
slams | -0.110 |
clinic | -0.103 |
chores | -0.102 |
promises | -0.100 |
Token | you |
Token ID | 345 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
red | +0.042 |
bye | +0.042 |
ever | +0.041 |
seven | +0.038 |
By | +0.037 |
Neg logit contributions | |
hospital | -0.057 |
slams | -0.050 |
clinic | -0.047 |
chores | -0.047 |
mistakes | -0.046 |
Token | eat |
Token ID | 4483 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
ever | +0.062 |
bye | +0.058 |
red | +0.056 |
seven | +0.052 |
ago | +0.051 |
Neg logit contributions | |
hospital | -0.072 |
slams | -0.067 |
mun | -0.062 |
clinic | -0.061 |
mistakes | -0.058 |
Token | Billy |
Token ID | 15890 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
hospital | +0.176 |
slams | +0.171 |
clinic | +0.165 |
mun | +0.158 |
promises | +0.146 |
Neg logit contributions | |
ever | -0.128 |
bye | -0.107 |
red | -0.106 |
By | -0.096 |
ago | -0.093 |
Token | had |
Token ID | 550 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
hospital | +0.020 |
slams | +0.019 |
clinic | +0.018 |
mun | +0.017 |
mistakes | +0.017 |
Neg logit contributions | |
ever | -0.008 |
red | -0.007 |
bye | -0.007 |
ago | -0.006 |
seven | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
bye | +0.180 |
ever | +0.177 |
red | +0.173 |
seven | +0.163 |
ago | +0.159 |
Neg logit contributions | |
hospital | -0.242 |
slams | -0.221 |
clinic | -0.200 |
mun | -0.200 |
promises | -0.197 |
Token | about |
Token ID | 546 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
hospital | +0.021 |
slams | +0.018 |
chores | +0.017 |
clinic | +0.017 |
cleans | +0.017 |
Neg logit contributions | |
bye | -0.021 |
red | -0.020 |
ever | -0.019 |
seven | -0.019 |
By | -0.018 |
Token | pin |
Token ID | 6757 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
hospital | +0.129 |
slams | +0.123 |
clinic | +0.115 |
mun | +0.112 |
promises | +0.104 |
Neg logit contributions | |
ever | -0.101 |
red | -0.093 |
bye | -0.092 |
ago | -0.085 |
seven | -0.082 |
Token | ching |
Token ID | 10813 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
hospital | +0.119 |
slams | +0.108 |
clinic | +0.101 |
mun | +0.092 |
promises | +0.089 |
Neg logit contributions | |
ever | -0.135 |
red | -0.133 |
bye | -0.127 |
seven | -0.118 |
ago | -0.116 |
Token | the |
Token ID | 262 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
hospital | +0.330 |
slams | +0.302 |
clinic | +0.280 |
mun | +0.270 |
cleans | +0.260 |
Neg logit contributions | |
ever | -0.287 |
bye | -0.279 |
red | -0.276 |
seven | -0.250 |
ago | -0.249 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ever | +0.004 |
bye | +0.004 |
red | +0.004 |
seven | +0.004 |
ago | +0.004 |
Neg logit contributions | |
hospital | -0.004 |
slams | -0.004 |
clinic | -0.004 |
mun | -0.004 |
cleans | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ever | +0.012 |
red | +0.011 |
bye | +0.011 |
ago | +0.010 |
seven | +0.010 |
Neg logit contributions | |
hospital | -0.017 |
slams | -0.016 |
clinic | -0.015 |
mun | -0.014 |
cleans | -0.014 |
Token | but |
Token ID | 475 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
hospital | +0.030 |
slams | +0.028 |
clinic | +0.026 |
mun | +0.025 |
chores | +0.024 |
Neg logit contributions | |
ever | -0.022 |
red | -0.021 |
bye | -0.021 |
ago | -0.019 |
seven | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
hospital | +0.059 |
slams | +0.053 |
clinic | +0.049 |
mun | +0.048 |
promises | +0.048 |
Neg logit contributions | |
bye | -0.041 |
ever | -0.041 |
red | -0.041 |
seven | -0.037 |
ago | -0.037 |
Token | start |
Token ID | 923 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
hospital | +0.070 |
slams | +0.064 |
clinic | +0.062 |
mun | +0.062 |
mistakes | +0.062 |
Neg logit contributions | |
ever | -0.052 |
seven | -0.048 |
bye | -0.047 |
hy | -0.043 |
