Token | cops |
Token ID | 14073 |
Feature activation | +3.10e-03 |
Pos logit contributions | |
fountain | +0.036 |
bucket | +0.026 |
jug | +0.026 |
cup | +0.026 |
bin | +0.026 |
Neg logit contributions | |
ascal | -0.061 |
ita | -0.059 |
umper | -0.058 |
ems | -0.058 |
zo | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ascal | +0.000 |
ita | +0.000 |
ems | +0.000 |
zo | +0.000 |
umper | +0.000 |
Neg logit contributions | |
fountain | -0.000 |
bucket | -0.000 |
jug | -0.000 |
bin | -0.000 |
pitcher | -0.000 |
Token | They |
Token ID | 1119 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ascal | +0.075 |
ita | +0.072 |
umper | +0.070 |
ems | +0.068 |
ities | +0.068 |
Neg logit contributions | |
fountain | -0.059 |
bucket | -0.045 |
jug | -0.045 |
cup | -0.045 |
bin | -0.045 |
Token | take |
Token ID | 1011 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ascal | +0.019 |
ita | +0.019 |
ems | +0.018 |
zo | +0.018 |
umper | +0.018 |
Neg logit contributions | |
fountain | -0.015 |
cup | -0.011 |
tray | -0.011 |
jug | -0.011 |
bucket | -0.011 |
Token | b |
Token ID | 275 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ascal | +0.104 |
ita | +0.104 |
umper | +0.102 |
zo | +0.102 |
ems | +0.099 |
Neg logit contributions | |
fountain | -0.098 |
bucket | -0.077 |
tray | -0.075 |
jug | -0.075 |
pitcher | -0.074 |
Token | unn |
Token ID | 20935 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
ascal | +0.049 |
ita | +0.044 |
ems | +0.040 |
umper | +0.038 |
zo | +0.037 |
Neg logit contributions | |
fountain | -0.195 |
bucket | -0.171 |
cup | -0.169 |
jug | -0.168 |
bin | -0.167 |
Token | ies |
Token ID | 444 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
ascal | +0.192 |
ita | +0.172 |
umper | +0.167 |
ems | +0.159 |
ities | +0.152 |
Neg logit contributions | |
fountain | -0.578 |
bucket | -0.505 |
jug | -0.498 |
tray | -0.498 |
cup | -0.496 |
Token | away |
Token ID | 1497 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
ems | +0.185 |
ita | +0.183 |
ascal | +0.182 |
zo | +0.176 |
umper | +0.175 |
Neg logit contributions | |
fountain | -0.193 |
bin | -0.151 |
jug | -0.149 |
bucket | -0.148 |
pitcher | -0.148 |
Token | ." |
Token ID | 526 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
ascal | +0.033 |
ita | +0.033 |
ems | +0.031 |
umper | +0.031 |
zo | +0.031 |
Neg logit contributions | |
fountain | -0.032 |
bucket | -0.025 |
jug | -0.025 |
tray | -0.025 |
bin | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
fountain | +0.039 |
bucket | +0.029 |
jug | +0.029 |
cup | +0.028 |
tray | +0.028 |
Neg logit contributions | |
ascal | -0.057 |
ita | -0.055 |
umper | -0.053 |
ems | -0.053 |
zo | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
fountain | +0.010 |
bucket | +0.007 |
jug | +0.007 |
tray | +0.007 |
cup | +0.007 |
Neg logit contributions | |
ascal | -0.015 |
ita | -0.014 |
umper | -0.014 |
ems | -0.014 |
ities | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
ascal | +0.024 |
ita | +0.024 |
zo | +0.023 |
ities | +0.021 |
ems | +0.021 |
Neg logit contributions | |
fountain | -0.025 |
jug | -0.020 |
bucket | -0.020 |
tray | -0.020 |
are | -0.020 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
fountain | +0.040 |
tray | +0.031 |
jug | +0.031 |
pitcher | +0.031 |
bucket | +0.030 |
Neg logit contributions | |
ascal | -0.038 |
umper | -0.036 |
ita | -0.036 |
zo | -0.036 |
ities | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
fountain | +0.039 |
bucket | +0.027 |
tray | +0.027 |
jug | +0.026 |
bin | +0.026 |
Neg logit contributions | |
ascal | -0.081 |
ita | -0.079 |
umper | -0.077 |
zo | -0.076 |
ems | -0.076 |
Token | other |
Token ID | 584 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
fountain | +0.004 |
bucket | +0.003 |
cup | +0.003 |
bin | +0.003 |
tray | +0.003 |
Neg logit contributions | |
ascal | -0.004 |
ita | -0.004 |
umper | -0.004 |
ems | -0.004 |
zo | -0.004 |
Token | b |
Token ID | 275 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ascal | +0.038 |
umper | +0.036 |
zo | +0.035 |
ems | +0.034 |
ita | +0.034 |
Neg logit contributions | |
fountain | -0.039 |
bin | -0.034 |
are | -0.034 |
cup | -0.033 |
bucket | -0.033 |
Token | unn |
Token ID | 20935 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
ascal | +0.024 |
ita | +0.022 |
ems | +0.022 |
umper | +0.019 |
matter | +0.019 |
Neg logit contributions | |
fountain | -0.115 |
bucket | -0.102 |
cup | -0.100 |
jug | -0.100 |
bin | -0.099 |
Token | ies |
Token ID | 444 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ascal | +0.208 |
matter | +0.206 |
umper | +0.197 |
ems | +0.195 |
ita | +0.185 |
Neg logit contributions | |
fountain | -0.470 |
bucket | -0.416 |
cup | -0.409 |
jug | -0.404 |
buckets | -0.403 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ascal | +0.181 |
ita | +0.174 |
umper | +0.170 |
zo | +0.167 |
ems | +0.167 |
Neg logit contributions | |
fountain | -0.124 |
tray | -0.093 |
bucket | -0.093 |
jug | -0.091 |
bin | -0.090 |
Token | George |
Token ID | 4502 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
fountain | +0.010 |
tray | +0.008 |
bucket | +0.008 |
jug | +0.007 |
bin | +0.007 |
Neg logit contributions | |
ascal | -0.011 |
ita | -0.011 |
umper | -0.011 |
ems | -0.011 |
ities | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
ascal | +0.109 |
ita | +0.105 |
umper | +0.101 |
ems | +0.100 |
zo | +0.099 |
Neg logit contributions | |
fountain | -0.099 |
bucket | -0.078 |
tray | -0.077 |
jug | -0.076 |
bin | -0.076 |
Token | always |
Token ID | 1464 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
fountain | +0.029 |
bucket | +0.022 |
tray | +0.022 |
jug | +0.022 |
bin | +0.021 |
Neg logit contributions | |
ascal | -0.049 |
ita | -0.047 |
umper | -0.045 |
zo | -0.044 |
iny | -0.043 |
Token | two |
Token ID | 734 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
matter | +0.035 |
ita | +0.034 |
die | +0.032 |
ities | +0.032 |
iny | +0.031 |
Neg logit contributions | |
fountain | -0.033 |
case | -0.029 |
pitcher | -0.024 |
tray | -0.023 |
jug | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
ita | +0.066 |
ascal | +0.061 |
ities | +0.061 |
zo | +0.058 |
matter | +0.057 |
Neg logit contributions | |
fountain | -0.063 |
room | -0.049 |
tray | -0.049 |
ocolate | -0.048 |
jug | -0.047 |
Token | became |
Token ID | 2627 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
ita | +0.036 |
ascal | +0.033 |
zo | +0.033 |
ems | +0.033 |
ities | +0.033 |
Neg logit contributions | |
fountain | -0.028 |
tray | -0.023 |
case | -0.022 |
he | -0.022 |
jug | -0.021 |
Token | two |
Token ID | 734 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ascal | +0.144 |
ita | +0.143 |
die | +0.133 |
ities | +0.133 |
matter | +0.132 |
Neg logit contributions | |
fountain | -0.120 |
he | -0.100 |
case | -0.098 |
room | -0.095 |
rack | -0.094 |
Token | b |
Token ID | 275 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ita | +0.079 |
ascal | +0.076 |
ities | +0.071 |
zo | +0.070 |
itive | +0.069 |
Neg logit contributions | |
fountain | -0.090 |
room | -0.076 |
ocolate | -0.073 |
jug | -0.073 |
tray | -0.072 |
Token | unn |
Token ID | 20935 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
ascal | +0.024 |
ita | +0.021 |
umper | +0.018 |
zo | +0.016 |
ems | +0.015 |
Neg logit contributions | |
fountain | -0.146 |
tray | -0.128 |
bucket | -0.128 |
jug | -0.128 |
bin | -0.128 |
Token | ies |
Token ID | 444 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
ascal | +0.140 |
ita | +0.131 |
zo | +0.107 |
umper | +0.106 |
ems | +0.103 |
Neg logit contributions | |
fountain | -0.593 |
bucket | -0.515 |
tray | -0.515 |
bin | -0.513 |
jug | -0.512 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ita | +0.166 |
ascal | +0.159 |
zo | +0.152 |
itive | +0.147 |
ities | +0.146 |
Neg logit contributions | |
fountain | -0.161 |
soda | -0.128 |
bin | -0.127 |
bucket | -0.127 |
tray | -0.127 |
Token | " |
Token ID | 366 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ascal | +0.017 |
ita | +0.017 |
umper | +0.016 |
Him | +0.016 |
ems | +0.016 |
Neg logit contributions | |
fountain | -0.017 |
bucket | -0.014 |
tray | -0.013 |
jug | -0.013 |
are | -0.013 |
Token | Wow |
Token ID | 22017 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
ascal | +0.066 |
ita | +0.063 |
umper | +0.061 |
ems | +0.060 |
zo | +0.059 |
Neg logit contributions | |
fountain | -0.076 |
bucket | -0.063 |
tray | -0.062 |
jug | -0.061 |
bin | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ita | +0.043 |
ascal | +0.043 |
ems | +0.043 |
umper | +0.040 |
zo | +0.040 |
Neg logit contributions | |
fountain | -0.039 |
bucket | -0.029 |
tray | -0.029 |
cup | -0.029 |
bin | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
ascal | +0.090 |
ita | +0.088 |
ems | +0.083 |
umper | +0.083 |
zo | +0.083 |
Neg logit contributions | |
fountain | -0.086 |
bucket | -0.069 |
tray | -0.067 |
jug | -0.067 |
bin | -0.067 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ascal | +0.031 |
ita | +0.030 |
umper | +0.029 |
ems | +0.029 |
zo | +0.029 |
Neg logit contributions | |
fountain | -0.023 |
bucket | -0.017 |
tray | -0.017 |
jug | -0.017 |
bin | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
ascal | +0.144 |
ita | +0.139 |
umper | +0.134 |
ems | +0.134 |
zo | +0.133 |
Neg logit contributions | |
fountain | -0.124 |
bucket | -0.098 |
tray | -0.096 |
jug | -0.095 |
cup | -0.095 |
Token | not |
Token ID | 407 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ascal | +0.055 |
ita | +0.053 |
umper | +0.051 |
zo | +0.051 |
ems | +0.051 |
Neg logit contributions | |
fountain | -0.041 |
tray | -0.031 |
bucket | -0.031 |
jug | -0.031 |
cup | -0.031 |
Token | take |
Token ID | 1011 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ascal | +0.030 |
ita | +0.029 |
umper | +0.028 |
ems | +0.028 |
ities | +0.027 |
Neg logit contributions | |
fountain | -0.017 |
bucket | -0.012 |
are | -0.012 |
jug | -0.012 |
cup | -0.011 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
ascal | +0.091 |
ita | +0.086 |
umper | +0.082 |
ems | +0.082 |
zo | +0.079 |
Neg logit contributions | |
fountain | -0.103 |
bucket | -0.084 |
bin | -0.084 |
cup | -0.082 |
their | -0.081 |
Token | risks |
Token ID | 7476 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ascal | +0.245 |
ita | +0.226 |
umper | +0.218 |
ems | +0.202 |
zo | +0.196 |
Neg logit contributions | |
fountain | -0.485 |
bucket | -0.415 |
bin | -0.406 |
are | -0.403 |
cup | -0.401 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ascal | +0.189 |
zo | +0.189 |
ems | +0.185 |
ita | +0.182 |
ities | +0.178 |
Neg logit contributions | |
fountain | -0.191 |
bucket | -0.160 |
tray | -0.158 |
jug | -0.158 |
cup | -0.157 |
Token | We |
Token ID | 775 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
ascal | +0.012 |
ita | +0.011 |
umper | +0.011 |
ems | +0.011 |
zo | +0.011 |
Neg logit contributions | |
fountain | -0.008 |
bucket | -0.006 |
jug | -0.006 |
tray | -0.006 |
cup | -0.006 |
Token | should |
Token ID | 815 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
fountain | +0.042 |
tray | +0.035 |
cup | +0.034 |
bucket | +0.034 |
jug | +0.033 |
Neg logit contributions | |
ascal | -0.038 |
ita | -0.036 |
umper | -0.036 |
zo | -0.036 |
ems | -0.035 |
Token | always |
Token ID | 1464 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
ascal | +0.066 |
ita | +0.063 |
umper | +0.061 |
zo | +0.061 |
ems | +0.060 |
Neg logit contributions | |
fountain | -0.070 |
tray | -0.057 |
cup | -0.057 |
bucket | -0.056 |
jug | -0.056 |
Token | with |
Token ID | 351 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
fountain | +0.010 |
tray | +0.008 |
bin | +0.008 |
jug | +0.008 |
Mine | +0.008 |
Neg logit contributions | |
ita | -0.011 |
ascal | -0.010 |
iny | -0.010 |
aware | -0.010 |
zo | -0.010 |
Token | lots |
Token ID | 6041 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
fountain | +0.038 |
tray | +0.030 |
bucket | +0.028 |
bin | +0.028 |
jug | +0.028 |
Neg logit contributions | |
ascal | -0.043 |
umper | -0.041 |
ita | -0.040 |
zo | -0.040 |
emy | -0.038 |
Token | of |
Token ID | 286 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
fountain | +0.035 |
tray | +0.025 |
bucket | +0.025 |
bin | +0.024 |
jug | +0.024 |
Neg logit contributions | |
ascal | -0.064 |
ita | -0.062 |
umper | -0.061 |
zo | -0.060 |
ems | -0.059 |
Token | other |
Token ID | 584 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
fountain | +0.002 |
bucket | +0.002 |
bin | +0.002 |
cup | +0.002 |
jug | +0.002 |
Neg logit contributions | |
ascal | -0.003 |
ita | -0.003 |
ems | -0.003 |
umper | -0.003 |
zo | -0.003 |
Token | b |
Token ID | 275 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ascal | +0.061 |
ems | +0.057 |
umper | +0.056 |
zo | +0.056 |
ita | +0.054 |
Neg logit contributions | |
fountain | -0.046 |
are | -0.041 |
bucket | -0.041 |
jug | -0.039 |
bin | -0.038 |
Token | unn |
Token ID | 20935 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
ascal | +0.026 |
ita | +0.023 |
ems | +0.022 |
umper | +0.020 |
ities | +0.019 |
Neg logit contributions | |
fountain | -0.128 |
bucket | -0.114 |
cup | -0.112 |
jug | -0.111 |
bin | -0.110 |
Token | ies |
Token ID | 444 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
matter | +0.211 |
ascal | +0.208 |
umper | +0.199 |
ems | +0.198 |
ita | +0.192 |
Neg logit contributions | |
fountain | -0.456 |
bucket | -0.407 |
cup | -0.398 |
jug | -0.393 |
buckets | -0.390 |
Token | . |
Token ID | 13 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
ascal | +0.198 |
ita | +0.190 |
umper | +0.186 |
ems | +0.183 |
zo | +0.183 |
Neg logit contributions | |
fountain | -0.125 |
bucket | -0.093 |
tray | -0.092 |
jug | -0.091 |
bin | -0.090 |
Token | One |
Token ID | 1881 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
fountain | +0.017 |
bucket | +0.014 |
jug | +0.013 |
cup | +0.013 |
bin | +0.013 |
Neg logit contributions | |
ascal | -0.028 |
ita | -0.027 |
ache | -0.026 |
ems | -0.026 |
ities | -0.026 |
Token | day |
Token ID | 1110 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ascal | +0.034 |
ita | +0.032 |
umper | +0.031 |
ems | +0.031 |
zo | +0.031 |
Neg logit contributions | |
fountain | -0.030 |
bucket | -0.023 |
tray | -0.023 |
jug | -0.023 |
bin | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
ascal | +0.155 |
ita | +0.151 |
zo | +0.144 |
umper | +0.144 |
ities | +0.143 |
Neg logit contributions | |
fountain | -0.037 |
bucket | -0.024 |
jug | -0.024 |
are | -0.023 |
their | -0.022 |
Token | be |
Token ID | 307 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
fountain | +0.033 |
bucket | +0.025 |
jug | +0.024 |
bin | +0.024 |
tray | +0.024 |
Neg logit contributions | |
ascal | -0.045 |
ita | -0.043 |
umper | -0.042 |
ems | -0.042 |
zo | -0.041 |
Token | prepared |
Token ID | 5597 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ascal | +0.101 |
ita | +0.098 |
umper | +0.095 |
zo | +0.093 |
ems | +0.092 |
Neg logit contributions | |
fountain | -0.080 |
tray | -0.062 |
bucket | -0.061 |
jug | -0.061 |
cup | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ascal | +0.058 |
ita | +0.056 |
ems | +0.054 |
umper | +0.054 |
ities | +0.053 |
Neg logit contributions | |
fountain | -0.058 |
tray | -0.045 |
bucket | -0.045 |
jug | -0.045 |
bin | -0.044 |
Token | not |
Token ID | 407 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
ascal | +0.062 |
ita | +0.060 |
umper | +0.058 |
zo | +0.058 |
ems | +0.058 |
Neg logit contributions | |
fountain | -0.049 |
tray | -0.038 |
bucket | -0.038 |
jug | -0.037 |
cup | -0.037 |
Token | take |
Token ID | 1011 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ascal | +0.030 |
ita | +0.029 |
umper | +0.028 |
ems | +0.028 |
ities | +0.027 |
Neg logit contributions | |
fountain | -0.022 |
bucket | -0.017 |
jug | -0.016 |
bin | -0.016 |
cup | -0.016 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
ascal | +0.077 |
ita | +0.072 |
umper | +0.070 |
ems | +0.069 |
zo | +0.068 |
Neg logit contributions | |
fountain | -0.091 |
bucket | -0.074 |
jug | -0.073 |
tray | -0.073 |
bin | -0.072 |
Token | risks |
Token ID | 7476 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ascal | +0.228 |
ita | +0.207 |
umper | +0.200 |
ems | +0.186 |
zo | +0.182 |
Neg logit contributions | |
fountain | -0.486 |
bucket | -0.418 |
bin | -0.409 |
cup | -0.406 |
tray | -0.406 |
Token | . |
Token ID | 13 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
ascal | +0.186 |
zo | +0.185 |
ems | +0.184 |
ita | +0.183 |
umper | +0.178 |
Neg logit contributions | |
fountain | -0.186 |
tray | -0.153 |
bucket | -0.153 |
jug | -0.151 |
cup | -0.150 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ascal | +0.006 |
ita | +0.006 |
ems | +0.006 |
umper | +0.006 |
zo | +0.006 |
Neg logit contributions | |
fountain | -0.004 |
bucket | -0.003 |
jug | -0.003 |
cup | -0.003 |
bin | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ascal | +0.059 |
umper | +0.056 |
ita | +0.055 |
zo | +0.053 |
ems | +0.052 |
Neg logit contributions | |
fountain | -0.071 |
bucket | -0.059 |
tray | -0.059 |
jug | -0.058 |
bin | -0.056 |
Token | upon |
Token ID | 2402 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
fountain | +0.013 |
tray | +0.011 |
rack | +0.011 |
bin | +0.011 |
bucket | +0.011 |
Neg logit contributions | |
ascal | -0.007 |
ita | -0.007 |
umper | -0.007 |
Him | -0.006 |
zo | -0.006 |
Token | You |
Token ID | 921 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
fountain | +0.033 |
tray | +0.028 |
bucket | +0.027 |
jug | +0.027 |
bin | +0.026 |
Neg logit contributions | |
ascal | -0.027 |
ita | -0.026 |
umper | -0.026 |
ems | -0.026 |
zo | -0.025 |
Token | are |
Token ID | 389 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ascal | +0.059 |
ems | +0.059 |
zo | +0.059 |
umper | +0.058 |
ita | +0.057 |
Neg logit contributions | |
fountain | -0.034 |
tray | -0.026 |
cup | -0.025 |
bucket | -0.024 |
rack | -0.023 |
Token | mean |
Token ID | 1612 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
fountain | +0.072 |
bucket | +0.055 |
jug | +0.054 |
bin | +0.054 |
tray | +0.053 |
Neg logit contributions | |
ascal | -0.102 |
ita | -0.097 |
umper | -0.096 |
ities | -0.092 |
zo | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ascal | +0.161 |
ita | +0.154 |
umper | +0.152 |
ems | +0.148 |
zo | +0.148 |
Neg logit contributions | |
fountain | -0.098 |
bucket | -0.073 |
cup | -0.071 |
tray | -0.071 |
jug | -0.070 |
Token | B |
Token ID | 347 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
ascal | +0.083 |
ita | +0.079 |
umper | +0.078 |
ems | +0.077 |
ities | +0.075 |
Neg logit contributions | |
fountain | -0.088 |
tray | -0.073 |
bucket | -0.072 |
jug | -0.070 |
bin | -0.069 |
Token | unn |
Token ID | 20935 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
ascal | +0.109 |
ita | +0.103 |
ems | +0.101 |
umper | +0.100 |
zo | +0.099 |
Neg logit contributions | |
fountain | -0.150 |
bucket | -0.127 |
jug | -0.125 |
tray | -0.125 |
bin | -0.123 |
Token | ies |
Token ID | 444 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ascal | +0.154 |
ita | +0.138 |
umper | +0.128 |
ems | +0.123 |
zo | +0.120 |
Neg logit contributions | |
fountain | -0.546 |
bucket | -0.476 |
tray | -0.472 |
jug | -0.471 |
bin | -0.469 |
Token | are |
Token ID | 389 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ascal | +0.195 |
ems | +0.191 |
ita | +0.187 |
zo | +0.185 |
umper | +0.184 |
Neg logit contributions | |
fountain | -0.073 |
tray | -0.053 |
cup | -0.052 |
bucket | -0.051 |
jug | -0.047 |
Token | nice |
Token ID | 3621 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
fountain | +0.119 |
bucket | +0.090 |
jug | +0.089 |
tray | +0.088 |
bin | +0.088 |
Neg logit contributions | |
ascal | -0.164 |
ita | -0.158 |
umper | -0.151 |
ems | -0.151 |
zo | -0.150 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ascal | +0.019 |
ita | +0.018 |
ems | +0.018 |
ities | +0.018 |
umper | +0.017 |
Neg logit contributions | |
fountain | -0.016 |
tray | -0.012 |
bucket | -0.012 |
bin | -0.012 |
jug | -0.012 |
Token | they |
Token ID | 484 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ascal | +0.007 |
ems | +0.007 |
ita | +0.007 |
zo | +0.007 |
matter | +0.007 |
Neg logit contributions | |
fountain | -0.007 |
case | -0.005 |
room | -0.005 |
tray | -0.005 |
he | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
ita | +0.008 |
ems | +0.008 |
iny | +0.007 |
zo | +0.007 |
ascal | +0.007 |
Neg logit contributions | |
fountain | -0.009 |
bucket | -0.007 |
pitcher | -0.007 |
jug | -0.007 |
tray | -0.007 |
Token | school |
Token ID | 1524 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ascal | +0.038 |
ita | +0.038 |
umper | +0.036 |
ities | +0.035 |
ems | +0.035 |
Neg logit contributions | |
fountain | -0.028 |
bucket | -0.021 |
jug | -0.021 |
case | -0.021 |
tray | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ita | +0.025 |
ems | +0.025 |
ities | +0.024 |
ascal | +0.024 |
zo | +0.023 |
Neg logit contributions | |
fountain | -0.027 |
bucket | -0.024 |
jug | -0.023 |
pitcher | -0.022 |
bin | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ascal | +0.012 |
ita | +0.012 |
umper | +0.012 |
ems | +0.011 |
zo | +0.011 |
Neg logit contributions | |
fountain | -0.008 |
bucket | -0.006 |
tray | -0.006 |
jug | -0.006 |
bin | -0.006 |
Token | B |
Token ID | 33 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ascal | +0.063 |
ita | +0.060 |
umper | +0.058 |
ems | +0.057 |
zo | +0.056 |
Neg logit contributions | |
fountain | -0.070 |
bucket | -0.057 |
tray | -0.056 |
jug | -0.056 |
bin | -0.055 |
Token | unn |
Token ID | 20935 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
ascal | +0.164 |
ita | +0.153 |
umper | +0.150 |
zo | +0.148 |
ities | +0.145 |
Neg logit contributions | |
fountain | -0.183 |
bucket | -0.149 |
tray | -0.148 |
jug | -0.148 |
cup | -0.147 |
Token | ies |
Token ID | 444 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ascal | +0.162 |
ita | +0.146 |
umper | +0.137 |
zo | +0.130 |
ems | +0.129 |
Neg logit contributions | |
fountain | -0.533 |
bucket | -0.465 |
jug | -0.460 |
tray | -0.458 |
cup | -0.458 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ascal | +0.217 |
ems | +0.216 |
ita | +0.214 |
umper | +0.208 |
zo | +0.206 |
Neg logit contributions | |
fountain | -0.086 |
bucket | -0.060 |
cup | -0.060 |
tray | -0.057 |
jug | -0.056 |
Token | carrots |
Token ID | 34397 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
fountain | +0.051 |
case | +0.042 |
bucket | +0.041 |
block | +0.040 |
room | +0.039 |
Neg logit contributions | |
ascal | -0.055 |
ita | -0.053 |
ems | -0.052 |
Him | -0.051 |
ities | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ems | +0.119 |
ita | +0.119 |
ascal | +0.118 |
zo | +0.113 |
ities | +0.113 |
Neg logit contributions | |
fountain | -0.146 |
bin | -0.118 |
bucket | -0.114 |
room | -0.114 |
jug | -0.113 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ascal | +0.014 |
ita | +0.013 |
umper | +0.013 |
zo | +0.012 |
ems | +0.012 |
Neg logit contributions | |
fountain | -0.015 |
bucket | -0.012 |
jug | -0.012 |
cup | -0.012 |
tray | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
fountain | +0.027 |
cup | +0.020 |
tray | +0.019 |
bucket | +0.019 |
jug | +0.019 |
Neg logit contributions | |
ascal | -0.049 |
ita | -0.047 |
umper | -0.046 |
ems | -0.046 |
zo | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
fountain | +0.020 |
bucket | +0.016 |
jug | +0.015 |
tray | +0.015 |
bin | +0.015 |
Neg logit contributions | |
ascal | -0.024 |
ita | -0.024 |
umper | -0.023 |
ems | -0.022 |
zo | -0.022 |
Token | " |
Token ID | 1 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
fountain | +0.004 |
bucket | +0.003 |
jug | +0.003 |
bin | +0.003 |
tray | +0.003 |
Neg logit contributions | |
ascal | -0.004 |
ita | -0.004 |
ems | -0.004 |
umper | -0.004 |
zo | -0.004 |
Token | We |
Token ID | 1135 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ascal | +0.002 |
ita | +0.002 |
umper | +0.002 |
ems | +0.001 |
zo | +0.001 |
Neg logit contributions | |
fountain | -0.002 |
bucket | -0.001 |
tray | -0.001 |
jug | -0.001 |
bin | -0.001 |
Token | have |
Token ID | 423 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
fountain | +0.005 |
tray | +0.004 |
rack | +0.004 |
soda | +0.003 |
pole | +0.003 |
Neg logit contributions | |
umper | -0.007 |
ems | -0.007 |
ascal | -0.006 |
ita | -0.006 |
matter | -0.006 |
Token | rad |
Token ID | 2511 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
ita | +0.085 |
ascal | +0.085 |
ems | +0.081 |
umper | +0.080 |
ities | +0.080 |
Neg logit contributions | |
fountain | -0.070 |
he | -0.054 |
case | -0.054 |
room | -0.054 |
tray | -0.054 |
Token | ishes |
Token ID | 5614 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
ascal | +0.178 |
ita | +0.170 |
zo | +0.155 |
ems | +0.149 |
umper | +0.147 |
Neg logit contributions | |
fountain | -0.514 |
bucket | -0.455 |
jug | -0.450 |
bin | -0.449 |
cup | -0.444 |
Token | from |
Token ID | 422 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ems | +0.264 |
ascal | +0.263 |
ita | +0.253 |
umper | +0.251 |
Him | +0.249 |
Neg logit contributions | |
fountain | -0.279 |
tray | -0.226 |
bucket | -0.219 |
case | -0.217 |
bin | -0.216 |
Token | our |
Token ID | 674 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ascal | +0.103 |
ita | +0.100 |
Him | +0.100 |
umper | +0.097 |
matter | +0.094 |
Neg logit contributions | |
fountain | -0.080 |
case | -0.065 |
bucket | -0.062 |
tray | -0.060 |
pitcher | -0.059 |
Token | garden |
Token ID | 11376 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ascal | +0.018 |
ita | +0.017 |
Him | +0.017 |
ior | +0.016 |
ities | +0.016 |
Neg logit contributions | |
fountain | -0.016 |
he | -0.014 |
case | -0.013 |
room | -0.013 |
equally | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ita | +0.078 |
ascal | +0.074 |
ems | +0.073 |
ities | +0.071 |
zo | +0.071 |
Neg logit contributions | |
fountain | -0.075 |
bucket | -0.059 |
Mine | -0.059 |
tray | -0.058 |
jug | -0.058 |
Token | was |
Token ID | 373 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
matter | +0.009 |
iny | +0.008 |
ascal | +0.008 |
ita | +0.008 |
die | +0.008 |
Neg logit contributions | |
fountain | -0.014 |
rack | -0.013 |
tray | -0.013 |
pitcher | -0.013 |
banner | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
fountain | +0.010 |
bin | +0.007 |
bucket | +0.007 |
tray | +0.007 |
jug | +0.007 |
Neg logit contributions | |
ascal | -0.014 |
ita | -0.014 |
umper | -0.013 |
Mic | -0.013 |
iny | -0.013 |
Token | family |
Token ID | 1641 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ascal | +0.044 |
ita | +0.042 |
umper | +0.041 |
ems | +0.040 |
zo | +0.040 |
Neg logit contributions | |
fountain | -0.045 |
bucket | -0.036 |
tray | -0.036 |
jug | -0.036 |
bin | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ascal | +0.132 |
ita | +0.127 |
umper | +0.122 |
zo | +0.120 |
iny | +0.115 |
Neg logit contributions | |
fountain | -0.128 |
tray | -0.107 |
bucket | -0.103 |
case | -0.102 |
bin | -0.101 |
Token | b |
Token ID | 275 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ascal | +0.001 |
ita | +0.001 |
ems | +0.001 |
umper | +0.001 |
zo | +0.001 |
Neg logit contributions | |
fountain | -0.001 |
bucket | -0.001 |
tray | -0.001 |
jug | -0.001 |
bin | -0.001 |
Token | unn |
Token ID | 20935 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
ascal | +0.020 |
ita | +0.017 |
umper | +0.014 |
ems | +0.013 |
zo | +0.013 |
Neg logit contributions | |
fountain | -0.136 |
bucket | -0.120 |
tray | -0.120 |
jug | -0.119 |
bin | -0.119 |
Token | ies |
Token ID | 444 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
ascal | +0.176 |
umper | +0.159 |
ita | +0.158 |
ems | +0.154 |
zo | +0.145 |
Neg logit contributions | |
fountain | -0.508 |
bucket | -0.443 |
jug | -0.438 |
cup | -0.435 |
tray | -0.433 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ascal | +0.179 |
ita | +0.172 |
umper | +0.167 |
ems | +0.165 |
zo | +0.164 |
Neg logit contributions | |
fountain | -0.131 |
bucket | -0.100 |
tray | -0.099 |
jug | -0.098 |
bin | -0.097 |
Token | The |
Token ID | 383 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ascal | +0.018 |
ita | +0.017 |
umper | +0.016 |
ems | +0.016 |
zo | +0.016 |
Neg logit contributions | |
fountain | -0.012 |
bucket | -0.009 |
tray | -0.009 |
jug | -0.009 |
bin | -0.008 |
Token | b |
Token ID | 275 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
fountain | +0.014 |
bucket | +0.011 |
tray | +0.011 |
jug | +0.011 |
bin | +0.011 |
Neg logit contributions | |
ascal | -0.016 |
ita | -0.016 |
umper | -0.015 |
ems | -0.015 |
zo | -0.015 |
Token | unn |
Token ID | 20935 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
fountain | +0.061 |
bucket | +0.053 |
jug | +0.053 |
cup | +0.053 |
bin | +0.052 |
Neg logit contributions | |
ascal | -0.014 |
ems | -0.012 |
ita | -0.012 |
zo | -0.012 |
matter | -0.011 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
fountain | +0.002 |
bucket | +0.001 |
cup | +0.001 |
jug | +0.001 |
bin | +0.001 |
Neg logit contributions | |
umper | -0.002 |
ascal | -0.002 |
ems | -0.002 |
ita | -0.001 |
Mic | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
ita | +0.100 |
ascal | +0.100 |
ems | +0.095 |
zo | +0.094 |
umper | +0.093 |
Neg logit contributions | |
fountain | -0.101 |
bucket | -0.081 |
tray | -0.079 |
jug | -0.079 |
bin | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
ascal | +0.051 |
ita | +0.049 |
ems | +0.047 |
umper | +0.047 |
zo | +0.046 |
Neg logit contributions | |
fountain | -0.047 |
tray | -0.038 |
bucket | -0.037 |
jug | -0.037 |
bin | -0.037 |
Token | never |
Token ID | 1239 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
ascal | +0.052 |
ita | +0.051 |
umper | +0.049 |
ems | +0.049 |
zo | +0.048 |
Neg logit contributions | |
fountain | -0.034 |
bucket | -0.026 |
tray | -0.025 |
jug | -0.025 |
cup | -0.025 |
Token | take |
Token ID | 1011 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
fountain | +0.030 |
are | +0.024 |
bucket | +0.021 |
slide | +0.020 |
their | +0.019 |
Neg logit contributions | |
ascal | -0.057 |
ita | -0.053 |
umper | -0.052 |
Him | -0.051 |
ities | -0.051 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
ascal | +0.062 |
ita | +0.058 |
umper | +0.056 |
ems | +0.055 |
zo | +0.054 |
Neg logit contributions | |
fountain | -0.082 |
bucket | -0.068 |
cup | -0.067 |
bin | -0.067 |
tray | -0.066 |
Token | risks |
Token ID | 7476 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ascal | +0.221 |
ita | +0.202 |
umper | +0.193 |
ems | +0.181 |
zo | +0.180 |
Neg logit contributions | |
fountain | -0.478 |
bucket | -0.410 |
bin | -0.402 |
cup | -0.400 |
jug | -0.398 |
Token | . |
Token ID | 13 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ascal | +0.176 |
ems | +0.175 |
zo | +0.173 |
ita | +0.171 |
umper | +0.169 |
Neg logit contributions | |
fountain | -0.192 |
tray | -0.163 |
bucket | -0.160 |
bin | -0.159 |
jug | -0.158 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ascal | +0.026 |
ita | +0.025 |
umper | +0.024 |
ems | +0.024 |
zo | +0.024 |
Neg logit contributions | |
fountain | -0.018 |
bucket | -0.014 |
tray | -0.014 |
jug | -0.014 |
bin | -0.014 |
Token | Once |
Token ID | 7454 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
ascal | +0.077 |
ita | +0.073 |
umper | +0.073 |
zo | +0.070 |
ems | +0.070 |
Neg logit contributions | |
fountain | -0.068 |
bucket | -0.055 |
tray | -0.054 |
jug | -0.053 |
bin | -0.052 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
fountain | +0.002 |
tray | +0.002 |
bucket | +0.002 |
bin | +0.002 |
jug | +0.002 |
Neg logit contributions | |
ascal | -0.001 |
ita | -0.001 |
umper | -0.001 |
ems | -0.001 |
zo | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
fountain | +0.035 |
bucket | +0.026 |
cup | +0.025 |
jug | +0.025 |
bin | +0.025 |
Neg logit contributions | |
ascal | -0.055 |
ita | -0.053 |
umper | -0.051 |
ems | -0.051 |
ities | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
fountain | +0.033 |
bucket | +0.025 |
tray | +0.025 |
jug | +0.025 |
bin | +0.024 |
Neg logit contributions | |
ascal | -0.046 |
ita | -0.044 |
umper | -0.043 |
ems | -0.042 |
zo | -0.042 |
Token | " |
Token ID | 1 |
Feature activation | +5.68e-03 |
Pos logit contributions | |
fountain | +0.018 |
tray | +0.014 |
jug | +0.014 |
bucket | +0.014 |
bin | +0.014 |
Neg logit contributions | |
ascal | -0.019 |
ita | -0.019 |
zo | -0.018 |
umper | -0.018 |
ems | -0.018 |
Token | I |
Token ID | 40 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ascal | +0.000 |
ita | +0.000 |
umper | +0.000 |
zo | +0.000 |
ems | +0.000 |
Neg logit contributions | |
fountain | -0.000 |
bucket | -0.000 |
tray | -0.000 |
jug | -0.000 |
cup | -0.000 |
Token | am |
Token ID | 716 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
ascal | +0.019 |
ita | +0.019 |
ems | +0.019 |
zo | +0.019 |
umper | +0.018 |
Neg logit contributions | |
fountain | -0.015 |
tray | -0.012 |
bucket | -0.012 |
jug | -0.011 |
pitcher | -0.011 |
Token | Owl |
Token ID | 37007 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
ascal | +0.041 |
ita | +0.040 |
umper | +0.038 |
Him | +0.037 |
ems | +0.037 |
Neg logit contributions | |
fountain | -0.032 |
bucket | -0.025 |
jug | -0.024 |
tray | -0.024 |
bin | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ascal | +0.423 |
ita | +0.407 |
umper | +0.397 |
ems | +0.393 |
zo | +0.390 |
Neg logit contributions | |
fountain | -0.259 |
bucket | -0.191 |
tray | -0.186 |
jug | -0.186 |
bin | -0.184 |
Token | I |
Token ID | 314 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ascal | +0.074 |
ita | +0.071 |
umper | +0.068 |
zo | +0.067 |
ities | +0.067 |
Neg logit contributions | |
fountain | -0.046 |
block | -0.034 |
cup | -0.034 |
are | -0.034 |
bin | -0.034 |
Token | live |
Token ID | 2107 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ascal | +0.040 |
zo | +0.040 |
ita | +0.039 |
ems | +0.039 |
umper | +0.037 |
Neg logit contributions | |
fountain | -0.031 |
tray | -0.026 |
pitcher | -0.025 |
jug | -0.024 |
rack | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ascal | +0.068 |
ita | +0.065 |
umper | +0.063 |
ems | +0.063 |
ities | +0.061 |
Neg logit contributions | |
fountain | -0.067 |
jug | -0.052 |
pitcher | -0.052 |
bin | -0.051 |
tray | -0.051 |
Token | this |
Token ID | 428 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ascal | +0.135 |
ita | +0.134 |
umper | +0.133 |
Horse | +0.132 |
iny | +0.129 |
Neg logit contributions | |
fountain | -0.123 |
pitcher | -0.094 |
bucket | -0.093 |
tray | -0.092 |
jug | -0.089 |
Token | more |
Token ID | 517 |
Feature activation | -2.00e-04 |
Pos logit contributions | |
ascal | +0.160 |
ita | +0.152 |
ems | +0.149 |
umper | +0.149 |
zo | +0.147 |
Neg logit contributions | |
fountain | -0.112 |
bucket | -0.086 |
cup | -0.082 |
bin | -0.081 |
jug | -0.081 |
Token | cautious |
Token ID | 21205 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
fountain | +0.000 |
bucket | +0.000 |
their | +0.000 |
high | +0.000 |
equally | +0.000 |
Neg logit contributions | |
ascal | -0.000 |
Him | -0.000 |
umper | -0.000 |
ems | -0.000 |
ities | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
ascal | +0.130 |
ita | +0.124 |
umper | +0.121 |
ems | +0.119 |
zo | +0.118 |
Neg logit contributions | |
fountain | -0.102 |
bucket | -0.079 |
tray | -0.077 |
jug | -0.077 |
cup | -0.077 |
Token | not |
Token ID | 407 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
fountain | +0.026 |
bucket | +0.020 |
bin | +0.019 |
jug | +0.019 |
cup | +0.019 |
Neg logit contributions | |
ascal | -0.036 |
ita | -0.034 |
umper | -0.034 |
ems | -0.033 |
ities | -0.033 |
Token | take |
Token ID | 1011 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
fountain | +0.008 |
bucket | +0.006 |
are | +0.006 |
jug | +0.005 |
cup | +0.005 |
Neg logit contributions | |
ascal | -0.014 |
ita | -0.014 |
umper | -0.013 |
ems | -0.013 |
ities | -0.013 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
ascal | +0.074 |
ita | +0.069 |
ems | +0.067 |
umper | +0.066 |
zo | +0.063 |
Neg logit contributions | |
fountain | -0.079 |
bin | -0.065 |
their | -0.065 |
cup | -0.064 |