ago | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
hospital | +0.069 |
slams | +0.065 |
mun | +0.064 |
clinic | +0.063 |
cleans | +0.061 |
Neg logit contributions | |
ever | -0.024 |
bye | -0.019 |
red | -0.018 |
seven | -0.017 |
ago | -0.016 |
Token | whine |
Token ID | 47409 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
hospital | +0.001 |
slams | +0.001 |
clinic | +0.001 |
cleans | +0.001 |
mun | +0.001 |
Neg logit contributions | |
ever | -0.001 |
bye | -0.001 |
wind | -0.001 |
seven | -0.001 |
hy | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
hospital | +0.117 |
slams | +0.104 |
clinic | +0.097 |
mun | +0.093 |
chores | +0.092 |
Neg logit contributions | |
bye | -0.112 |
ever | -0.111 |
red | -0.109 |
seven | -0.101 |
ago | -0.101 |
Token | f |
Token ID | 277 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
hospital | +0.001 |
slams | +0.001 |
clinic | +0.001 |
mun | +0.001 |
cleans | +0.001 |
Neg logit contributions | |
ever | -0.001 |
bye | -0.001 |
red | -0.001 |
ago | -0.001 |
seven | -0.001 |
Token | idget |
Token ID | 17484 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
hospital | +0.191 |
promises | +0.157 |
clinic | +0.155 |
mun | +0.150 |
slams | +0.148 |
Neg logit contributions | |
red | -0.182 |
ever | -0.164 |
bye | -0.161 |
ring | -0.157 |
ago | -0.157 |
Token | and |
Token ID | 290 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
hospital | +0.376 |
slams | +0.343 |
clinic | +0.316 |
mun | +0.311 |
chores | +0.301 |
Neg logit contributions | |
ever | -0.313 |
bye | -0.310 |
red | -0.302 |
seven | -0.278 |
By | -0.278 |
Token | push |
Token ID | 4574 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
hospital | +0.002 |
slams | +0.002 |
clinic | +0.002 |
mun | +0.002 |
promises | +0.002 |
Neg logit contributions | |
ever | -0.002 |
bye | -0.002 |
red | -0.002 |
seven | -0.002 |
ago | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
hospital | +0.089 |
slams | +0.081 |
clinic | +0.079 |
mun | +0.077 |
cleans | +0.072 |
Neg logit contributions | |
ever | -0.058 |
bye | -0.055 |
red | -0.054 |
seven | -0.050 |
than | -0.047 |
Token | other |
Token ID | 584 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ever | +0.017 |
bye | +0.016 |
red | +0.016 |
seven | +0.015 |
ago | +0.015 |
Neg logit contributions | |
hospital | -0.013 |
slams | -0.012 |
clinic | -0.011 |
mun | -0.010 |
cleans | -0.010 |
Token | kids |
Token ID | 3988 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
hospital | +0.131 |
slams | +0.118 |
clinic | +0.107 |
mun | +0.105 |
chores | +0.104 |
Neg logit contributions | |
red | -0.133 |
bye | -0.132 |
ever | -0.132 |
By | -0.122 |
ago | -0.120 |
Token | had |
Token ID | 550 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
hospital | +0.025 |
slams | +0.024 |
clinic | +0.022 |
mun | +0.022 |
promises | +0.021 |
Neg logit contributions | |
ever | -0.014 |
bye | -0.013 |
red | -0.013 |
ago | -0.011 |
seven | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ever | +0.175 |
bye | +0.170 |
red | +0.166 |
seven | +0.152 |
ago | +0.151 |
Neg logit contributions | |
hospital | -0.242 |
slams | -0.223 |
clinic | -0.207 |
mun | -0.203 |
promises | -0.196 |
Token | go |
Token ID | 467 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
mun | +0.011 |
slams | +0.011 |
hospital | +0.011 |
clinic | +0.010 |
arre | +0.010 |
Neg logit contributions | |
ever | -0.009 |
bye | -0.008 |
red | -0.007 |
wind | -0.007 |
ago | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
mun | +0.078 |
slams | +0.077 |
hospital | +0.076 |
cleans | +0.075 |
mistakes | +0.074 |
Neg logit contributions | |
ever | -0.032 |
bye | -0.025 |
ago | -0.021 |
red | -0.020 |
seven | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
mun | +0.015 |
arre | +0.014 |
slams | +0.014 |
uddle | +0.013 |