bucket | -0.064 |
Token | risks |
Token ID | 7476 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ascal | +0.226 |
ita | +0.203 |
umper | +0.198 |
ems | +0.180 |
zo | +0.178 |
Neg logit contributions | |
fountain | -0.467 |
bucket | -0.401 |
bin | -0.395 |
are | -0.394 |
cup | -0.391 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ascal | +0.186 |
zo | +0.184 |
ems | +0.182 |
ita | +0.180 |
umper | +0.178 |
Neg logit contributions | |
fountain | -0.176 |
tray | -0.145 |
bucket | -0.144 |
jug | -0.142 |
cup | -0.141 |
Token | The |
Token ID | 383 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
fountain | +0.009 |
bucket | +0.007 |
jug | +0.007 |
tray | +0.007 |
cup | +0.007 |
Neg logit contributions | |
ascal | -0.012 |
ita | -0.012 |
umper | -0.011 |
ems | -0.011 |
zo | -0.011 |
Token | memory |
Token ID | 4088 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
fountain | +0.012 |
bucket | +0.009 |
jug | +0.009 |
tray | +0.009 |
cup | +0.009 |
Neg logit contributions | |
ascal | -0.011 |
ita | -0.011 |
umper | -0.010 |
zo | -0.010 |
ems | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
fountain | +0.026 |
tray | +0.021 |
rack | +0.021 |
bucket | +0.020 |
cup | +0.020 |
Neg logit contributions | |
ascal | -0.035 |
ita | -0.034 |
zo | -0.034 |
umper | -0.033 |
ems | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
fountain | +0.074 |
bucket | +0.058 |
pitcher | +0.057 |
tray | +0.057 |
jug | +0.056 |
Neg logit contributions | |
ascal | -0.100 |
ita | -0.099 |
Him | -0.096 |
ities | -0.095 |
umper | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
fountain | +0.058 |
bucket | +0.047 |
jug | +0.046 |
pitcher | +0.045 |
tray | +0.045 |
Neg logit contributions | |
ems | -0.059 |
ita | -0.059 |
ascal | -0.059 |
zo | -0.056 |
ities | -0.056 |
Token | You |
Token ID | 921 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ascal | +0.049 |
ita | +0.047 |
umper | +0.046 |
zo | +0.045 |
ities | +0.044 |
Neg logit contributions | |
fountain | -0.041 |
bucket | -0.032 |
cup | -0.032 |
tray | -0.031 |
jug | -0.031 |
Token | love |
Token ID | 1842 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ascal | +0.037 |
ems | +0.037 |
ita | +0.037 |
umper | +0.036 |
zo | +0.036 |
Neg logit contributions | |
fountain | -0.030 |
tray | -0.023 |
cup | -0.023 |
jug | -0.022 |
bucket | -0.022 |
Token | b |
Token ID | 275 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
fountain | +0.015 |
bucket | +0.011 |
cup | +0.011 |
tray | +0.011 |
jug | +0.011 |
Neg logit contributions | |
ascal | -0.023 |
ita | -0.022 |
umper | -0.022 |
ems | -0.022 |
zo | -0.021 |
Token | unn |
Token ID | 20935 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
ascal | +0.024 |
ita | +0.022 |
ems | +0.020 |
umper | +0.019 |
zo | +0.019 |
Neg logit contributions | |
fountain | -0.104 |
bucket | -0.091 |
cup | -0.091 |
jug | -0.090 |
tray | -0.089 |
Token | ies |
Token ID | 444 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ascal | +0.165 |
ita | +0.152 |
umper | +0.147 |
zo | +0.137 |
ems | +0.136 |
Neg logit contributions | |
fountain | -0.501 |
bucket | -0.435 |
jug | -0.432 |
cup | -0.430 |
tray | -0.429 |
Token | , |
Token ID | 11 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ascal | +0.126 |
ita | +0.123 |
ems | +0.120 |
zo | +0.116 |
ities | +0.114 |
Neg logit contributions | |
fountain | -0.139 |
bucket | -0.117 |
bin | -0.113 |
pitcher | -0.110 |
jug | -0.110 |
Token | right |
Token ID | 826 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
ascal | +0.041 |
ita | +0.039 |
ems | +0.039 |
Him | +0.038 |
matter | +0.038 |
Neg logit contributions | |
fountain | -0.044 |
bucket | -0.036 |
tray | -0.035 |
case | -0.035 |
bin | -0.035 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
fountain | +0.023 |
bucket | +0.016 |
cup | +0.016 |
bin | +0.015 |
jug | +0.015 |
Neg logit contributions | |
ascal | -0.043 |
umper | -0.041 |
ita | -0.041 |
zo | -0.040 |
ems | -0.039 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
fountain | +0.009 |
bucket | +0.006 |
cup | +0.006 |
jug | +0.006 |
bin | +0.006 |
Neg logit contributions | |
ascal | -0.016 |
ita | -0.015 |
umper | -0.015 |
zo | -0.015 |
ems | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
fountain | +0.051 |
equally | +0.040 |
case | +0.040 |
tray | +0.039 |
bucket | +0.038 |
Neg logit contributions | |
ascal | -0.076 |
ita | -0.074 |
umper | -0.071 |
ems | -0.071 |
zo | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
fountain | +0.040 |
tray | +0.033 |
jug | +0.032 |
bucket | +0.032 |
bin | +0.032 |
Neg logit contributions | |
ascal | -0.037 |
ita | -0.037 |
umper | -0.035 |
zo | -0.034 |
emy | -0.033 |
Token | " |
Token ID | 1 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ascal | +0.005 |
ita | +0.005 |
umper | +0.005 |
zo | +0.005 |
Mic | +0.005 |
Neg logit contributions | |
fountain | -0.007 |
jug | -0.006 |
tray | -0.006 |
bucket | -0.006 |
bin | -0.006 |
Token | Hello |
Token ID | 15496 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ascal | +0.009 |
ita | +0.008 |
umper | +0.008 |
ems | +0.008 |
zo | +0.008 |
Neg logit contributions | |
fountain | -0.010 |
bucket | -0.008 |
tray | -0.008 |
jug | -0.008 |
cup | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ascal | +0.160 |
ita | +0.156 |
ems | +0.151 |
umper | +0.149 |
zo | +0.147 |
Neg logit contributions | |
fountain | -0.113 |
bucket | -0.087 |
tray | -0.085 |
jug | -0.084 |
bin | -0.083 |
Token | owl |
Token ID | 39610 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
ascal | +0.113 |
ita | +0.109 |
umper | +0.108 |
ems | +0.107 |
zo | +0.103 |
Neg logit contributions | |
fountain | -0.116 |
bucket | -0.096 |
tray | -0.094 |
buckets | -0.093 |
jug | -0.091 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
ascal | +0.353 |
ita | +0.347 |
ems | +0.331 |
zo | +0.330 |
umper | +0.326 |
Neg logit contributions | |
fountain | -0.303 |
bucket | -0.244 |
tray | -0.238 |
jug | -0.238 |
bin | -0.234 |
Token | she |
Token ID | 673 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
fountain | +0.033 |
tray | +0.026 |
bucket | +0.026 |
jug | +0.026 |
bin | +0.024 |
Neg logit contributions | |
ita | -0.038 |
ascal | -0.038 |
zo | -0.037 |
ems | -0.037 |
umper | -0.037 |
Token | said |
Token ID | 531 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ascal | +0.037 |
ita | +0.036 |
umper | +0.035 |
ems | +0.035 |
zo | +0.035 |
Neg logit contributions | |
fountain | -0.031 |
bucket | -0.024 |
jug | -0.024 |
tray | -0.024 |
bin | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ascal | +0.001 |
ita | +0.001 |
Him | +0.001 |
zo | +0.001 |
ities | +0.001 |
Neg logit contributions | |
fountain | -0.001 |
bucket | -0.001 |
bin | -0.001 |
jug | -0.001 |
tray | -0.001 |
Token | |
Token ID | 220 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ascal | +0.008 |
ita | +0.008 |
umper | +0.007 |
ems | +0.007 |
zo | +0.007 |
Neg logit contributions | |
fountain | -0.007 |
bucket | -0.006 |
tray | -0.006 |
jug | -0.006 |
bin | -0.006 |
Token | did |
Token ID | 750 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ascal | +0.008 |
ita | +0.008 |
umper | +0.008 |
ems | +0.008 |
zo | +0.008 |
Neg logit contributions | |
fountain | -0.008 |
bucket | -0.007 |
tray | -0.007 |
jug | -0.007 |
bin | -0.007 |
Token | something |
Token ID | 1223 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
fountain | +0.102 |
jug | +0.084 |
tray | +0.083 |
bucket | +0.081 |
pitcher | +0.081 |
Neg logit contributions | |
matter | -0.116 |
ita | -0.115 |
ascal | -0.114 |
ems | -0.113 |
melodies | -0.111 |
Token | special |
Token ID | 2041 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
ascal | +0.013 |
ita | +0.013 |
matter | +0.013 |
ems | +0.012 |
zo | +0.012 |
Neg logit contributions | |
fountain | -0.010 |
bucket | -0.008 |
tray | -0.008 |
jug | -0.008 |
room | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
fountain | +0.037 |
bucket | +0.030 |
jug | +0.029 |
tray | +0.028 |
pitcher | +0.028 |
Neg logit contributions | |
ascal | -0.042 |
ita | -0.042 |
ems | -0.042 |
ities | -0.040 |
zo | -0.040 |
Token | On |
Token ID | 1550 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
fountain | +0.028 |
cup | +0.021 |
jug | +0.021 |
bucket | +0.021 |
bin | +0.020 |
Neg logit contributions | |
ascal | -0.048 |
ita | -0.044 |
zo | -0.044 |
ities | -0.044 |
umper | -0.044 |
Token | Wed |
Token ID | 3300 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
ita | +0.021 |
matter | +0.019 |
Horse | +0.019 |
Him | +0.018 |
iny | +0.018 |
Neg logit contributions | |
fountain | -0.024 |
tted | -0.022 |
bucket | -0.021 |
bin | -0.020 |
tray | -0.020 |
Token | nes |
Token ID | 2516 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ascal | +0.364 |
ita | +0.357 |
zo | +0.345 |
ems | +0.342 |
umper | +0.340 |
Neg logit contributions | |
fountain | -0.306 |
bucket | -0.247 |
jug | -0.244 |
cup | -0.243 |
bin | -0.241 |
Token | days |
Token ID | 12545 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
ascal | +0.142 |
ita | +0.141 |
umper | +0.134 |
ems | +0.132 |
zo | +0.131 |
Neg logit contributions | |
fountain | -0.127 |
tray | -0.106 |
jug | -0.099 |
bucket | -0.099 |
bin | -0.098 |
Token | she |
Token ID | 673 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ita | +0.047 |
ascal | +0.046 |
ems | +0.045 |
umper | +0.044 |
Him | +0.043 |
Neg logit contributions | |
fountain | -0.038 |
tray | -0.033 |
bucket | -0.032 |
jug | -0.030 |
bin | -0.030 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ita | +0.055 |
ascal | +0.054 |
zo | +0.052 |
ems | +0.052 |
umper | +0.049 |
Neg logit contributions | |
fountain | -0.087 |
tray | -0.076 |
bucket | -0.073 |
jug | -0.073 |
bin | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
fountain | +0.057 |
bucket | +0.045 |
tray | +0.045 |
jug | +0.044 |
bin | +0.044 |
Neg logit contributions | |
ascal | -0.065 |
ita | -0.062 |
umper | -0.060 |
zo | -0.059 |
ems | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
ascal | +0.136 |
ita | +0.130 |
umper | +0.126 |
ems | +0.125 |
zo | +0.124 |
Neg logit contributions | |
fountain | -0.126 |
bucket | -0.100 |
tray | -0.098 |
jug | -0.098 |
bin | -0.097 |
Token | T |
Token ID | 309 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ascal | +0.025 |
ita | +0.023 |
ities | +0.022 |
die | +0.022 |
umper | +0.022 |
Neg logit contributions | |
fountain | -0.023 |
cup | -0.020 |
their | -0.020 |
are | -0.019 |
jug | -0.019 |
Token | idy |
Token ID | 19325 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ascal | +0.039 |
ita | +0.036 |
umper | +0.035 |
ems | +0.034 |
zo | +0.034 |
Neg logit contributions | |
fountain | -0.054 |
bucket | -0.045 |
tray | -0.044 |
jug | -0.044 |
bin | -0.043 |
Token | were |
Token ID | 547 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ascal | +0.082 |
ita | +0.080 |
umper | +0.077 |
ems | +0.077 |
zo | +0.076 |
Neg logit contributions | |
fountain | -0.075 |
bucket | -0.059 |
tray | -0.059 |
jug | -0.057 |
cup | -0.057 |
Token | in |
Token ID | 287 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
fountain | +0.055 |
bucket | +0.045 |
bin | +0.044 |
tray | +0.044 |
jug | +0.043 |
Neg logit contributions | |
ita | -0.057 |
ascal | -0.056 |
umper | -0.052 |
zo | -0.050 |
aware | -0.050 |
Token | se |
Token ID | 325 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
ita | +0.111 |
matter | +0.109 |
ascal | +0.108 |
ities | +0.103 |
Him | +0.103 |
Neg logit contributions | |
fountain | -0.089 |
bucket | -0.068 |
jug | -0.066 |
bin | -0.065 |
case | -0.064 |
Token | per |
Token ID | 525 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ita | +0.327 |
ascal | +0.317 |
zo | +0.306 |
ems | +0.298 |
umper | +0.296 |
Neg logit contributions | |
fountain | -0.334 |
tray | -0.270 |
bucket | -0.270 |
jug | -0.267 |
bin | -0.255 |
Token | able |
Token ID | 540 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ita | +0.147 |
ascal | +0.138 |
zo | +0.136 |
ems | +0.129 |
umper | +0.126 |
Neg logit contributions | |
fountain | -0.159 |
tray | -0.128 |
bucket | -0.127 |
jug | -0.127 |
bin | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
ita | +0.075 |
ascal | +0.074 |
zo | +0.070 |
ities | +0.070 |
matter | +0.069 |
Neg logit contributions | |
fountain | -0.093 |
tray | -0.076 |
bucket | -0.075 |
jug | -0.074 |
block | -0.073 |
Token | They |
Token ID | 1119 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
ascal | +0.017 |
ita | +0.016 |
ems | +0.016 |
umper | +0.016 |
zo | +0.016 |
Neg logit contributions | |
fountain | -0.013 |
cup | -0.010 |
jug | -0.010 |
bin | -0.010 |
bucket | -0.010 |
Token | would |
Token ID | 561 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
fountain | +0.020 |
tray | +0.016 |
bucket | +0.016 |
cup | +0.015 |
rack | +0.015 |
Neg logit contributions | |
ita | -0.019 |
ascal | -0.019 |
zo | -0.018 |
umper | -0.018 |
ems | -0.018 |
Token | be |
Token ID | 307 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
ascal | +0.032 |
ita | +0.030 |
umper | +0.030 |
ems | +0.029 |
zo | +0.029 |
Neg logit contributions | |
fountain | -0.024 |
tray | -0.019 |
bucket | -0.019 |
jug | -0.019 |
cup | -0.018 |
Token | careful |
Token ID | 8161 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
ascal | +0.153 |
ita | +0.146 |
umper | +0.143 |
ems | +0.141 |
zo | +0.140 |
Neg logit contributions | |
fountain | -0.119 |
bucket | -0.092 |
tray | -0.090 |
jug | -0.089 |
bin | -0.089 |
Token | and |
Token ID | 290 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ascal | +0.059 |
ita | +0.057 |
umper | +0.054 |
ems | +0.054 |
ities | +0.054 |
Neg logit contributions | |
fountain | -0.050 |
bucket | -0.038 |
bin | -0.038 |
tray | -0.038 |
jug | -0.038 |
Token | not |
Token ID | 407 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
fountain | +0.021 |
bucket | +0.016 |
jug | +0.015 |
bin | +0.015 |
cup | +0.015 |
Neg logit contributions | |
ascal | -0.032 |
ita | -0.030 |
umper | -0.030 |
zo | -0.029 |
ems | -0.029 |
Token | take |
Token ID | 1011 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
fountain | +0.010 |
bucket | +0.007 |
are | +0.007 |
block | +0.007 |
jug | +0.007 |
Neg logit contributions | |
ascal | -0.019 |
ita | -0.018 |
umper | -0.017 |
ems | -0.017 |
Him | -0.017 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
ascal | +0.082 |
ita | +0.078 |
umper | +0.076 |
ems | +0.075 |
zo | +0.075 |
Neg logit contributions | |
fountain | -0.061 |
bucket | -0.047 |
bin | -0.046 |
cup | -0.046 |
tray | -0.046 |
Token | risks |
Token ID | 7476 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
ascal | +0.199 |
ita | +0.182 |
umper | +0.174 |
ems | +0.165 |
zo | +0.163 |
Neg logit contributions | |
fountain | -0.469 |
bucket | -0.402 |
tray | -0.396 |
bin | -0.396 |
jug | -0.395 |
Token | . |
Token ID | 13 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ems | +0.167 |
zo | +0.161 |
ascal | +0.161 |
ita | +0.160 |
umper | +0.157 |
Neg logit contributions | |
fountain | -0.178 |
bucket | -0.150 |
tray | -0.147 |
jug | -0.145 |
cup | -0.145 |
Token | The |
Token ID | 383 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
fountain | +0.008 |
cup | +0.006 |
jug | +0.005 |
bucket | +0.005 |
bin | +0.005 |
Neg logit contributions | |
ascal | -0.015 |
ita | -0.014 |
zo | -0.014 |
umper | -0.014 |
ities | -0.014 |
Token | moral |
Token ID | 6573 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
fountain | +0.018 |
bucket | +0.014 |
tray | +0.014 |
jug | +0.014 |
cup | +0.013 |
Neg logit contributions | |
ascal | -0.020 |
ita | -0.019 |
umper | -0.018 |
ems | -0.018 |
ities | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ascal | +0.088 |
ita | +0.085 |
umper | +0.083 |
ems | +0.082 |
zo | +0.082 |
Neg logit contributions | |
fountain | -0.043 |
bucket | -0.030 |
tray | -0.030 |
jug | -0.030 |
bin | -0.029 |
Token | there |
Token ID | 612 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
ascal | +0.036 |
ita | +0.035 |
umper | +0.034 |
ems | +0.033 |
zo | +0.033 |
Neg logit contributions | |
fountain | -0.025 |
tray | -0.019 |
bucket | -0.019 |
bin | -0.018 |
jug | -0.018 |
Token | were |
Token ID | 547 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
iny | +0.002 |
ascal | +0.002 |
matter | +0.002 |
ita | +0.002 |
die | +0.001 |
Neg logit contributions | |
fountain | -0.003 |
rack | -0.002 |
tray | -0.002 |
banner | -0.002 |
pitcher | -0.002 |
Token | two |
Token ID | 734 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
fountain | +0.067 |
tray | +0.054 |
bin | +0.052 |
case | +0.051 |
bucket | +0.051 |
Neg logit contributions | |
ascal | -0.083 |
umper | -0.079 |
ita | -0.078 |
zo | -0.074 |
emy | -0.074 |
Token | little |
Token ID | 1310 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ascal | +0.045 |
ita | +0.043 |
umper | +0.040 |
zo | +0.040 |
ities | +0.039 |
Neg logit contributions | |
fountain | -0.056 |
bucket | -0.046 |
tray | -0.046 |
jug | -0.045 |
bin | -0.045 |
Token | b |
Token ID | 275 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ascal | +0.083 |
ita | +0.078 |
umper | +0.075 |
zo | +0.073 |
ems | +0.073 |
Neg logit contributions | |
fountain | -0.121 |
bucket | -0.100 |
tray | -0.100 |
jug | -0.099 |
bin | -0.098 |
Token | unn |
Token ID | 20935 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
ascal | +0.015 |
ita | +0.013 |
umper | +0.011 |
zo | +0.010 |
ems | +0.010 |
Neg logit contributions | |
fountain | -0.095 |
bucket | -0.084 |
tray | -0.084 |
jug | -0.083 |
bin | -0.083 |
Token | ies |
Token ID | 444 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ascal | +0.166 |
ita | +0.148 |
umper | +0.147 |
ems | +0.145 |
zo | +0.136 |
Neg logit contributions | |
fountain | -0.482 |
bucket | -0.422 |
jug | -0.417 |
cup | -0.415 |
tray | -0.414 |
Token | . |
Token ID | 13 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
ascal | +0.150 |
ita | +0.143 |
umper | +0.139 |
ems | +0.138 |
zo | +0.135 |
Neg logit contributions | |
fountain | -0.143 |
bucket | -0.114 |
jug | -0.112 |
tray | -0.112 |
cup | -0.111 |
Token | They |
Token ID | 1119 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ascal | +0.003 |