cleans | +0.013 |
Neg logit contributions | |
ever | -0.007 |
bye | -0.005 |
ago | -0.005 |
wind | -0.005 |
Dad | -0.004 |
Token | hospital |
Token ID | 4436 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
mun | +0.002 |
slams | +0.001 |
cleans | +0.001 |
arre | +0.001 |
promises | +0.001 |
Neg logit contributions | |
bye | -0.004 |
ever | -0.004 |
seven | -0.004 |
wind | -0.004 |
By | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
hospital | +0.432 |
slams | +0.408 |
mun | +0.384 |
clinic | +0.371 |
cleans | +0.370 |
Neg logit contributions | |
ever | -0.294 |
bye | -0.274 |
red | -0.269 |
ago | -0.256 |
seven | -0.240 |
Token | The |
Token ID | 383 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
hospital | +0.006 |
slams | +0.006 |
mun | +0.006 |
clinic | +0.006 |
promises | +0.006 |
Neg logit contributions | |
bye | -0.004 |
ever | -0.004 |
red | -0.003 |
ago | -0.003 |
hy | -0.003 |
Token | doctor |
Token ID | 6253 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
slams | +0.007 |
mun | +0.007 |
arre | +0.007 |
cleans | +0.006 |
promises | +0.006 |
Neg logit contributions | |
ever | -0.016 |
bye | -0.016 |
wind | -0.016 |
By | -0.015 |
seven | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
hospital | +0.355 |
slams | +0.335 |
clinic | +0.310 |
mun | +0.304 |
chores | +0.303 |
Neg logit contributions | |
ever | -0.254 |
bye | -0.236 |
red | -0.235 |
seven | -0.209 |
ago | -0.207 |
Token | he |
Token ID | 339 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
hospital | +0.026 |
slams | +0.024 |
clinic | +0.023 |
mun | +0.023 |
promises | +0.022 |
Neg logit contributions | |
ever | -0.017 |
bye | -0.016 |
red | -0.016 |
ago | -0.015 |
seven | -0.015 |
Token | helped |
Token ID | 4193 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
hospital | +0.073 |
slams | +0.068 |
clinic | +0.063 |
mun | +0.061 |
chores | +0.060 |
Neg logit contributions | |
ever | -0.053 |
red | -0.051 |
bye | -0.050 |
ago | -0.046 |
seven | -0.046 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
slams | +0.119 |
hospital | +0.118 |
mun | +0.108 |
clinic | +0.106 |
arre | +0.103 |
Neg logit contributions | |
ever | -0.078 |
red | -0.070 |
bye | -0.067 |
seven | -0.059 |
ago | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
hospital | +0.186 |
mun | +0.186 |
slams | +0.180 |
mistakes | +0.163 |
conflicts | +0.160 |
Neg logit contributions | |
ever | -0.112 |
red | -0.100 |
ring | -0.095 |
ago | -0.089 |
bye | -0.087 |
Token | use |
Token ID | 779 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
hospital | +0.009 |
slams | +0.009 |
mun | +0.008 |
mistakes | +0.008 |
clinic | +0.008 |
Neg logit contributions | |
ever | -0.008 |
bye | -0.007 |
red | -0.007 |
ago | -0.007 |
seven | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ever | +0.003 |
red | +0.002 |
seven | +0.002 |
ago | +0.002 |
bye | +0.002 |
Neg logit contributions | |
hospital | -0.005 |
slams | -0.005 |
mun | -0.005 |
clinic | -0.005 |
arre | -0.005 |
Token | toilet |
Token ID | 16146 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
ever | +0.022 |
seven | +0.021 |
ago | +0.020 |
wind | +0.020 |
bye | +0.019 |
Neg logit contributions | |
hospital | -0.017 |
slams | -0.017 |
mun | -0.015 |
clinic | -0.015 |
arre | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
hospital | +0.368 |
slams | +0.339 |
mun | +0.320 |
clinic | +0.317 |
cleans | +0.302 |
Neg logit contributions | |
ever | -0.263 |
bye | -0.249 |
red | -0.247 |
seven | -0.228 |
ago | -0.227 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ago | +0.003 |
red | +0.003 |
ever | +0.003 |
seven | +0.003 |
By | +0.003 |
Neg logit contributions | |
hospital | -0.004 |
mun | -0.004 |
slams | -0.004 |
promises | -0.004 |
clinic | -0.004 |
Token | felt |
Token ID | 2936 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