ita | +0.003 |
umper | +0.003 |
ems | +0.003 |
zo | +0.003 |
Neg logit contributions | |
fountain | -0.003 |
bucket | -0.002 |
tray | -0.002 |
jug | -0.002 |
bin | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
fountain | +0.024 |
tray | +0.018 |
bucket | +0.018 |
cup | +0.018 |
jug | +0.018 |
Neg logit contributions | |
ascal | -0.030 |
ita | -0.029 |
umper | -0.028 |
zo | -0.028 |
ems | -0.028 |
Token | best |
Token ID | 1266 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
fountain | +0.040 |
bucket | +0.031 |
tray | +0.030 |
rack | +0.030 |
case | +0.029 |
Neg logit contributions | |
ascal | -0.053 |
ita | -0.051 |
umper | -0.048 |
zo | -0.047 |
Horse | -0.046 |
Token | mouse |
Token ID | 10211 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ascal | +0.016 |
ita | +0.015 |
umper | +0.015 |
ems | +0.015 |
zo | +0.015 |
Neg logit contributions | |
fountain | -0.016 |
bucket | -0.013 |
tray | -0.013 |
jug | -0.013 |
cup | -0.013 |
Token | named |
Token ID | 3706 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ascal | +0.042 |
ita | +0.041 |
umper | +0.039 |
zo | +0.039 |
ems | +0.038 |
Neg logit contributions | |
fountain | -0.040 |
tray | -0.032 |
bucket | -0.032 |
jug | -0.032 |
pitcher | -0.030 |
Token | Mickey |
Token ID | 27232 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
fountain | +0.091 |
bucket | +0.073 |
jug | +0.072 |
tray | +0.072 |
bin | +0.072 |
Neg logit contributions | |
ascal | -0.093 |
ita | -0.088 |
ems | -0.085 |
umper | -0.085 |
zo | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ascal | +0.244 |
ita | +0.233 |
ems | +0.230 |
umper | +0.227 |
zo | +0.225 |
Neg logit contributions | |
fountain | -0.104 |
bucket | -0.071 |
cup | -0.071 |
jug | -0.069 |
bin | -0.068 |
Token | " |
Token ID | 366 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
fountain | +0.006 |
bin | +0.005 |
jug | +0.005 |
cup | +0.005 |
bucket | +0.005 |
Neg logit contributions | |
ascal | -0.013 |
ities | -0.012 |
ita | -0.012 |
ems | -0.011 |
zo | -0.011 |
Token | Mic |
Token ID | 25437 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
ascal | +0.065 |
ities | +0.065 |
ita | +0.062 |
ems | +0.061 |
Him | +0.057 |
Neg logit contributions | |
fountain | -0.060 |
Mine | -0.049 |
bin | -0.048 |
jug | -0.047 |
are | -0.045 |
Token | key |
Token ID | 2539 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ascal | +0.279 |
ita | +0.261 |
Him | +0.261 |
ities | +0.260 |
melodies | +0.248 |
Neg logit contributions | |
fountain | -0.328 |
bin | -0.287 |
are | -0.284 |
jug | -0.283 |
equally | -0.266 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ascal | +0.221 |
ita | +0.213 |
umper | +0.207 |
ems | +0.205 |
zo | +0.204 |
Neg logit contributions | |
fountain | -0.136 |
bucket | -0.100 |
tray | -0.098 |
jug | -0.098 |
bin | -0.097 |
Token | help |
Token ID | 1037 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ascal | +0.083 |
ita | +0.079 |
umper | +0.078 |
ems | +0.077 |
zo | +0.075 |
Neg logit contributions | |
fountain | -0.071 |
bucket | -0.056 |
tray | -0.055 |
jug | -0.054 |
cup | -0.054 |
Token | ! |
Token ID | 0 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
ascal | +0.078 |
ita | +0.072 |
ities | +0.071 |
ems | +0.070 |
umper | +0.070 |
Neg logit contributions | |
fountain | -0.075 |
bin | -0.059 |
are | -0.058 |
cup | -0.058 |
jug | -0.058 |
Token | The |
Token ID | 383 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
fountain | +0.003 |
bin | +0.002 |
jug | +0.002 |
cup | +0.002 |
bucket | +0.002 |
Neg logit contributions | |
ascal | -0.005 |
ita | -0.005 |
ities | -0.004 |
zo | -0.004 |
ems | -0.004 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ascal | +0.001 |
ita | +0.001 |
umper | +0.001 |
ems | +0.001 |
ities | +0.001 |
Neg logit contributions | |
fountain | -0.001 |
bucket | -0.000 |
bin | -0.000 |
cup | -0.000 |
jug | -0.000 |
Token | 't |
Token ID | 470 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
fountain | +0.001 |
bucket | +0.001 |
tray | +0.001 |
bin | +0.001 |
jug | +0.001 |
Neg logit contributions | |
ascal | -0.001 |
umper | -0.001 |
zo | -0.001 |
ita | -0.001 |
iny | -0.001 |
Token | understand |
Token ID | 1833 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
fountain | +0.016 |
are | +0.012 |
bucket | +0.011 |
block | +0.011 |
bin | +0.011 |
Neg logit contributions | |
ascal | -0.032 |
ita | -0.030 |
ities | -0.029 |
umper | -0.029 |
ems | -0.029 |
Token | why |
Token ID | 1521 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
ascal | +0.045 |
ita | +0.043 |
umper | +0.041 |
ems | +0.040 |
zo | +0.039 |
Neg logit contributions | |
fountain | -0.077 |
cup | -0.064 |
bucket | -0.064 |
bin | -0.064 |
tray | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ascal | +0.035 |
ita | +0.033 |
umper | +0.032 |
zo | +0.032 |
ems | +0.032 |
Neg logit contributions | |
fountain | -0.028 |
bucket | -0.022 |
tray | -0.022 |
jug | -0.022 |
bin | -0.021 |
Token | stadium |
Token ID | 10308 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
fountain | +0.077 |
jug | +0.068 |
aney | +0.067 |
cup | +0.066 |
room | +0.066 |
Neg logit contributions | |
musician | -0.091 |
warrior | -0.085 |
matter | -0.084 |
tunes | -0.084 |
zo | -0.083 |
Token | was |
Token ID | 373 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
fountain | +0.339 |
bucket | +0.303 |
tray | +0.302 |
pitcher | +0.301 |
buckets | +0.294 |
Neg logit contributions | |
matter | -0.295 |
zo | -0.287 |
ita | -0.263 |
ascal | -0.258 |
ache | -0.255 |
Token | so |
Token ID | 523 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
fountain | +0.120 |
bucket | +0.095 |
tray | +0.094 |
jug | +0.094 |
cup | +0.092 |
Neg logit contributions | |
ascal | -0.121 |
ita | -0.120 |
matter | -0.118 |
zo | -0.115 |
umper | -0.115 |
Token | thin |
Token ID | 7888 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
fountain | +0.030 |
tray | +0.025 |
jug | +0.024 |
bucket | +0.024 |
cup | +0.024 |
Neg logit contributions | |
ascal | -0.024 |
zo | -0.024 |
ita | -0.023 |
matter | -0.023 |
umper | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
fountain | +0.057 |
bucket | +0.046 |
tray | +0.045 |
jug | +0.045 |
bin | +0.044 |
Neg logit contributions | |
ascal | -0.064 |
ita | -0.062 |
umper | -0.060 |
zo | -0.060 |
ems | -0.060 |
Token | why |
Token ID | 1521 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
fountain | +0.082 |
tray | +0.066 |
bucket | +0.064 |
jug | +0.064 |
room | +0.063 |
Neg logit contributions | |
ascal | -0.080 |
zo | -0.077 |
matter | -0.077 |
ita | -0.077 |
umper | -0.075 |
Token | makes |
Token ID | 1838 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ascal | +0.073 |
ita | +0.072 |
ems | +0.071 |
umper | +0.069 |
zo | +0.068 |
Neg logit contributions | |
fountain | -0.065 |
bucket | -0.055 |
jug | -0.054 |
tray | -0.054 |
bin | -0.052 |
Token | v |
Token ID | 410 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
fountain | +0.025 |
tray | +0.021 |
bin | +0.021 |
bucket | +0.020 |
jug | +0.020 |
Neg logit contributions | |
ascal | -0.027 |
ita | -0.026 |
zo | -0.026 |
ems | -0.026 |
melodies | -0.025 |
Token | room |
Token ID | 3823 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
fountain | +0.140 |
bucket | +0.114 |
tray | +0.110 |
bin | +0.108 |
jug | +0.108 |
Neg logit contributions | |
ascal | -0.253 |
umper | -0.235 |
zo | -0.229 |
ems | -0.227 |
ities | -0.226 |
Token | - |
Token ID | 12 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
fountain | +0.300 |
bucket | +0.255 |
jug | +0.248 |
tray | +0.245 |
bin | +0.239 |
Neg logit contributions | |
ascal | -0.304 |
ems | -0.302 |
zo | -0.298 |
ita | -0.295 |
melodies | -0.284 |
Token | v |
Token ID | 85 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
fountain | +0.214 |
tray | +0.192 |
bucket | +0.188 |
jug | +0.188 |
bin | +0.180 |
Neg logit contributions | |
ascal | -0.161 |
zo | -0.158 |
umper | -0.151 |
ita | -0.150 |
please | -0.150 |
Token | room |
Token ID | 3823 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
fountain | +0.072 |
tray | +0.055 |
jug | +0.049 |
bucket | +0.049 |
bin | +0.047 |
Neg logit contributions | |
ascal | -0.169 |
ities | -0.160 |
umper | -0.157 |
ita | -0.157 |
zo | -0.156 |
Token | sounds |
Token ID | 5238 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
fountain | +0.307 |
bucket | +0.259 |
jug | +0.257 |
tray | +0.250 |
bin | +0.245 |
Neg logit contributions | |
zo | -0.314 |
ems | -0.310 |
ascal | -0.309 |
ita | -0.307 |
melodies | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
fountain | +0.082 |
bin | +0.072 |
jug | +0.071 |
bucket | +0.068 |
tray | +0.067 |
Neg logit contributions | |
zo | -0.069 |
ita | -0.066 |
ems | -0.066 |
ascal | -0.065 |
beating | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
fountain | +0.027 |
tray | +0.022 |
bucket | +0.022 |
jug | +0.022 |
bin | +0.021 |
Neg logit contributions | |
ascal | -0.026 |
ita | -0.026 |
ems | -0.025 |
umper | -0.025 |
zo | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
fountain | +0.005 |
bucket | +0.004 |
tray | +0.004 |
jug | +0.004 |
bin | +0.004 |
Neg logit contributions | |
ascal | -0.006 |
ita | -0.005 |
umper | -0.005 |
zo | -0.005 |
iny | -0.005 |
Token | " |
Token ID | 1 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ascal | +0.013 |
ita | +0.012 |
umper | +0.012 |
emy | +0.011 |
zo | +0.011 |
Neg logit contributions | |
fountain | -0.017 |
jug | -0.015 |
tray | -0.014 |
bucket | -0.014 |
bin | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ita | +0.050 |
ascal | +0.046 |
ems | +0.045 |
matter | +0.045 |
Him | +0.044 |
Neg logit contributions | |
fountain | -0.059 |
bin | -0.048 |
jug | -0.048 |
bucket | -0.048 |
tray | -0.047 |
Token | check |
Token ID | 2198 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
matter | +0.011 |
ita | +0.011 |
Him | +0.011 |
zo | +0.011 |
melodies | +0.011 |
Neg logit contributions | |
fountain | -0.013 |
jug | -0.011 |
pitcher | -0.011 |
tray | -0.011 |
cup | -0.011 |
Token | if |
Token ID | 611 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
ascal | +0.136 |
ita | +0.133 |
ems | +0.133 |
umper | +0.130 |
ities | +0.127 |
Neg logit contributions | |
fountain | -0.108 |
bucket | -0.082 |
tray | -0.081 |
jug | -0.081 |
bin | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
fountain | +0.035 |
tray | +0.029 |
bucket | +0.028 |
block | +0.027 |
jug | +0.027 |
Neg logit contributions | |
ascal | -0.046 |
ita | -0.046 |
ems | -0.044 |
Him | -0.044 |
umper | -0.043 |
Token | new |
Token ID | 649 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
fountain | +0.040 |
jug | +0.035 |
bin | +0.033 |
cup | +0.032 |
ho | +0.032 |
Neg logit contributions | |
matter | -0.039 |
musician | -0.038 |
melodies | -0.038 |
tunes | -0.038 |
warrior | -0.037 |
Token | stadium |
Token ID | 10308 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
fountain | +0.129 |
jug | +0.112 |
bin | +0.105 |
pitcher | +0.104 |
� | +0.102 |
Neg logit contributions | |
ita | -0.139 |
tunes | -0.136 |
melodies | -0.134 |
matter | -0.133 |
musician | -0.130 |
Token | was |
Token ID | 373 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
fountain | +0.331 |
pitcher | +0.292 |
bucket | +0.291 |
tray | +0.286 |
cup | +0.285 |
Neg logit contributions | |
matter | -0.254 |
ems | -0.252 |
ita | -0.251 |
zo | -0.244 |
ascal | -0.223 |
Token | finished |
Token ID | 5201 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
fountain | +0.092 |
jug | +0.072 |
bin | +0.072 |
tray | +0.071 |
bucket | +0.070 |
Neg logit contributions | |
ita | -0.098 |
ascal | -0.098 |
matter | -0.095 |
zo | -0.094 |
beating | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
fountain | +0.041 |
tray | +0.032 |
bin | +0.032 |
bucket | +0.032 |
jug | +0.032 |
Neg logit contributions | |
ita | -0.041 |
ascal | -0.040 |
ities | -0.039 |
ems | -0.038 |
zo | -0.037 |
Token | but |
Token ID | 475 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ita | +0.007 |
ascal | +0.007 |
ems | +0.007 |
ities | +0.006 |
Him | +0.006 |
Neg logit contributions | |
fountain | -0.009 |
tray | -0.008 |
bin | -0.008 |
jug | -0.008 |
bucket | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ita | +0.087 |
ascal | +0.084 |
matter | +0.083 |
ems | +0.082 |
Him | +0.082 |
Neg logit contributions | |
fountain | -0.075 |
tray | -0.063 |
bucket | -0.060 |
block | -0.059 |
room | -0.059 |
Token | it |
Token ID | 340 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ascal | +0.030 |
ita | +0.030 |
zo | +0.029 |
Him | +0.029 |
melodies | +0.029 |
Neg logit contributions | |
fountain | -0.027 |
jug | -0.022 |
bin | -0.021 |
bucket | -0.021 |
tray | -0.021 |
Token | go |
Token ID | 467 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
fountain | +0.008 |
bin | +0.007 |
tray | +0.007 |
jug | +0.007 |
room | +0.006 |
Neg logit contributions | |
matter | -0.008 |
zo | -0.008 |
ita | -0.007 |
beating | -0.007 |
ems | -0.007 |
Token | v |
Token ID | 410 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
fountain | +0.102 |
tray | +0.082 |
jug | +0.080 |
bucket | +0.079 |
bin | +0.077 |
Neg logit contributions | |
zo | -0.105 |
matter | -0.101 |
umper | -0.100 |
ita | -0.099 |
ascal | -0.098 |
Token | room |
Token ID | 3823 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
fountain | +0.087 |
bucket | +0.070 |
bin | +0.068 |
tray | +0.067 |
jug | +0.067 |
Neg logit contributions | |
ascal | -0.179 |
umper | -0.169 |
zo | -0.161 |
ities | -0.160 |
rows | -0.157 |
Token | v |
Token ID | 410 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
fountain | +0.285 |
bucket | +0.244 |
jug | +0.238 |
bin | +0.229 |
tray | +0.228 |
Neg logit contributions | |
zo | -0.252 |
ems | -0.249 |
ascal | -0.246 |
ita | -0.243 |
ache | -0.237 |
Token | room |
Token ID | 3823 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
fountain | +0.124 |
bucket | +0.101 |
tray | +0.096 |
bin | +0.095 |
jug | +0.095 |
Neg logit contributions | |
ascal | -0.254 |
umper | -0.239 |
zo | -0.229 |
ities | -0.226 |
rows | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
fountain | +0.322 |
bucket | +0.278 |
jug | +0.269 |
tray | +0.256 |
bin | +0.256 |
Neg logit contributions | |
ems | -0.292 |
zo | -0.292 |
ascal | -0.283 |
ita | -0.281 |
tunes | -0.274 |
Token | When |
Token ID | 1649 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
fountain | +0.023 |
tray | +0.019 |
bucket | +0.019 |
jug | +0.018 |
bin | +0.018 |
Neg logit contributions | |
ascal | -0.024 |
ita | -0.023 |
umper | -0.023 |
ems | -0.022 |
zo | -0.022 |
Token | they |
Token ID | 484 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
fountain | +0.010 |
tray | +0.008 |
equally | +0.008 |
tted | +0.008 |
aney | +0.008 |
Neg logit contributions | |
matter | -0.010 |
Horse | -0.010 |
ems | -0.010 |
zo | -0.010 |
Him | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
fountain | +0.075 |
tray | +0.069 |
equally | +0.066 |
soda | +0.065 |
rack | +0.064 |
Neg logit contributions | |
umper | -0.063 |
ems | -0.059 |
matter | -0.056 |
ascal | -0.055 |
zo | -0.054 |
Token | done |
Token ID | 1760 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
fountain | +0.122 |
jug | +0.103 |
bin | +0.102 |
tray | +0.100 |
bucket | +0.098 |
Neg logit contributions | |
ascal | -0.104 |
ita | -0.099 |
umper | -0.094 |
ems | -0.091 |
ities | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
fountain | +0.123 |
bin | +0.099 |
pitcher | +0.097 |
jug | +0.097 |
bucket | +0.097 |
Neg logit contributions | |
ita | -0.110 |
ems | -0.108 |
ities | -0.104 |
ascal | -0.104 |
Him | -0.102 |
Token | make |
Token ID | 787 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
fountain | +0.009 |
tray | +0.007 |
jug | +0.007 |
bin | +0.007 |
bucket | +0.007 |
Neg logit contributions | |
ems | -0.008 |
ita | -0.008 |
ascal | -0.008 |
zo | -0.007 |
Him | -0.007 |
Token | v |
Token ID | 410 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Him | +0.038 |
ita | +0.038 |
ascal | +0.038 |
melodies | +0.037 |
zo | +0.036 |
Neg logit contributions | |
fountain | -0.036 |
� | -0.030 |
jug | -0.030 |
bin | -0.029 |
bucket | -0.029 |
Token | room |
Token ID | 3823 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
fountain | +0.086 |
bucket | +0.070 |
bin | +0.066 |
jug | +0.066 |
tray | +0.062 |
Neg logit contributions | |
ascal | -0.182 |
umper | -0.165 |
ities | -0.163 |
iddles | -0.162 |
ita | -0.162 |
Token | v |
Token ID | 410 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
fountain | +0.239 |
bucket | +0.203 |
jug | +0.198 |
tray | +0.189 |
bin | +0.188 |
Neg logit contributions | |
ascal | -0.261 |
zo | -0.258 |
ita | -0.257 |
ems | -0.255 |
melodies | -0.253 |
Token | room |
Token ID | 3823 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
fountain | +0.132 |
bucket | +0.110 |
jug | +0.104 |
bin | +0.103 |
tray | +0.099 |
Neg logit contributions | |
ascal | -0.253 |
umper | -0.231 |
zo | -0.226 |
ities | -0.226 |
rows | -0.224 |
Token | noises |
Token ID | 26782 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
fountain | +0.308 |
bucket | +0.268 |
jug | +0.261 |
bin | +0.245 |
tray | +0.240 |
Neg logit contributions | |
zo | -0.299 |
ems | -0.297 |
ita | -0.294 |
ascal | -0.293 |
melodies | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
fountain | +0.089 |
jug | +0.077 |
bucket | +0.076 |
bin | +0.074 |
pitcher | +0.071 |
Neg logit contributions | |
zo | -0.073 |
ems | -0.071 |
ita | -0.069 |
ities | -0.068 |
ascal | -0.067 |
Token | |
Token ID | 220 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
fountain | +0.021 |
tray | +0.018 |
bucket | +0.018 |
jug | +0.017 |
bin | +0.017 |
Neg logit contributions | |
ascal | -0.020 |
ita | -0.020 |
umper | -0.019 |
ems | -0.019 |
zo | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
ascal | +0.055 |
umper | +0.053 |
ita | +0.052 |
ems | +0.051 |
zo | +0.050 |
Neg logit contributions | |
fountain | -0.058 |
bucket | -0.046 |
jug | -0.046 |
tray | -0.046 |
bin | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
fountain | +0.005 |
tray | +0.004 |
bucket | +0.004 |
jug | +0.004 |
bin | +0.004 |
Neg logit contributions | |
ascal | -0.005 |
ita | -0.005 |
umper | -0.005 |
iny | -0.005 |
zo | -0.005 |
Token | delicious |
Token ID | 12625 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
fountain | +0.017 |
tray | +0.013 |
bucket | +0.013 |
jug | +0.012 |
bin | +0.012 |
Neg logit contributions | |
ascal | -0.022 |
ita | -0.022 |
zo | -0.020 |
umper | -0.020 |
ems | -0.020 |
Token | smell |
Token ID | 8508 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
fountain | +0.041 |
bucket | +0.030 |
tray | +0.029 |
jug | +0.029 |
bin | +0.029 |
Neg logit contributions | |
ascal | -0.066 |
ita | -0.064 |
umper | -0.062 |
ems | -0.061 |
zo | -0.061 |
Token | coming |
Token ID | 2406 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
fountain | +0.016 |
bucket | +0.014 |
buckets | +0.014 |
jug | +0.013 |
tray | +0.013 |
Neg logit contributions | |
ita | -0.014 |
ascal | -0.014 |
ache | -0.014 |
ems | -0.013 |
ities | -0.013 |
Token | from |
Token ID | 422 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
fountain | +0.058 |
� | +0.051 |
case | +0.050 |
bucket | +0.049 |
pitcher | +0.048 |
Neg logit contributions | |
ita | -0.026 |
iny | -0.024 |
owl | -0.024 |
ascal | -0.022 |
umper | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
fountain | +0.020 |
case | +0.016 |
room | +0.015 |
tray | +0.015 |
pitcher | +0.015 |
Neg logit contributions | |
ascal | -0.026 |
ita | -0.026 |
umper | -0.026 |
matter | -0.025 |
Him | -0.025 |
Token | concession |
Token ID | 33130 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
ascal | +0.048 |
ita | +0.046 |
ities | +0.045 |
umper | +0.044 |
matter | +0.044 |
Neg logit contributions | |
fountain | -0.036 |
equally | -0.031 |
their | -0.030 |
tray | -0.030 |
room | -0.030 |
Token | stand |
Token ID | 1302 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
fountain | +0.244 |
jug | +0.208 |
bucket | +0.204 |
buckets | +0.204 |
room | +0.199 |
Neg logit contributions | |
ascal | -0.333 |
ita | -0.312 |
ems | -0.311 |
ache | -0.308 |
zo | -0.304 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
fountain | +0.027 |
Mine | +0.024 |
jug | +0.023 |
bucket | +0.023 |
bin | +0.022 |
Neg logit contributions | |
ita | -0.023 |
zo | -0.022 |
ascal | -0.021 |
iny | -0.021 |
ems | -0.021 |
Token | She |
Token ID | 1375 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
fountain | +0.012 |
cup | +0.009 |
bucket | +0.009 |
jug | +0.008 |
bin | +0.008 |
Neg logit contributions | |
ascal | -0.020 |
ita | -0.019 |
umper | -0.019 |
zo | -0.019 |
ems | -0.019 |
Token | followed |
Token ID | 3940 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
ascal | +0.038 |
umper | +0.036 |
ems | +0.036 |
ities | +0.035 |
ita | +0.035 |
Neg logit contributions | |
fountain | -0.030 |
bucket | -0.024 |
cup | -0.024 |
bin | -0.023 |
jug | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
ascal | +0.061 |
ita | +0.059 |
umper | +0.057 |
ems | +0.057 |
zo | +0.057 |
Neg logit contributions | |
fountain | -0.028 |
bucket | -0.019 |
tray | -0.019 |
jug | -0.019 |
cup | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
fountain | +0.023 |
tray | +0.019 |
bucket | +0.019 |
frame | +0.019 |
jug | +0.018 |
Neg logit contributions | |
ascal | -0.023 |
ita | -0.022 |
emy | -0.021 |
ior | -0.021 |
die | -0.020 |
Token | both |
Token ID | 1111 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
fountain | +0.064 |
tray | +0.056 |
pitcher | +0.053 |
soda | +0.053 |
rack | +0.052 |
Neg logit contributions | |
zo | -0.053 |
ita | -0.052 |
ascal | -0.052 |
umper | -0.050 |
ems | -0.049 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
fountain | +0.041 |
tray | +0.037 |
jug | +0.035 |
pitcher | +0.035 |
bin | +0.034 |
Neg logit contributions | |
ita | -0.026 |
zo | -0.026 |
ascal | -0.025 |
ems | -0.023 |
umper | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
fountain | +0.005 |
tray | +0.004 |
bucket | +0.003 |
pitcher | +0.003 |
jug | +0.003 |
Neg logit contributions | |
ascal | -0.008 |
ita | -0.008 |
Him | -0.007 |
zo | -0.007 |
ities | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
fountain | +0.053 |
tray | +0.042 |
bucket | +0.041 |
pitcher | +0.040 |
case | +0.040 |
Neg logit contributions | |
ascal | -0.075 |
ita | -0.075 |
matter | -0.074 |
Him | -0.074 |
ities | -0.073 |
Token | pretend |
Token ID | 16614 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
fountain | +0.048 |
pitcher | +0.038 |
jug | +0.037 |
tray | +0.037 |
bucket | +0.037 |
Neg logit contributions | |
ascal | -0.049 |
ita | -0.045 |
zo | -0.045 |
matter | -0.044 |
ities | -0.044 |
Token | play |
Token ID | 711 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
fountain | +0.285 |
pitcher | +0.239 |
tray | +0.231 |
jug | +0.229 |
bucket | +0.227 |
Neg logit contributions | |
zo | -0.295 |
ascal | -0.289 |
ita | -0.282 |
matter | -0.270 |
Him | -0.269 |
Token | was |
Token ID | 373 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
fountain | +0.204 |
pitcher | +0.189 |
Megan | +0.179 |
jug | +0.178 |
aney | +0.177 |
Neg logit contributions | |
zo | -0.190 |
matter | -0.185 |
tunes | -0.181 |
iny | -0.177 |
melodies | -0.170 |
Token | over |
Token ID | 625 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
fountain | +0.117 |
tray | +0.092 |
jug | +0.092 |
bucket | +0.091 |
pitcher | +0.091 |
Neg logit contributions | |
ita | -0.129 |
ascal | -0.129 |
matter | -0.128 |
zo | -0.126 |
ities | -0.122 |
Token | with |
Token ID | 351 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
fountain | +0.038 |
tray | +0.032 |
case | +0.032 |
pitcher | +0.030 |
jug | +0.030 |
Neg logit contributions | |
ascal | -0.042 |
ita | -0.041 |
ities | -0.039 |
zo | -0.038 |
Him | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
fountain | +0.082 |
pitcher | +0.076 |
case | +0.074 |
he | +0.067 |
tray | +0.066 |
Neg logit contributions | |
Him | -0.103 |
matter | -0.098 |
ities | -0.097 |
Horse | -0.096 |
unnecessary | -0.096 |
Token | she |
Token ID | 673 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ita | +0.039 |
though | +0.039 |
ascal | +0.039 |
umper | +0.037 |
Him | +0.036 |
Neg logit contributions | |
fountain | -0.051 |
bin | -0.046 |
tray | -0.045 |
case | -0.042 |
tted | -0.041 |
Token | jumped |
Token ID | 11687 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ascal | +0.012 |
ita | +0.012 |
umper | +0.012 |
ems | +0.011 |
zo | +0.011 |
Neg logit contributions | |
fountain | -0.011 |
bucket | -0.008 |
jug | -0.008 |
tray | -0.008 |
cup | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
fountain | +0.089 |
tray | +0.074 |
bucket | +0.072 |
bin | +0.071 |
jug | +0.071 |
Neg logit contributions | |
ascal | -0.075 |
umper | -0.074 |
ita | -0.072 |
ems | -0.072 |
zo | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
fountain | +0.002 |
tray | +0.002 |
case | +0.002 |
bin | +0.002 |
bucket | +0.002 |
Neg logit contributions | |
ita | -0.002 |
ascal | -0.002 |
ems | -0.002 |
Him | -0.002 |
umper | -0.002 |
Token | tr |
Token ID | 491 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ascal | +0.015 |
ita | +0.014 |
umper | +0.014 |
ems | +0.014 |
zo | +0.014 |
Neg logit contributions | |
fountain | -0.014 |
bucket | -0.011 |
tray | -0.010 |
jug | -0.010 |
bin | -0.010 |
Token | amp |
Token ID | 696 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
fountain | +0.082 |
tray | +0.061 |
bucket | +0.061 |
jug | +0.059 |
bin | +0.059 |
Neg logit contributions | |
ascal | -0.143 |
ita | -0.134 |
umper | -0.134 |
zo | -0.129 |
ems | -0.128 |
Token | oline |
Token ID | 14453 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
fountain | +0.384 |
bucket | +0.332 |
jug | +0.328 |
tray | +0.322 |
bin | +0.322 |
Neg logit contributions | |
ascal | -0.219 |
ita | -0.210 |
ems | -0.203 |
zo | -0.202 |
umper | -0.196 |
Token | made |
Token ID | 925 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
fountain | +0.115 |
tray | +0.104 |
jug | +0.103 |
bucket | +0.100 |
bin | +0.098 |
Neg logit contributions | |
zo | -0.081 |
ita | -0.080 |
ems | -0.074 |
ascal | -0.073 |
beating | -0.072 |
Token | a |
Token ID | 257 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
fountain | +0.034 |
bin | +0.029 |
jug | +0.027 |
tray | +0.026 |
bucket | +0.026 |
Neg logit contributions | |
ita | -0.036 |
melodies | -0.034 |
Him | -0.034 |
ascal | -0.033 |
zo | -0.033 |
Token | loud |
Token ID | 7812 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
fountain | +0.001 |
jug | +0.001 |
bin | +0.001 |
room | +0.001 |
tray | +0.001 |
Neg logit contributions | |
ita | -0.001 |
ascal | -0.001 |
matter | -0.001 |
zo | -0.001 |
melodies | -0.001 |
Token | sound |
Token ID | 2128 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
fountain | +0.114 |
bucket | +0.097 |
jug | +0.096 |
tray | +0.094 |
bin | +0.094 |
Neg logit contributions | |
ascal | -0.080 |
ita | -0.079 |
zo | -0.077 |
ems | -0.073 |
melodies | -0.073 |
Token | made |
Token ID | 925 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
fountain | +0.014 |
tray | +0.012 |
cup | +0.012 |
jug | +0.011 |
pitcher | +0.011 |
Neg logit contributions | |
zo | -0.013 |
ems | -0.013 |
ita | -0.012 |
ascal | -0.011 |
umper | -0.011 |
Token | v |
Token ID | 410 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
ascal | +0.028 |
melodies | +0.028 |
Him | +0.027 |
zo | +0.027 |
ita | +0.027 |
Neg logit contributions | |
fountain | -0.025 |
case | -0.022 |
jug | -0.021 |
� | -0.021 |
bin | -0.020 |
Token | room |
Token ID | 3823 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
fountain | +0.094 |
bucket | +0.079 |
tray | +0.077 |
jug | +0.076 |
bin | +0.075 |
Neg logit contributions | |
ascal | -0.157 |
umper | -0.143 |
rows | -0.141 |
zo | -0.141 |
ities | -0.138 |
Token | - |
Token ID | 12 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
fountain | +0.241 |
bucket | +0.209 |
jug | +0.204 |
tray | +0.198 |
bin | +0.193 |
Neg logit contributions | |
zo | -0.259 |
ems | -0.249 |
ascal | -0.248 |
melodies | -0.248 |
beating | -0.247 |
Token | v |
Token ID | 85 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
fountain | +0.171 |
tray | +0.152 |
bucket | +0.149 |
jug | +0.149 |
bin | +0.142 |
Neg logit contributions | |
zo | -0.134 |
ascal | -0.132 |
umper | -0.125 |
ita | -0.124 |
please | -0.124 |
Token | room |
Token ID | 3823 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
fountain | +0.054 |
tray | +0.041 |
jug | +0.037 |
bucket | +0.037 |
bin | +0.035 |
Neg logit contributions | |
ascal | -0.122 |
ities | -0.118 |
umper | -0.113 |
zo | -0.113 |
iny | -0.113 |
Token | noises |
Token ID | 26782 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
fountain | +0.285 |
jug | +0.250 |
bucket | +0.248 |
tray | +0.235 |
bin | +0.233 |
Neg logit contributions | |
zo | -0.286 |
beating | -0.273 |
tunes | -0.271 |
melodies | -0.271 |
ems | -0.267 |
Token | as |
Token ID | 355 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
fountain | +0.065 |
jug | +0.058 |
bucket | +0.057 |
bin | +0.056 |
tray | +0.053 |
Neg logit contributions | |
zo | -0.055 |
ems | -0.053 |
beating | -0.051 |
ita | -0.051 |
ascal | -0.051 |
Token | they |
Token ID | 484 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
zo | +0.027 |
ems | +0.025 |
ascal | +0.025 |
ita | +0.025 |
beating | +0.025 |
Neg logit contributions | |
fountain | -0.021 |
bin | -0.018 |
tray | -0.018 |
jug | -0.018 |
ocolate | -0.016 |
Token | moved |
Token ID | 3888 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
fountain | +0.114 |
tray | +0.096 |
jug | +0.094 |
bucket | +0.092 |
bin | +0.092 |
Neg logit contributions | |
ascal | -0.098 |
zo | -0.098 |
ems | -0.097 |
ita | -0.095 |
umper | -0.092 |
Token | their |
Token ID | 511 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
zo | +0.014 |
ems | +0.013 |
melodies | +0.013 |
ita | +0.013 |
tunes | +0.013 |
Neg logit contributions | |
fountain | -0.017 |
tray | -0.015 |
jug | -0.015 |
case | -0.015 |
pitcher | -0.014 |
Token | bounce |
Token ID | 20110 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
fountain | +0.150 |
bin | +0.129 |
jug | +0.128 |
tray | +0.127 |
bucket | +0.125 |
Neg logit contributions | |
ita | -0.139 |
zo | -0.137 |
ems | -0.132 |
ascal | -0.130 |
umper | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
fountain | +0.062 |
bucket | +0.053 |
jug | +0.052 |
tray | +0.051 |
bin | +0.051 |
Neg logit contributions | |
zo | -0.053 |
ita | -0.049 |
melodies | -0.048 |
tunes | -0.048 |
ems | -0.048 |
Token | purple |
Token ID | 14032 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
fountain | +0.026 |
Jen | +0.021 |
Megan | +0.021 |
bin | +0.020 |
jug | +0.020 |
Neg logit contributions | |
zo | -0.032 |
tunes | -0.031 |
melodies | -0.031 |
warrior | -0.031 |
matter | -0.031 |
Token | around |
Token ID | 1088 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
fountain | +0.120 |
Megan | +0.101 |
equally | +0.098 |
aney | +0.097 |
prise | +0.096 |
Neg logit contributions | |
tunes | -0.179 |
melodies | -0.176 |
zo | -0.170 |
ita | -0.163 |
musician | -0.162 |
Token | the |
Token ID | 262 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
fountain | +0.063 |
bucket | +0.054 |
pitcher | +0.052 |
tray | +0.052 |
jug | +0.051 |
Neg logit contributions | |
ita | -0.059 |
ascal | -0.059 |
zo | -0.058 |
melodies | -0.056 |
umper | -0.055 |
Token | stadium |
Token ID | 10308 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
fountain | +0.033 |
jug | +0.028 |
Jen | +0.027 |
aney | +0.027 |
bin | +0.027 |
Neg logit contributions | |
ita | -0.040 |
zo | -0.040 |
musician | -0.039 |
warrior | -0.039 |
tunes | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -9.39e-02 |
Pos logit contributions | |
fountain | +0.309 |
jug | +0.282 |
bucket | +0.280 |
buckets | +0.271 |
pitcher | +0.271 |
Neg logit contributions | |
ita | -0.235 |
zo | -0.233 |
tunes | -0.221 |
melodies | -0.210 |
matter | -0.207 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
fountain | +0.005 |
tray | +0.004 |
bucket | +0.004 |
jug | +0.004 |
bin | +0.004 |
Neg logit contributions | |
ascal | -0.006 |
ita | -0.005 |
umper | -0.005 |
zo | -0.005 |
ems | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ascal | +0.058 |
ita | +0.055 |
umper | +0.054 |
ems | +0.052 |
zo | +0.052 |
Neg logit contributions | |
fountain | -0.066 |
bucket | -0.054 |
tray | -0.054 |
jug | -0.053 |
bin | -0.052 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
fountain | +0.013 |
tray | +0.011 |
bin | +0.010 |
bucket | +0.010 |
pitcher | +0.010 |
Neg logit contributions | |
ascal | -0.007 |
ita | -0.007 |
umper | -0.007 |
zo | -0.007 |
ems | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ascal | +0.021 |
ita | +0.021 |
zo | +0.020 |
umper | +0.020 |
ities | +0.020 |
Neg logit contributions | |
fountain | -0.015 |
jug | -0.011 |
bin | -0.011 |
tray | -0.011 |
bucket | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
fountain | +0.056 |
bucket | +0.043 |
tray | +0.042 |
jug | +0.042 |
cup | +0.042 |
Neg logit contributions | |
ascal | -0.077 |
ita | -0.074 |
umper | -0.072 |
ems | -0.072 |
zo | -0.071 |
Token | measure |
Token ID | 3953 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
matter | +0.009 |
ascal | +0.009 |
umper | +0.009 |
ita | +0.008 |
please | +0.008 |
Neg logit contributions | |
fountain | -0.009 |
tray | -0.007 |
bin | -0.007 |
jug | -0.007 |
cup | -0.007 |
Token | how |
Token ID | 703 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
ascal | +0.098 |
ita | +0.095 |
umper | +0.092 |
ems | +0.092 |
ities | +0.091 |
Neg logit contributions | |
fountain | -0.068 |
bucket | -0.051 |
tray | -0.050 |
jug | -0.050 |
bin | -0.049 |
Token | high |
Token ID | 1029 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ascal | +0.048 |
zo | +0.048 |
ita | +0.046 |
umper | +0.046 |
matter | +0.045 |
Neg logit contributions | |
fountain | -0.030 |
tray | -0.023 |
bin | -0.022 |
cup | -0.021 |
rack | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
fountain | +0.112 |
bin | +0.063 |
bucket | +0.062 |
jug | +0.061 |
top | +0.057 |
Neg logit contributions | |
ascal | -0.347 |
ita | -0.335 |
umper | -0.327 |
ems | -0.319 |
ities | -0.316 |
Token | ball |
Token ID | 2613 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
fountain | +0.092 |
bucket | +0.070 |
jug | +0.069 |
tray | +0.068 |
bin | +0.066 |
Neg logit contributions | |
ascal | -0.159 |
ita | -0.154 |
ems | -0.150 |
umper | -0.149 |
Him | -0.148 |
Token | went |
Token ID | 1816 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
fountain | +0.322 |
tray | +0.277 |
rack | +0.271 |
cup | +0.268 |
pitcher | +0.268 |
Neg logit contributions | |
zo | -0.232 |
matter | -0.230 |
ems | -0.215 |
iny | -0.210 |
ita | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
fountain | +0.052 |
bucket | +0.040 |
tray | +0.039 |
jug | +0.039 |
cup | +0.038 |
Neg logit contributions | |
ascal | -0.067 |
ita | -0.066 |
umper | -0.065 |
zo | -0.064 |
ems | -0.064 |
Token | so |
Token ID | 523 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
fountain | +0.029 |
tray | +0.024 |
bucket | +0.024 |
jug | +0.024 |
bin | +0.024 |
Neg logit contributions | |
ascal | -0.022 |
ita | -0.021 |
ems | -0.021 |
umper | -0.021 |
zo | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
fountain | +0.017 |
bucket | +0.013 |
cup | +0.012 |
jug | +0.012 |
bin | +0.012 |
Neg logit contributions | |
ascal | -0.024 |
ita | -0.023 |
umper | -0.022 |
ems | -0.022 |
ities | -0.022 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
fountain | +0.024 |
bucket | +0.019 |
jug | +0.018 |
bin | +0.018 |
tray | +0.018 |
Neg logit contributions | |
ascal | -0.029 |
ita | -0.027 |
umper | -0.027 |
ems | -0.026 |
ities | -0.026 |
Token | believe |
Token ID | 1975 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ascal | +0.043 |
zo | +0.042 |
ita | +0.042 |
umper | +0.041 |
ems | +0.040 |
Neg logit contributions | |
fountain | -0.034 |
tray | -0.027 |
jug | -0.027 |
cup | -0.026 |
bucket | -0.026 |
Token | how |
Token ID | 703 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ascal | +0.110 |