hospital | +0.184 |
slams | +0.168 |
clinic | +0.158 |
chores | +0.155 |
mistakes | +0.154 |
Neg logit contributions | |
ever | -0.128 |
red | -0.122 |
bye | -0.116 |
seven | -0.113 |
By | -0.108 |
Token | better |
Token ID | 1365 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ever | +0.045 |
bye | +0.045 |
red | +0.044 |
seven | +0.040 |
ago | +0.040 |
Neg logit contributions | |
hospital | -0.049 |
slams | -0.045 |
clinic | -0.041 |
mun | -0.040 |
promises | -0.039 |
Token | after |
Token ID | 706 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
hospital | +0.181 |
slams | +0.151 |
clinic | +0.147 |
promises | +0.145 |
mistakes | +0.138 |
Neg logit contributions | |
bye | -0.211 |
red | -0.206 |
seven | -0.196 |
ever | -0.195 |
seventeen | -0.190 |
Token | do |
Token ID | 466 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ever | +0.064 |
bye | +0.062 |
red | +0.060 |
seven | +0.056 |
ago | +0.056 |
Neg logit contributions | |
hospital | -0.065 |
slams | -0.060 |
clinic | -0.056 |
mun | -0.054 |
cleans | -0.051 |
Token | ? |
Token ID | 30 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
hospital | +0.113 |
slams | +0.099 |
clinic | +0.087 |
mun | +0.084 |
chores | +0.084 |
Neg logit contributions | |
bye | -0.160 |
red | -0.159 |
ever | -0.158 |
seven | -0.147 |
By | -0.146 |
Token | You |
Token ID | 921 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
hospital | +0.046 |
slams | +0.041 |
clinic | +0.040 |
mun | +0.040 |
chores | +0.039 |
Neg logit contributions | |
ever | -0.026 |
red | -0.025 |
ago | -0.024 |
bye | -0.024 |
seven | -0.022 |
Token | ruined |
Token ID | 20484 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
hospital | +0.092 |
slams | +0.084 |
clinic | +0.079 |
mun | +0.077 |
promises | +0.074 |
Neg logit contributions | |
ever | -0.071 |
bye | -0.067 |
red | -0.066 |
seven | -0.060 |
ago | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
hospital | +0.048 |
mun | +0.045 |
clinic | +0.045 |
slams | +0.045 |
cleans | +0.040 |
Neg logit contributions | |
ever | -0.021 |
bye | -0.019 |
red | -0.019 |
seven | -0.018 |
wind | -0.017 |
Token | rug |
Token ID | 14477 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
ever | +0.018 |
wind | +0.017 |
seven | +0.016 |
bye | +0.016 |
ago | +0.016 |
Neg logit contributions | |
mun | -0.016 |
slams | -0.016 |
hospital | -0.015 |
clinic | -0.015 |
cleans | -0.014 |
Token | ! |
Token ID | 0 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
hospital | +0.357 |
slams | +0.329 |
clinic | +0.306 |
mun | +0.302 |
promises | +0.291 |
Neg logit contributions | |
ever | -0.251 |
bye | -0.244 |
red | -0.238 |
seven | -0.217 |
ago | -0.216 |
Token | You |
Token ID | 921 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ever | +0.104 |
bye | +0.101 |
red | +0.100 |
ago | +0.094 |
seven | +0.090 |
Neg logit contributions | |
hospital | -0.166 |
slams | -0.151 |
mun | -0.145 |
clinic | -0.144 |
chores | -0.140 |
Token | know |
Token ID | 760 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
hospital | +0.089 |
slams | +0.082 |
clinic | +0.073 |
mun | +0.073 |
cleans | +0.072 |
Neg logit contributions | |
bye | -0.072 |
ever | -0.070 |
red | -0.070 |
seven | -0.065 |
ago | -0.064 |
Token | you |
Token ID | 345 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
hospital | +0.041 |
slams | +0.038 |
clinic | +0.037 |
mun | +0.035 |
promises | +0.033 |
Neg logit contributions | |
ever | -0.030 |
bye | -0.028 |
red | -0.027 |
ago | -0.025 |
seven | -0.025 |
Token | are |
Token ID | 389 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
ever | +0.051 |
bye | +0.049 |
red | +0.048 |
seven | +0.043 |
ago | +0.043 |
Neg logit contributions | |
hospital | -0.077 |
slams | -0.071 |
clinic | -0.066 |
mun | -0.065 |
promises | -0.063 |