ita | +0.105 |
umper | +0.102 |
ems | +0.101 |
zo | +0.101 |
Neg logit contributions | |
fountain | -0.083 |
bucket | -0.064 |
tray | -0.063 |
jug | -0.063 |
bin | -0.062 |
Token | much |
Token ID | 881 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
zo | +0.078 |
ita | +0.074 |
die | +0.072 |
ascal | +0.071 |
aware | +0.069 |
Neg logit contributions | |
fountain | -0.066 |
tray | -0.062 |
jug | -0.058 |
pitcher | -0.058 |
bin | -0.056 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
fountain | +0.164 |
tray | +0.137 |
bucket | +0.136 |
jug | +0.136 |
room | +0.133 |
Neg logit contributions | |
matter | -0.169 |
ita | -0.165 |
zo | -0.161 |
ascal | -0.160 |
ems | -0.158 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
fountain | +0.132 |
bucket | +0.108 |
tray | +0.107 |
jug | +0.107 |
pitcher | +0.103 |
Neg logit contributions | |
ita | -0.147 |
ascal | -0.146 |
ems | -0.144 |
zo | -0.144 |
ities | -0.138 |
Token | game |
Token ID | 983 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
fountain | +0.072 |
tray | +0.064 |
jug | +0.063 |
room | +0.063 |
case | +0.062 |
Neg logit contributions | |
ascal | -0.082 |
ita | -0.081 |
zo | -0.080 |
matter | -0.078 |
melodies | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
fountain | +0.281 |
tray | +0.247 |
jug | +0.246 |
bucket | +0.244 |
cup | +0.244 |
Neg logit contributions | |
zo | -0.264 |
matter | -0.252 |
ita | -0.250 |
ems | -0.248 |
tunes | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
fountain | +0.099 |
jug | +0.083 |
tray | +0.082 |
bucket | +0.081 |
pitcher | +0.079 |
Neg logit contributions | |
ita | -0.098 |
zo | -0.095 |
ascal | -0.093 |
matter | -0.093 |
ems | -0.092 |
Token | |
Token ID | 220 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ascal | +0.016 |
ita | +0.016 |
umper | +0.015 |
ems | +0.015 |
zo | +0.015 |
Neg logit contributions | |
fountain | -0.016 |
bucket | -0.012 |
tray | -0.012 |
jug | -0.012 |
bin | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
ascal | +0.081 |
ita | +0.078 |
umper | +0.077 |
zo | +0.075 |
ems | +0.074 |
Neg logit contributions | |
fountain | -0.082 |
bucket | -0.066 |
jug | -0.066 |
tray | -0.065 |
bin | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
ita | +0.034 |
ascal | +0.034 |
zo | +0.033 |
ems | +0.032 |
umper | +0.031 |
Neg logit contributions | |
fountain | -0.037 |
tray | -0.032 |
jug | -0.031 |
bucket | -0.031 |
cup | -0.030 |
Token | showing |
Token ID | 4478 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
fountain | +0.052 |
case | +0.045 |
bucket | +0.043 |
jug | +0.042 |
pitcher | +0.042 |
Neg logit contributions | |
ascal | -0.042 |
ita | -0.040 |
umper | -0.040 |
Him | -0.039 |
Horse | -0.038 |
Token | them |
Token ID | 606 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
fountain | +0.033 |
pitcher | +0.027 |
tray | +0.027 |
bucket | +0.026 |
jug | +0.026 |
Neg logit contributions | |
ita | -0.034 |
Him | -0.033 |
zo | -0.033 |
ascal | -0.032 |
umper | -0.032 |
Token | how |
Token ID | 703 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
fountain | +0.064 |
pitcher | +0.054 |
room | +0.051 |
tray | +0.051 |
rack | +0.051 |
Neg logit contributions | |
ita | -0.065 |
aware | -0.062 |
zo | -0.062 |
Him | -0.062 |
melodies | -0.060 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ita | +0.012 |
zo | +0.012 |
aware | +0.012 |
ascal | +0.012 |
Him | +0.011 |
Neg logit contributions | |
fountain | -0.012 |
tray | -0.010 |
room | -0.009 |
bin | -0.009 |
jug | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
fountain | +0.079 |
tray | +0.057 |
bucket | +0.057 |
cup | +0.056 |
jug | +0.056 |
Neg logit contributions | |
ascal | -0.147 |
ita | -0.145 |
ems | -0.141 |
zo | -0.140 |
umper | -0.138 |
Token | park |
Token ID | 3952 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
fountain | +0.112 |
tray | +0.087 |
bucket | +0.087 |
jug | +0.086 |
cup | +0.086 |
Neg logit contributions | |
ascal | -0.132 |
ita | -0.128 |
umper | -0.122 |
zo | -0.121 |
ems | -0.121 |
Token | could |
Token ID | 714 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
fountain | +0.306 |
pitcher | +0.270 |
tray | +0.268 |
bucket | +0.266 |
cup | +0.264 |
Neg logit contributions | |
zo | -0.252 |
ita | -0.246 |
matter | -0.238 |
ems | -0.226 |
melodies | -0.221 |
Token | be |
Token ID | 307 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
fountain | +0.045 |
tray | +0.039 |
cup | +0.038 |
jug | +0.038 |
bin | +0.037 |
Neg logit contributions | |
matter | -0.039 |
ita | -0.039 |
zo | -0.037 |
ascal | -0.037 |
beating | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
ita | +0.066 |
ascal | +0.065 |
zo | +0.064 |
umper | +0.062 |
ems | +0.062 |
Neg logit contributions | |
fountain | -0.057 |
tray | -0.047 |
jug | -0.045 |
bucket | -0.044 |
bin | -0.044 |
Token | After |
Token ID | 2293 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
fountain | +0.004 |
tray | +0.003 |
bucket | +0.003 |
jug | +0.003 |
bin | +0.003 |
Neg logit contributions | |
ita | -0.003 |
ascal | -0.003 |
zo | -0.003 |
umper | -0.003 |
ior | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
ascal | +0.020 |
ita | +0.020 |
Him | +0.019 |
zo | +0.019 |
Horse | +0.019 |
Neg logit contributions | |
fountain | -0.016 |
tray | -0.014 |
case | -0.013 |
bucket | -0.013 |
block | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
though | +0.012 |
ita | +0.011 |
zo | +0.011 |
tunes | +0.010 |
beating | +0.010 |
Neg logit contributions | |
fountain | -0.026 |
bin | -0.023 |
jug | -0.023 |
case | -0.022 |
tray | -0.022 |
Token | started |
Token ID | 2067 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ita | +0.002 |
ems | +0.002 |
zo | +0.002 |
umper | +0.002 |
ascal | +0.001 |
Neg logit contributions | |
fountain | -0.002 |
tray | -0.002 |
jug | -0.002 |
bin | -0.002 |
bucket | -0.002 |
Token | imagining |
Token ID | 34140 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ita | +0.056 |
ascal | +0.055 |
zo | +0.053 |
umper | +0.050 |
ems | +0.050 |
Neg logit contributions | |
fountain | -0.067 |
jug | -0.056 |
tray | -0.055 |
bin | -0.055 |
bucket | -0.054 |
Token | what |
Token ID | 644 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
ascal | +0.017 |
ita | +0.017 |
zo | +0.017 |
ities | +0.016 |
Him | +0.016 |
Neg logit contributions | |
fountain | -0.018 |
pitcher | -0.015 |
jug | -0.015 |
tray | -0.015 |
bucket | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
fountain | +0.032 |
tray | +0.025 |
bucket | +0.025 |
jug | +0.025 |
cup | +0.024 |
Neg logit contributions | |
ascal | -0.037 |
ita | -0.036 |
zo | -0.035 |
umper | -0.034 |
ems | -0.034 |
Token | game |
Token ID | 983 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
fountain | +0.083 |
jug | +0.064 |
bin | +0.063 |
bucket | +0.062 |
room | +0.060 |
Neg logit contributions | |
ita | -0.102 |
matter | -0.100 |
zo | -0.099 |
ascal | -0.099 |
ems | -0.096 |
Token | would |
Token ID | 561 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
fountain | +0.291 |
tray | +0.247 |
jug | +0.247 |
bucket | +0.243 |
pitcher | +0.243 |
Neg logit contributions | |
zo | -0.262 |
matter | -0.259 |
ems | -0.248 |
ita | -0.247 |
iny | -0.236 |
Token | be |
Token ID | 307 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
fountain | +0.062 |
jug | +0.053 |
tray | +0.053 |
cup | +0.052 |
bin | +0.051 |
Neg logit contributions | |
matter | -0.054 |
zo | -0.047 |
ems | -0.045 |
ita | -0.045 |
beating | -0.045 |
Token | like |
Token ID | 588 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ita | +0.042 |
ascal | +0.042 |
ems | +0.041 |
zo | +0.041 |
umper | +0.040 |
Neg logit contributions | |
fountain | -0.039 |
jug | -0.031 |
bucket | -0.030 |
tray | -0.030 |
bin | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
fountain | +0.107 |
jug | +0.089 |
bucket | +0.088 |
tray | +0.085 |
pitcher | +0.085 |
Neg logit contributions | |
ita | -0.096 |
zo | -0.096 |
ascal | -0.095 |
ems | -0.093 |
umper | -0.091 |
Token | He |
Token ID | 679 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
fountain | +0.018 |
tray | +0.014 |
bucket | +0.014 |
jug | +0.014 |
bin | +0.014 |
Neg logit contributions | |
ascal | -0.015 |
ita | -0.015 |
umper | -0.014 |
zo | -0.014 |
ems | -0.014 |
Token | cheer |
Token ID | 14042 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
fountain | +0.008 |
tray | +0.006 |
bucket | +0.006 |
jug | +0.006 |
bin | +0.006 |
Neg logit contributions | |
ascal | -0.011 |
ita | -0.010 |
zo | -0.010 |
ems | -0.010 |
umper | -0.010 |
Token | as |
Token ID | 355 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
ascal | +0.022 |
ita | +0.021 |
umper | +0.021 |
ems | +0.020 |
zo | +0.020 |
Neg logit contributions | |
fountain | -0.018 |
tray | -0.014 |
bucket | -0.014 |
cup | -0.014 |
bin | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ascal | +0.051 |
zo | +0.051 |
ita | +0.050 |
Him | +0.049 |
ems | +0.049 |
Neg logit contributions | |
fountain | -0.030 |
tray | -0.022 |
jug | -0.022 |
bucket | -0.021 |
case | -0.021 |
Token | watched |
Token ID | 7342 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
fountain | +0.086 |
bucket | +0.068 |
tray | +0.067 |
jug | +0.067 |
bin | +0.066 |
Neg logit contributions | |
ascal | -0.090 |
ita | -0.086 |
umper | -0.083 |
ems | -0.082 |
zo | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
ascal | +0.002 |
ita | +0.001 |
zo | +0.001 |
Him | +0.001 |
ities | +0.001 |
Neg logit contributions | |
fountain | -0.001 |
bucket | -0.001 |
jug | -0.001 |
bin | -0.001 |
tray | -0.001 |
Token | pretend |
Token ID | 16614 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
fountain | +0.019 |
cup | +0.015 |
bucket | +0.015 |
tray | +0.015 |
jug | +0.014 |
Neg logit contributions | |
ascal | -0.022 |
ita | -0.022 |
umper | -0.021 |
ems | -0.021 |
ities | -0.021 |
Token | w |
Token ID | 266 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
fountain | +0.282 |
bucket | +0.241 |
jug | +0.232 |
tray | +0.226 |
equally | +0.225 |
Neg logit contributions | |
ascal | -0.293 |
zo | -0.285 |
ita | -0.276 |
umper | -0.261 |
ems | -0.258 |
Token | affles |
Token ID | 48501 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
fountain | +0.164 |
tray | +0.136 |
cup | +0.136 |
bucket | +0.134 |
jug | +0.132 |
Neg logit contributions | |
ita | -0.106 |
ascal | -0.105 |
ems | -0.100 |
umper | -0.098 |
zo | -0.098 |
Token | fly |
Token ID | 6129 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
fountain | +0.046 |
jug | +0.039 |
bucket | +0.039 |
bin | +0.039 |
frame | +0.036 |
Neg logit contributions | |
zo | -0.042 |
ems | -0.042 |
ities | -0.041 |
ascal | -0.041 |
ita | -0.040 |
Token | high |
Token ID | 1029 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
fountain | +0.078 |
jug | +0.066 |
bucket | +0.065 |
pitcher | +0.064 |
cup | +0.063 |
Neg logit contributions | |
zo | -0.077 |
ita | -0.070 |
iny | -0.069 |
ems | -0.068 |
ascal | -0.065 |
Token | up |
Token ID | 510 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
fountain | +0.135 |
bucket | +0.101 |
tray | +0.099 |
jug | +0.098 |
cup | +0.097 |
Neg logit contributions | |
ascal | -0.207 |
ita | -0.198 |
umper | -0.194 |
ems | -0.191 |
zo | -0.189 |
Token |
|
Token ID | 198 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
fountain | +0.024 |
tray | +0.019 |
bucket | +0.019 |
jug | +0.019 |
bin | +0.018 |
Neg logit contributions | |
ascal | -0.027 |
ita | -0.026 |
umper | -0.026 |
zo | -0.025 |
ems | -0.024 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
fountain | +0.002 |
tray | +0.002 |
jug | +0.002 |
bucket | +0.002 |
bin | +0.002 |
Neg logit contributions | |
ita | -0.001 |
ascal | -0.001 |
umper | -0.001 |
emy | -0.001 |
Mic | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ita | +0.045 |
ascal | +0.043 |
ems | +0.042 |
umper | +0.041 |
Him | +0.040 |
Neg logit contributions | |
fountain | -0.041 |
tray | -0.034 |
rack | -0.032 |
block | -0.031 |
case | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ita | +0.007 |
ascal | +0.007 |
umper | +0.007 |
matter | +0.006 |
ems | +0.006 |
Neg logit contributions | |
fountain | -0.007 |
tray | -0.006 |
case | -0.006 |
rack | -0.006 |
block | -0.006 |
Token | tr |
Token ID | 491 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ascal | +0.002 |
ita | +0.002 |
umper | +0.002 |
ems | +0.002 |
zo | +0.002 |
Neg logit contributions | |
fountain | -0.002 |
tray | -0.001 |
bucket | -0.001 |
jug | -0.001 |
bin | -0.001 |
Token | amp |
Token ID | 696 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
fountain | +0.086 |
tray | +0.064 |
bucket | +0.063 |
jug | +0.062 |
bin | +0.062 |
Neg logit contributions | |
ascal | -0.147 |
ita | -0.139 |
umper | -0.138 |
zo | -0.133 |
ems | -0.131 |
Token | oline |
Token ID | 14453 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
fountain | +0.361 |
bucket | +0.307 |
tray | +0.303 |
jug | +0.301 |
bin | +0.295 |
Neg logit contributions | |
ascal | -0.237 |
ita | -0.225 |
umper | -0.218 |
ems | -0.214 |
zo | -0.212 |
Token | collapsed |
Token ID | 14707 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
fountain | +0.112 |
tray | +0.098 |
jug | +0.094 |
bucket | +0.094 |
equally | +0.093 |
Neg logit contributions | |
ita | -0.083 |
ascal | -0.081 |
zo | -0.081 |
ems | -0.076 |
umper | -0.076 |
Token | beneath |
Token ID | 11061 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
fountain | +0.103 |
jug | +0.084 |
bucket | +0.083 |
tray | +0.082 |
are | +0.080 |
Neg logit contributions | |
ita | -0.084 |
ascal | -0.082 |
beating | -0.078 |
ities | -0.078 |
zo | -0.076 |
Token | her |
Token ID | 607 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
fountain | +0.034 |
case | +0.030 |
tray | +0.028 |
pitcher | +0.028 |
rack | +0.028 |
Neg logit contributions | |
matter | -0.028 |
ita | -0.027 |
umper | -0.027 |
ascal | -0.027 |
melodies | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ascal | +0.009 |
ita | +0.009 |
zo | +0.008 |
ities | +0.008 |
umper | +0.008 |
Neg logit contributions | |
fountain | -0.012 |
jug | -0.010 |
tray | -0.010 |
bin | -0.010 |
pitcher | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
fountain | +0.018 |
tray | +0.015 |
bucket | +0.015 |
jug | +0.015 |
cup | +0.015 |
Neg logit contributions | |
ascal | -0.013 |
ita | -0.012 |
umper | -0.012 |
ities | -0.012 |
zo | -0.012 |
Token | quickly |
Token ID | 2952 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
ascal | +0.052 |
ita | +0.050 |
umper | +0.048 |
ems | +0.047 |
zo | +0.047 |
Neg logit contributions | |
fountain | -0.046 |
bucket | -0.036 |
tray | -0.036 |
jug | -0.035 |
bin | -0.035 |
Token | realized |
Token ID | 6939 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
fountain | +0.039 |
tray | +0.031 |
jug | +0.031 |
bucket | +0.030 |
bin | +0.030 |
Neg logit contributions | |
ascal | -0.037 |
ita | -0.037 |
zo | -0.034 |
ems | -0.034 |
umper | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
fountain | +0.023 |
tray | +0.017 |
bucket | +0.017 |
jug | +0.017 |
cup | +0.016 |
Neg logit contributions | |
ascal | -0.034 |
ita | -0.033 |
umper | -0.032 |
zo | -0.032 |
ems | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
fountain | +0.040 |
tray | +0.033 |
jug | +0.031 |
bucket | +0.031 |
pitcher | +0.031 |
Neg logit contributions | |
ascal | -0.044 |
ita | -0.043 |
zo | -0.042 |
matter | -0.042 |
ities | -0.042 |
Token | stadium |
Token ID | 10308 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
fountain | +0.032 |
jug | +0.027 |
cup | +0.026 |
room | +0.026 |
pitcher | +0.025 |
Neg logit contributions | |
matter | -0.038 |
warrior | -0.036 |
melodies | -0.036 |
tunes | -0.036 |
musician | -0.035 |
Token | wasn |
Token ID | 2492 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
fountain | +0.292 |
tray | +0.250 |
pitcher | +0.244 |
bucket | +0.242 |
rack | +0.242 |
Neg logit contributions | |
matter | -0.260 |
zo | -0.258 |
ita | -0.247 |
ascal | -0.241 |
ems | -0.233 |
Token | 't |
Token ID | 470 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
umper | +0.032 |
beating | +0.030 |
ascal | +0.030 |
iny | +0.029 |
zo | +0.029 |
Neg logit contributions | |
fountain | -0.042 |
bucket | -0.035 |
bin | -0.035 |
tray | -0.034 |
buckets | -0.034 |
Token | ready |
Token ID | 3492 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ascal | +0.001 |
ita | +0.001 |
umper | +0.001 |
zo | +0.001 |
ems | +0.001 |
Neg logit contributions | |
fountain | -0.001 |
jug | -0.000 |
bucket | -0.000 |
tray | -0.000 |
bin | -0.000 |
Token | yet |
Token ID | 1865 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ascal | +0.011 |
ities | +0.011 |
ita | +0.011 |
matter | +0.011 |
ems | +0.011 |
Neg logit contributions | |
fountain | -0.012 |
tray | -0.010 |
jug | -0.010 |
bucket | -0.009 |
bin | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
fountain | +0.127 |
tray | +0.107 |
bucket | +0.101 |
jug | +0.101 |
pitcher | +0.098 |
Neg logit contributions | |
ita | -0.127 |
ascal | -0.126 |
ities | -0.124 |
matter | -0.123 |
zo | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ascal | +0.006 |
ita | +0.006 |
Him | +0.005 |
ems | +0.005 |
zo | +0.005 |
Neg logit contributions | |
fountain | -0.004 |
jug | -0.003 |
bucket | -0.003 |
bin | -0.003 |
tray | -0.003 |
Token | window |
Token ID | 4324 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
fountain | +0.001 |
bucket | +0.000 |
tray | +0.000 |
cup | +0.000 |
bin | +0.000 |
Neg logit contributions | |
ascal | -0.001 |
ita | -0.001 |
umper | -0.001 |
ems | -0.001 |
zo | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
fountain | +0.107 |
jug | +0.094 |
bin | +0.091 |
bucket | +0.091 |
Mine | +0.089 |
Neg logit contributions | |
ita | -0.056 |
ities | -0.050 |
beating | -0.049 |
though | -0.048 |
ly | -0.047 |
Token | hoped |
Token ID | 10719 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
fountain | +0.014 |
bucket | +0.011 |
tray | +0.011 |
jug | +0.011 |
bin | +0.011 |
Neg logit contributions | |
ascal | -0.017 |
ita | -0.017 |
umper | -0.016 |
ems | -0.016 |
zo | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
fountain | +0.099 |
tray | +0.078 |
bucket | +0.075 |
pitcher | +0.075 |
jug | +0.074 |
Neg logit contributions | |
Him | -0.141 |
ascal | -0.137 |
ita | -0.137 |
ities | -0.133 |
matter | -0.133 |
Token | truck |
Token ID | 7779 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
fountain | +0.069 |
bucket | +0.056 |
cup | +0.056 |
jug | +0.055 |
tray | +0.055 |
Neg logit contributions | |
ascal | -0.069 |
ita | -0.064 |
ities | -0.063 |
zo | -0.063 |
ems | -0.061 |
Token | would |
Token ID | 561 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
fountain | +0.401 |
pitcher | +0.357 |
bucket | +0.357 |
jug | +0.355 |
tray | +0.343 |
Neg logit contributions | |
zo | -0.171 |
ems | -0.160 |
ita | -0.156 |
matter | -0.155 |
ache | -0.150 |
Token | move |
Token ID | 1445 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
fountain | +0.071 |
jug | +0.059 |
bin | +0.058 |
tray | +0.058 |
bucket | +0.057 |
Neg logit contributions | |
matter | -0.072 |
Him | -0.065 |
ascal | -0.065 |
ita | -0.064 |
ems | -0.064 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
fountain | +0.041 |
pitcher | +0.034 |
jug | +0.033 |
bucket | +0.033 |
tray | +0.033 |
Neg logit contributions | |
zo | -0.034 |
ita | -0.033 |
ems | -0.032 |
matter | -0.032 |
Him | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
fountain | +0.102 |
jug | +0.084 |
bucket | +0.084 |
tray | +0.081 |
pitcher | +0.080 |
Neg logit contributions | |
ita | -0.089 |
ities | -0.088 |
ems | -0.088 |
ascal | -0.086 |
Him | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
fountain | +0.017 |
bucket | +0.013 |
tray | +0.013 |
jug | +0.013 |
bin | +0.013 |
Neg logit contributions | |
ascal | -0.023 |
ita | -0.022 |
umper | -0.022 |
ems | -0.022 |
zo | -0.021 |
Token | there |
Token ID | 612 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
fountain | +0.012 |
tray | +0.010 |
bin | +0.009 |
room | +0.009 |
rack | +0.009 |
Neg logit contributions | |
ascal | -0.012 |
ita | -0.011 |
umper | -0.011 |
zo | -0.011 |
Him | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
ita | +0.002 |
ascal | +0.002 |
zo | +0.002 |
umper | +0.001 |
Him | +0.001 |
Neg logit contributions | |
fountain | -0.002 |
tray | -0.001 |
pitcher | -0.001 |
jug | -0.001 |
bucket | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ascal | +0.034 |
ita | +0.034 |
umper | +0.032 |
zo | +0.032 |
ems | +0.031 |
Neg logit contributions | |
fountain | -0.041 |
tray | -0.035 |
jug | -0.033 |
bucket | -0.033 |
bin | -0.032 |
Token | that |
Token ID | 326 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
fountain | +0.078 |
tray | +0.065 |
rack | +0.062 |
pitcher | +0.061 |
jug | +0.061 |
Neg logit contributions | |
ascal | -0.106 |
umper | -0.102 |
ita | -0.101 |
zo | -0.100 |
ities | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
fountain | +0.038 |
tray | +0.030 |
rack | +0.029 |
pitcher | +0.029 |
jug | +0.029 |
Neg logit contributions | |
ascal | -0.045 |
zo | -0.044 |
ita | -0.044 |
matter | -0.043 |
ems | -0.043 |
Token | stadium |
Token ID | 10308 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
fountain | +0.035 |
jug | +0.030 |
cup | +0.028 |
pitcher | +0.028 |
ho | +0.028 |
Neg logit contributions | |
matter | -0.039 |
warrior | -0.038 |
musician | -0.038 |
ita | -0.037 |
zo | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
fountain | +0.293 |
tray | +0.262 |
bucket | +0.252 |
pitcher | +0.251 |
rack | +0.251 |
Neg logit contributions | |
matter | -0.238 |
zo | -0.225 |
ita | -0.217 |
beating | -0.205 |
ascal | -0.203 |
Token | closed |
Token ID | 4838 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
fountain | +0.060 |
room | +0.047 |
bin | +0.046 |
tray | +0.046 |
jug | +0.046 |
Neg logit contributions | |
beating | -0.061 |
matter | -0.061 |
ascal | -0.060 |
ita | -0.060 |
zo | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
fountain | +0.002 |
tray | +0.002 |
jug | +0.002 |
pitcher | +0.002 |
bucket | +0.002 |
Neg logit contributions | |
ita | -0.002 |
ascal | -0.002 |
ities | -0.002 |
zo | -0.002 |
matter | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
fountain | +0.018 |
tray | +0.015 |
bucket | +0.015 |
jug | +0.015 |
cup | +0.015 |
Neg logit contributions | |
ascal | -0.013 |
ita | -0.012 |
umper | -0.012 |
ities | -0.012 |
zo | -0.012 |
Token | quickly |
Token ID | 2952 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
ascal | +0.052 |
ita | +0.050 |
umper | +0.048 |
ems | +0.047 |
zo | +0.047 |
Neg logit contributions | |
fountain | -0.046 |
bucket | -0.036 |
tray | -0.036 |
jug | -0.035 |
bin | -0.035 |
Token | her |
Token ID | 607 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Him | +0.005 |
ita | +0.005 |
ascal | +0.005 |
melodies | +0.005 |
ities | +0.005 |
Neg logit contributions | |
fountain | -0.005 |
bucket | -0.005 |
pitcher | -0.004 |
jug | -0.004 |
block | -0.004 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ita | +0.007 |
ascal | +0.006 |
aware | +0.006 |
instincts | +0.006 |
zo | +0.006 |
Neg logit contributions | |
fountain | -0.012 |
rack | -0.010 |
room | -0.010 |
he | -0.010 |
pitcher | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
ita | +0.058 |
ems | +0.057 |
ascal | +0.054 |
itive | +0.053 |
aware | +0.053 |
Neg logit contributions | |
fountain | -0.095 |
pitcher | -0.084 |
tray | -0.083 |
bucket | -0.082 |
block | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
fountain | +0.045 |
tray | +0.037 |
bucket | +0.037 |
pitcher | +0.036 |
rack | +0.036 |
Neg logit contributions | |
ita | -0.053 |
ems | -0.053 |
matter | -0.053 |
ascal | -0.051 |
Him | -0.051 |
Token | new |
Token ID | 649 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
fountain | +0.025 |
room | +0.021 |
aney | +0.021 |
jug | +0.021 |
pitcher | +0.020 |
Neg logit contributions | |
musician | -0.025 |
warrior | -0.025 |
matter | -0.025 |
melodies | -0.025 |
zo | -0.024 |
Token | stadium |
Token ID | 10308 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
fountain | +0.131 |
jug | +0.108 |
pitcher | +0.106 |
bin | +0.103 |
rack | +0.102 |
Neg logit contributions | |
ita | -0.143 |
zo | -0.137 |
tunes | -0.137 |
musician | -0.135 |
melodies | -0.134 |
Token | was |
Token ID | 373 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
fountain | +0.290 |
pitcher | +0.255 |
bucket | +0.253 |
tray | +0.253 |
cup | +0.249 |
Neg logit contributions | |
matter | -0.246 |
zo | -0.238 |
ita | -0.238 |
ems | -0.233 |
tunes | -0.216 |
Token | finally |
Token ID | 3443 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
fountain | +0.049 |
jug | +0.040 |
tray | +0.039 |
bucket | +0.039 |
bin | +0.039 |
Neg logit contributions | |
ita | -0.046 |
matter | -0.045 |
beating | -0.044 |
zo | -0.044 |
ascal | -0.043 |
Token | replaced |
Token ID | 6928 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
ita | +0.014 |
ascal | +0.014 |
ems | +0.013 |
zo | +0.013 |
umper | +0.013 |
Neg logit contributions | |
fountain | -0.012 |
jug | -0.009 |
tray | -0.009 |
bin | -0.009 |
bucket | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ita | +0.021 |
matter | +0.019 |
ities | +0.019 |
though | +0.019 |
iny | +0.019 |
Neg logit contributions | |
fountain | -0.027 |
pitcher | -0.024 |
bucket | -0.023 |
jug | -0.023 |
tray | -0.022 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
fountain | +0.059 |
bucket | +0.051 |
tray | +0.051 |
jug | +0.048 |
bin | +0.048 |
Neg logit contributions | |
ita | -0.044 |
ascal | -0.039 |
ems | -0.039 |
umper | -0.038 |
Him | -0.038 |
Token | : |
Token ID | 25 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ascal | +0.026 |
ita | +0.025 |
Him | +0.024 |
zo | +0.024 |
umper | +0.024 |
Neg logit contributions | |
fountain | -0.022 |
bucket | -0.018 |
tray | -0.018 |
jug | -0.017 |
cup | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
fountain | +0.025 |
bucket | +0.020 |
tray | +0.020 |
jug | +0.019 |
bin | +0.019 |
Neg logit contributions | |
ascal | -0.028 |
ita | -0.026 |
umper | -0.026 |
ems | -0.025 |
zo | -0.025 |
Token | Nice |
Token ID | 35284 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ascal | +0.040 |
ities | +0.037 |
ita | +0.036 |
ems | +0.036 |
umper | +0.035 |
Neg logit contributions | |
fountain | -0.027 |
block | -0.021 |
room | -0.020 |
are | -0.020 |
he | -0.019 |
Token | job |
Token ID | 1693 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ita | +0.009 |
ems | +0.008 |
zo | +0.008 |
ascal | +0.008 |
Him | +0.008 |
Neg logit contributions | |
fountain | -0.010 |
jug | -0.008 |
bin | -0.008 |
bucket | -0.008 |
tray | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ascal | +0.091 |
ita | +0.091 |
ems | +0.088 |
ities | +0.085 |
zo | +0.085 |
Neg logit contributions | |
fountain | -0.079 |
bucket | -0.064 |
tray | -0.061 |
jug | -0.061 |
bin | -0.061 |
Token | Elliot |
Token ID | 30451 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ascal | +0.092 |
ita | +0.088 |
umper | +0.086 |
ems | +0.084 |
zo | +0.083 |
Neg logit contributions | |
fountain | -0.106 |
bucket | -0.086 |
tray | -0.085 |
jug | -0.085 |
cup | -0.084 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ascal | +0.255 |
ita | +0.248 |
umper | +0.239 |
zo | +0.237 |
ems | +0.236 |
Neg logit contributions | |
fountain | -0.179 |
bucket | -0.136 |
jug | -0.134 |
tray | -0.133 |
bin | -0.131 |
Token | Elliot |
Token ID | 30451 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
fountain | +0.064 |
bin | +0.047 |
bucket | +0.047 |
jug | +0.046 |
tray | +0.045 |
Neg logit contributions | |
ascal | -0.103 |
ita | -0.098 |
umper | -0.095 |
ems | -0.094 |
ities | -0.093 |
Token | had |
Token ID | 550 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ita | +0.134 |
ascal | +0.129 |
zo | +0.125 |
umper | +0.120 |
ems | +0.116 |
Neg logit contributions | |
fountain | -0.140 |
tray | -0.116 |
jug | -0.115 |
bucket | -0.114 |
bin | -0.112 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ita | +0.042 |
ascal | +0.040 |
umper | +0.039 |
zo | +0.039 |
ems | +0.039 |
Neg logit contributions | |
fountain | -0.041 |
tray | -0.034 |
jug | -0.034 |
bin | -0.033 |
bucket | -0.032 |
Token | lot |
Token ID | 1256 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ita | +0.066 |
matter | +0.065 |
ascal | +0.062 |
zo | +0.061 |
die | +0.061 |
Neg logit contributions | |
fountain | -0.058 |
room | -0.046 |
buckets | -0.043 |
jug | -0.043 |
he | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
fountain | +0.002 |
bucket | +0.002 |
jug | +0.002 |
tray | +0.002 |
bin | +0.002 |
Neg logit contributions | |
ascal | -0.004 |
ita | -0.004 |
ities | -0.004 |
umper | -0.004 |
zo | -0.004 |
Token | lab |
Token ID | 2248 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ascal | +0.065 |
ita | +0.064 |
zo | +0.062 |
matter | +0.061 |
umper | +0.060 |
Neg logit contributions | |
fountain | -0.055 |
bucket | -0.044 |
equally | -0.043 |
jug | -0.043 |
tray | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
fountain | +0.067 |
bucket | +0.055 |
jug | +0.054 |
tray | +0.054 |
pitcher | +0.051 |
Neg logit contributions | |
zo | -0.064 |
ita | -0.064 |
ascal | -0.061 |
ems | -0.061 |
ities | -0.059 |
Token | He |
Token ID | 679 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
fountain | +0.008 |
bucket | +0.007 |
cup | +0.006 |
bin | +0.006 |
jug | +0.006 |
Neg logit contributions | |
ascal | -0.007 |
ita | -0.007 |
umper | -0.006 |
ems | -0.006 |
zo | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ascal | +0.045 |
ita | +0.045 |
zo | +0.044 |
ems | +0.042 |
umper | +0.042 |
Neg logit contributions | |
fountain | -0.047 |
tray | -0.039 |
jug | -0.038 |
bucket | -0.038 |
bin | -0.037 |
Token | feeling |
Token ID | 4203 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
fountain | +0.014 |
jug | +0.011 |
bin | +0.011 |
bucket | +0.011 |
tray | +0.011 |
Neg logit contributions | |
ascal | -0.015 |
ita | -0.015 |
umper | -0.014 |
zo | -0.014 |
beating | -0.014 |
Token | very |
Token ID | 845 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ascal | +0.243 |
ita | +0.230 |
umper | +0.226 |
zo | +0.222 |
ities | +0.215 |
Neg logit contributions | |
fountain | -0.206 |
tray | -0.162 |
bucket | -0.161 |
bin | -0.160 |
jug | -0.156 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
fountain | +0.008 |
tray | +0.006 |
bin | +0.006 |
bucket | +0.006 |
jug | +0.006 |
Neg logit contributions | |
ascal | -0.008 |
ita | -0.008 |
umper | -0.007 |
zo | -0.007 |
ems | -0.007 |
Token | because |
Token ID | 780 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
ascal | +0.104 |
ita | +0.098 |
umper | +0.097 |
ems | +0.095 |
zo | +0.093 |
Neg logit contributions | |
fountain | -0.079 |
cup | -0.062 |
bucket | -0.061 |
bin | -0.060 |
tray | -0.059 |
Token | his |
Token ID | 465 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
fountain | +0.043 |
tray | +0.037 |
bucket | +0.034 |
pitcher | +0.034 |
jug | +0.034 |
Neg logit contributions | |
ascal | -0.028 |
umper | -0.027 |
zo | -0.026 |
ita | -0.026 |
matter | -0.026 |
Token | sister |
Token ID | 6621 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
fountain | +0.061 |
equally | +0.046 |
he | +0.046 |
rack | +0.046 |
block | +0.045 |
Neg logit contributions | |
ascal | -0.061 |
ita | -0.059 |
ities | -0.057 |
zo | -0.057 |
ems | -0.055 |
Token | himself |
Token ID | 2241 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ascal | +0.021 |
ita | +0.020 |
umper | +0.019 |
ems | +0.019 |
zo | +0.019 |
Neg logit contributions | |
fountain | -0.016 |
bucket | -0.012 |
bin | -0.012 |
cup | -0.012 |
jug | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ascal | +0.063 |
ita | +0.061 |
ems | +0.060 |
zo | +0.059 |
umper | +0.059 |
Neg logit contributions | |
fountain | -0.062 |
bucket | -0.050 |
jug | -0.049 |
tray | -0.049 |
bin | -0.048 |
Token | not |
Token ID | 407 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ascal | +0.015 |
ita | +0.014 |
umper | +0.014 |
ems | +0.013 |
zo | +0.013 |
Neg logit contributions | |
fountain | -0.013 |
bucket | -0.010 |
tray | -0.010 |
jug | -0.010 |
bin | -0.010 |
Token | listen |
Token ID | 6004 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ascal | +0.018 |
ita | +0.018 |
umper | +0.017 |
ems | +0.017 |
zo | +0.017 |
Neg logit contributions | |
fountain | -0.014 |
bucket | -0.011 |
jug | -0.011 |
tray | -0.011 |
cup | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ascal | +0.012 |
ita | +0.011 |
umper | +0.011 |
ems | +0.011 |
zo | +0.011 |
Neg logit contributions | |
fountain | -0.009 |
bucket | -0.007 |
tray | -0.007 |
jug | -0.007 |
bin | -0.007 |
Token | others |
Token ID | 1854 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
fountain | +0.007 |
bucket | +0.005 |
bin | +0.005 |
cup | +0.005 |
tray | +0.005 |
Neg logit contributions | |
ascal | -0.009 |
ita | -0.009 |
umper | -0.009 |
ems | -0.009 |
zo | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ascal | +0.241 |
ita | +0.231 |
ems | +0.226 |
zo | +0.225 |
ities | +0.224 |
Neg logit contributions | |
fountain | -0.183 |
bucket | -0.144 |
jug | -0.139 |
tray | -0.137 |
bin | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
fountain | +0.015 |
bucket | +0.012 |
tray | +0.011 |
jug | +0.011 |
cup | +0.011 |
Neg logit contributions | |
ascal | -0.021 |
ita | -0.020 |
umper | -0.020 |
ems | -0.019 |
zo | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +8.46e-03 |
Pos logit contributions | |
fountain | +0.014 |
bucket | +0.011 |
tray | +0.011 |
jug | +0.010 |
bin | +0.010 |
Neg logit contributions | |
ascal | -0.019 |
ita | -0.019 |
umper | -0.018 |
zo | -0.018 |
ems | -0.018 |
Token | One |
Token ID | 3198 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
ascal | +0.000 |
ita | +0.000 |
umper | +0.000 |
ems | +0.000 |
zo | +0.000 |
Neg logit contributions | |
fountain | -0.001 |
bucket | -0.000 |
tray | -0.000 |
jug | -0.000 |
bin | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ascal | +0.002 |
ita | +0.002 |
zo | +0.002 |
matter | +0.001 |
umper | +0.001 |
Neg logit contributions | |
fountain | -0.002 |
bin | -0.002 |
jug | -0.001 |
bucket | -0.001 |
tray | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ascal | +0.000 |
ita | +0.000 |
umper | +0.000 |
ems | +0.000 |
zo | +0.000 |
Neg logit contributions | |
fountain | -0.000 |
bucket | -0.000 |
tray | -0.000 |
jug | -0.000 |
bin | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ascal | +0.036 |
ita | +0.034 |
umper | +0.034 |
ems | +0.033 |
ities | +0.032 |
Neg logit contributions | |
fountain | -0.034 |
bucket | -0.027 |
bin | -0.027 |
jug | -0.026 |
cup | -0.026 |
Token | never |
Token ID | 1239 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ascal | +0.059 |
ita | +0.059 |
zo | +0.058 |
umper | +0.057 |
ems | +0.056 |
Neg logit contributions | |
fountain | -0.050 |
tray | -0.041 |
jug | -0.040 |
bin | -0.039 |
bucket | -0.038 |
Token | played |
Token ID | 2826 |
Feature activation | +4.42e-03 |
Pos logit contributions | |
fountain | +0.013 |
bucket | +0.010 |
are | +0.010 |
cup | +0.010 |
bin | +0.009 |
Neg logit contributions | |
ascal | -0.015 |
ita | -0.014 |
umper | -0.013 |
Him | -0.013 |
ems | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ascal | +0.000 |
zo | +0.000 |
umper | +0.000 |
ities | +0.000 |
ems | +0.000 |
Neg logit contributions | |
fountain | -0.000 |
bucket | -0.000 |
jug | -0.000 |
cup | -0.000 |
tray | -0.000 |
Token | others |
Token ID | 1854 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
fountain | +0.058 |
case | +0.053 |
tray | +0.048 |
pitcher | +0.048 |
he | +0.047 |
Neg logit contributions | |
ascal | -0.068 |
umper | -0.065 |
zo | -0.065 |
ita | -0.062 |
Him | -0.062 |
Token | before |
Token ID | 878 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
ascal | +0.183 |
ita | +0.174 |
zo | +0.171 |
ities | +0.167 |
umper | +0.167 |
Neg logit contributions | |
fountain | -0.218 |
bucket | -0.189 |
bin | -0.183 |
buckets | -0.179 |
tray | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ascal | +0.028 |
ita | +0.028 |
zo | +0.027 |
umper | +0.026 |
ities | +0.026 |
Neg logit contributions | |
fountain | -0.026 |
tray | -0.021 |
bucket | -0.021 |
jug | -0.020 |
bin | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
fountain | +0.007 |
bucket | +0.006 |
tray | +0.006 |
jug | +0.006 |
bin | +0.006 |
Neg logit contributions | |
ascal | -0.009 |
ita | -0.008 |
umper | -0.008 |
zo | -0.008 |
ems | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
fountain | +0.002 |
bucket | +0.001 |
tray | +0.001 |
jug | +0.001 |
bin | +0.001 |
Neg logit contributions | |
ascal | -0.002 |
ita | -0.002 |
umper | -0.002 |
zo | -0.002 |
ems | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
ascal | +0.016 |
ita | +0.015 |
zo | +0.014 |
umper | +0.014 |
ems | +0.014 |
Neg logit contributions | |
fountain | -0.018 |
tray | -0.015 |
jug | -0.015 |
bucket | -0.015 |
cup | -0.014 |
Token | love |
Token ID | 1842 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
ascal | +0.055 |
ita | +0.055 |
ems | +0.054 |
zo | +0.053 |
umper | +0.052 |
Neg logit contributions | |
fountain | -0.053 |
jug | -0.041 |
tray | -0.041 |
bucket | -0.041 |
bin | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
fountain | +0.024 |
cup | +0.018 |
bucket | +0.018 |
bin | +0.017 |
block | +0.017 |
Neg logit contributions | |
ascal | -0.043 |
ita | -0.041 |
ems | -0.040 |
umper | -0.040 |
ities | -0.040 |
Token | play |
Token ID | 711 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
ascal | +0.038 |
ita | +0.037 |
zo | +0.037 |
ems | +0.037 |
umper | +0.036 |
Neg logit contributions | |
fountain | -0.028 |
tray | -0.022 |
bucket | -0.021 |
jug | -0.021 |
bin | -0.021 |
Token | with |
Token ID | 351 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
fountain | +0.046 |
bucket | +0.037 |
jug | +0.036 |
bin | +0.035 |
tray | +0.035 |
Neg logit contributions | |
ascal | -0.056 |
zo | -0.054 |
ems | -0.053 |
umper | -0.052 |
ita | -0.052 |
Token | Big |
Token ID | 4403 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
fountain | +0.041 |
bucket | +0.032 |
tray | +0.032 |
jug | +0.031 |
bin | +0.030 |
Neg logit contributions | |
ascal | -0.049 |
ita | -0.047 |
umper | -0.046 |
zo | -0.046 |
ems | -0.045 |
Token | gie |
Token ID | 22699 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ascal | +0.118 |
ita | +0.109 |
ems | +0.102 |
umper | +0.100 |
Him | +0.098 |
Neg logit contributions | |
fountain | -0.299 |
bin | -0.256 |
block | -0.255 |
cup | -0.255 |
bucket | -0.254 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
ascal | +0.242 |
ita | +0.238 |
zo | +0.237 |
ems | +0.232 |
umper | +0.225 |
Neg logit contributions | |
fountain | -0.212 |
bucket | -0.169 |
bin | -0.165 |
jug | -0.165 |
tray | -0.158 |
Token | He |
Token ID | 679 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ascal | +0.038 |
ita | +0.036 |
umper | +0.036 |
ities | +0.035 |
ems | +0.034 |
Neg logit contributions | |
fountain | -0.029 |
bucket | -0.023 |
cup | -0.023 |
tray | -0.022 |
block | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ascal | +0.076 |
ita | +0.075 |
ems | +0.072 |
zo | +0.072 |
umper | +0.072 |
Neg logit contributions | |
fountain | -0.063 |
bucket | -0.049 |
jug | -0.049 |
tray | -0.048 |
bin | -0.048 |
Token | so |
Token ID | 523 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
fountain | +0.076 |
bucket | +0.057 |
jug | +0.056 |
bin | +0.056 |
tray | +0.055 |
Neg logit contributions | |
ascal | -0.120 |
ita | -0.117 |
umper | -0.113 |
zo | -0.112 |
ems | -0.110 |
Token | enormous |
Token ID | 9812 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ascal | +0.038 |
zo | +0.038 |
ita | +0.037 |
umper | +0.035 |
die | +0.034 |
Neg logit contributions | |
fountain | -0.038 |
tray | -0.031 |
bucket | -0.031 |
jug | -0.031 |
bin | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
fountain | +0.091 |
bucket | +0.071 |
bin | +0.071 |
jug | +0.070 |
tray | +0.068 |
Neg logit contributions | |
ascal | -0.098 |
ita | -0.095 |
Him | -0.093 |
ities | -0.091 |
ems | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
fountain | +0.019 |
bucket | +0.014 |
tray | +0.014 |
jug | +0.014 |
cup | +0.014 |
Neg logit contributions | |
ascal | -0.029 |
ita | -0.028 |
umper | -0.028 |
ems | -0.027 |
zo | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
fountain | +0.023 |
bucket | +0.018 |
tray | +0.018 |
jug | +0.017 |
bin | +0.017 |
Neg logit contributions | |
ascal | -0.029 |
ita | -0.028 |
umper | -0.028 |
ems | -0.027 |
zo | -0.027 |
Token | S |
Token ID | 50 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
fountain | +0.006 |
tray | +0.005 |
jug | +0.005 |
bucket | +0.005 |
bin | +0.005 |
Neg logit contributions | |
ascal | -0.006 |
ita | -0.006 |
umper | -0.006 |
ems | -0.005 |
emy | -0.005 |
Token | ara |
Token ID | 3301 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
fountain | +0.096 |
bucket | +0.081 |
jug | +0.078 |
tray | +0.078 |
bin | +0.077 |
Neg logit contributions | |
ascal | -0.086 |
ita | -0.082 |
ems | -0.080 |
umper | -0.077 |
ities | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
fountain | +0.079 |
bucket | +0.062 |
jug | +0.060 |
tray | +0.060 |
bin | +0.060 |
Neg logit contributions | |
ascal | -0.095 |
ita | -0.091 |
umper | -0.088 |
ems | -0.088 |
zo | -0.087 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ascal | +0.024 |
ita | +0.024 |
umper | +0.023 |
ems | +0.023 |
zo | +0.022 |
Neg logit contributions | |
fountain | -0.019 |
bucket | -0.014 |
bin | -0.014 |
tray | -0.014 |
jug | -0.014 |
Token | run |
Token ID | 1057 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
fountain | +0.021 |
cup | +0.017 |
jug | +0.017 |
bucket | +0.016 |
tray | +0.016 |
Neg logit contributions | |
ascal | -0.026 |
ems | -0.026 |
ita | -0.026 |
umper | -0.025 |
zo | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
fountain | +0.125 |
jug | +0.111 |
bucket | +0.107 |
pitcher | +0.105 |
tray | +0.103 |
Neg logit contributions | |
ita | -0.068 |
zo | -0.067 |
Him | -0.067 |
ems | -0.066 |
ascal | -0.066 |
Token | their |
Token ID | 511 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Him | +0.013 |
ior | +0.011 |
matter | +0.011 |
Horse | +0.011 |
God | +0.011 |
Neg logit contributions | |
fountain | -0.014 |
case | -0.014 |
pitcher | -0.012 |
tted | -0.012 |
oor | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
fountain | +0.059 |
jug | +0.045 |
bucket | +0.044 |
pitcher | +0.044 |
tray | +0.044 |
Neg logit contributions | |
ascal | -0.065 |
ita | -0.063 |
ities | -0.059 |
zo | -0.059 |
ems | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
fountain | +0.093 |
bucket | +0.083 |
jug | +0.083 |
pitcher | +0.081 |
buckets | +0.078 |
Neg logit contributions | |
ita | -0.061 |
ities | -0.060 |
tunes | -0.058 |
zo | -0.058 |
beating | -0.055 |
Token | They |
Token ID | 1119 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
ascal | +0.023 |
ita | +0.022 |
ems | +0.022 |
umper | +0.022 |
zo | +0.021 |
Neg logit contributions | |
fountain | -0.015 |
bucket | -0.011 |
tray | -0.011 |
jug | -0.011 |
bin | -0.011 |
Token | did |
Token ID | 750 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
fountain | +0.030 |
tray | +0.025 |
pitcher | +0.025 |
jug | +0.024 |
soda | +0.024 |
Neg logit contributions | |
ascal | -0.023 |
ita | -0.023 |
ems | -0.023 |
zo | -0.022 |
ities | -0.021 |
Token | not |
Token ID | 407 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
fountain | +0.049 |
jug | +0.042 |
bucket | +0.041 |
pitcher | +0.040 |
bin | +0.040 |
Neg logit contributions | |
ems | -0.047 |
matter | -0.047 |
ita | -0.047 |
ascal | -0.047 |
ities | -0.046 |
Token | talk |
Token ID | 1561 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ascal | +0.034 |
ita | +0.033 |
umper | +0.032 |
ems | +0.031 |
zo | +0.031 |
Neg logit contributions | |
fountain | -0.025 |
bucket | -0.019 |
jug | -0.019 |
cup | -0.019 |
tray | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ascal | +0.025 |
ems | +0.025 |
ita | +0.025 |
zo | +0.024 |
ities | +0.024 |
Neg logit contributions | |
fountain | -0.030 |
jug | -0.025 |
bucket | -0.025 |
tray | -0.024 |
pitcher | -0.024 |
Token | each |
Token ID | 1123 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ascal | +0.025 |
ita | +0.024 |
zo | +0.024 |
Him | +0.023 |
ities | +0.023 |
Neg logit contributions | |
fountain | -0.021 |
bucket | -0.016 |
tray | -0.016 |
jug | -0.016 |
bin | -0.015 |
Token | other |
Token ID | 584 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ita | +0.015 |
ascal | +0.015 |
umper | +0.015 |
matter | +0.014 |
ems | +0.014 |
Neg logit contributions | |
fountain | -0.013 |
jug | -0.010 |
bucket | -0.010 |
case | -0.010 |
bin | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
fountain | +0.068 |
bucket | +0.058 |
jug | +0.056 |
pitcher | +0.056 |
bin | +0.053 |
Neg logit contributions | |
ita | -0.059 |
ems | -0.058 |
ascal | -0.058 |
ities | -0.058 |
zo | -0.057 |
Token | They |
Token ID | 1119 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ascal | +0.035 |
ita | +0.034 |
umper | +0.033 |
ems | +0.033 |
zo | +0.033 |
Neg logit contributions | |
fountain | -0.021 |
bucket | -0.015 |
tray | -0.015 |
jug | -0.015 |
bin | -0.014 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
fountain | +0.025 |
tray | +0.021 |
pitcher | +0.020 |
jug | +0.020 |
bucket | +0.020 |
Neg logit contributions | |
ascal | -0.023 |
ita | -0.023 |
zo | -0.023 |
ems | -0.022 |
ities | -0.022 |
Token | perfectly |
Token ID | 7138 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
fountain | +0.039 |
tray | +0.033 |
case | +0.032 |
jug | +0.032 |
pitcher | +0.032 |
Neg logit contributions | |
zo | -0.033 |
ities | -0.032 |
ascal | -0.032 |
ems | -0.032 |
ita | -0.031 |
Token | into |
Token ID | 656 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
fountain | +0.063 |
bin | +0.050 |
jug | +0.050 |
tray | +0.049 |
bucket | +0.049 |
Neg logit contributions | |
ascal | -0.064 |
ita | -0.064 |
zo | -0.061 |
ems | -0.060 |
ities | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
ities | +0.048 |
ascal | +0.048 |
ita | +0.046 |
matter | +0.046 |
zo | +0.044 |
Neg logit contributions | |
fountain | -0.044 |
case | -0.035 |
tray | -0.035 |
jug | -0.034 |
pitcher | -0.032 |
Token | piece |
Token ID | 3704 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
matter | +0.025 |
die | +0.025 |
ita | +0.024 |
zo | +0.024 |
warrior | +0.024 |
Neg logit contributions | |
fountain | -0.018 |
ics | -0.017 |
Megan | -0.016 |
room | -0.016 |
Jen | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
fountain | +0.019 |
bin | +0.015 |
jug | +0.015 |
Mine | +0.015 |
lobby | +0.015 |
Neg logit contributions | |
though | -0.015 |
zo | -0.015 |
ita | -0.015 |
iny | -0.015 |
ly | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
fountain | +0.072 |
case | +0.063 |
room | +0.058 |
tray | +0.057 |
he | +0.056 |
Neg logit contributions | |
matter | -0.069 |
melodies | -0.065 |
tunes | -0.062 |
ita | -0.061 |
die | -0.061 |
Token | clay |
Token ID | 21558 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
matter | +0.032 |
ities | +0.032 |
ascal | +0.031 |
ita | +0.031 |
tunes | +0.030 |
Neg logit contributions | |
fountain | -0.031 |
Megan | -0.025 |
Jen | -0.024 |
case | -0.023 |
room | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ities | +0.093 |
zo | +0.093 |
ita | +0.092 |
ascal | +0.091 |
ems | +0.089 |
Neg logit contributions | |
fountain | -0.089 |
aney | -0.071 |
Megan | -0.070 |
he | -0.068 |
tray | -0.068 |
Token | had |
Token ID | 550 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
ascal | +0.013 |
ita | +0.013 |
zo | +0.012 |
umper | +0.012 |
ems | +0.012 |
Neg logit contributions | |
fountain | -0.013 |
jug | -0.011 |
tray | -0.011 |
bucket | -0.010 |
bin | -0.010 |
Token | just |
Token ID | 655 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
ascal | +0.028 |
ita | +0.028 |
umper | +0.028 |
zo | +0.028 |
ems | +0.028 |
Neg logit contributions | |
fountain | -0.030 |
tray | -0.026 |
jug | -0.026 |
bin | -0.025 |
bucket | -0.024 |
Token | shaped |
Token ID | 14292 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ascal | +0.033 |
ita | +0.032 |
ems | +0.031 |
ities | +0.031 |
umper | +0.031 |
Neg logit contributions | |
fountain | -0.034 |
tray | -0.028 |
jug | -0.027 |
bucket | -0.027 |
bin | -0.027 |
Token | He |
Token ID | 679 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
fountain | +0.007 |
bucket | +0.006 |
tray | +0.005 |
jug | +0.005 |
bin | +0.005 |
Neg logit contributions | |
ascal | -0.008 |
ita | -0.008 |
umper | -0.008 |
ems | -0.007 |
zo | -0.007 |
Token | only |
Token ID | 691 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ascal | +0.052 |
ita | +0.051 |
zo | +0.049 |
ems | +0.049 |
umper | +0.048 |
Neg logit contributions | |
fountain | -0.053 |
tray | -0.043 |
bucket | -0.043 |
jug | -0.042 |
bin | -0.041 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ascal | +0.007 |
ita | +0.007 |
umper | +0.007 |
ems | +0.006 |
zo | +0.006 |
Neg logit contributions | |
fountain | -0.008 |
bucket | -0.006 |
tray | -0.006 |
jug | -0.006 |
cup | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
fountain | +0.012 |
bucket | +0.009 |
tray | +0.009 |
jug | +0.009 |
bin | +0.009 |
Neg logit contributions | |
ascal | -0.015 |
ita | -0.014 |
umper | -0.014 |
zo | -0.013 |
ems | -0.013 |
Token | sleep |
Token ID | 3993 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ascal | +0.045 |
ita | +0.045 |
zo | +0.043 |
ems | +0.043 |
matter | +0.043 |
Neg logit contributions | |
fountain | -0.042 |
tray | -0.034 |
bucket | -0.034 |
jug | -0.033 |
bin | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
ascal | +0.109 |
ita | +0.104 |
zo | +0.101 |
ities | +0.101 |
ems | +0.100 |
Neg logit contributions | |
fountain | -0.085 |
bucket | -0.067 |
jug | -0.065 |
bin | -0.064 |
cup | -0.062 |
Token | cry |
Token ID | 3960 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ascal | +0.052 |
ita | +0.050 |
umper | +0.049 |
ems | +0.048 |
zo | +0.048 |
Neg logit contributions | |
fountain | -0.043 |
bucket | -0.033 |
tray | -0.033 |
jug | -0.033 |
cup | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
ascal | +0.108 |
ita | +0.105 |
umper | +0.103 |
ems | +0.101 |
zo | +0.100 |
Neg logit contributions | |
fountain | -0.056 |
bucket | -0.040 |
cup | -0.039 |
tray | -0.039 |
jug | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
fountain | +0.003 |
bucket | +0.002 |
cup | +0.002 |
jug | +0.002 |
bin | +0.002 |
Neg logit contributions | |
ascal | -0.004 |
ita | -0.004 |
ems | -0.004 |
umper | -0.004 |
zo | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ascal | +0.002 |
ita | +0.002 |
zo | +0.001 |
umper | +0.001 |
iny | +0.001 |
Neg logit contributions | |
fountain | -0.002 |
jug | -0.001 |
bucket | -0.001 |
tray | -0.001 |
bin | -0.001 |
Token | Mom |
Token ID | 29252 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ascal | +0.012 |
ita | +0.011 |
umper | +0.011 |
zo | +0.011 |
ems | +0.010 |
Neg logit contributions | |
fountain | -0.022 |
jug | -0.018 |
tray | -0.018 |
bucket | -0.018 |
bin | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
ascal | +0.003 |
ita | +0.003 |
umper | +0.003 |
ems | +0.003 |
zo | +0.003 |
Neg logit contributions | |
fountain | -0.002 |
bucket | -0.002 |
cup | -0.002 |
jug | -0.002 |
tray | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
fountain | +0.029 |
tray | +0.024 |
bucket | +0.023 |
jug | +0.023 |
bin | +0.023 |
Neg logit contributions | |
ascal | -0.029 |
ita | -0.029 |
umper | -0.027 |
ems | -0.027 |
zo | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ascal | +0.004 |
ita | +0.004 |
Him | +0.004 |
ems | +0.004 |
umper | +0.004 |
Neg logit contributions | |
fountain | -0.005 |
bucket | -0.004 |
tray | -0.004 |
buckets | -0.004 |
bin | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
fountain | +0.025 |
bucket | +0.019 |
tray | +0.019 |
jug | +0.019 |
cup | +0.018 |
Neg logit contributions | |
ascal | -0.032 |
ita | -0.031 |
umper | -0.030 |
ems | -0.029 |
zo | -0.029 |
Token | Ok |
Token ID | 18690 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ascal | +0.030 |
ita | +0.028 |
umper | +0.028 |
ems | +0.027 |
zo | +0.027 |
Neg logit contributions | |
fountain | -0.025 |
bucket | -0.019 |
tray | -0.019 |
jug | -0.019 |
cup | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
ascal | +0.036 |
ita | +0.034 |
umper | +0.034 |
zo | +0.033 |
ems | +0.033 |
Neg logit contributions | |
fountain | -0.020 |
bucket | -0.015 |
tray | -0.014 |
cup | -0.014 |
jug | -0.014 |
Token | let |
Token ID | 1309 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
ascal | +0.043 |
ita | +0.041 |
ems | +0.040 |
umper | +0.039 |
zo | +0.039 |
Neg logit contributions | |
fountain | -0.048 |
bucket | -0.039 |
tray | -0.038 |
jug | -0.038 |
bin | -0.038 |
Token | 's |
Token ID | 338 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ita | +0.037 |
ascal | +0.037 |
umper | +0.036 |
ems | +0.034 |
zo | +0.034 |
Neg logit contributions | |
fountain | -0.035 |
bucket | -0.027 |
tray | -0.027 |
jug | -0.027 |
bin | -0.026 |
Token | take |
Token ID | 1011 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ascal | +0.028 |
ita | +0.027 |
ems | +0.026 |
umper | +0.026 |
zo | +0.026 |
Neg logit contributions | |
fountain | -0.021 |
tray | -0.016 |
cup | -0.016 |
bin | -0.016 |
bucket | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ita | +0.078 |
umper | +0.076 |
ascal | +0.076 |
zo | +0.074 |
ems | +0.074 |
Neg logit contributions | |
fountain | -0.058 |
case | -0.045 |
tray | -0.045 |
jug | -0.044 |
bucket | -0.044 |
Token | home |
Token ID | 1363 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ita | +0.043 |
ems | +0.042 |
iny | +0.042 |
umper | +0.042 |
zo | +0.041 |
Neg logit contributions | |
fountain | -0.051 |
jug | -0.039 |
bin | -0.038 |
pitcher | -0.038 |
bucket | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
ascal | +0.061 |
ita | +0.058 |
umper | +0.057 |
ems | +0.056 |
zo | +0.055 |
Neg logit contributions | |
fountain | -0.048 |
bucket | -0.037 |
jug | -0.036 |
tray | -0.036 |
cup | -0.036 |
Token | applaud |
Token ID | 22517 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ascal | +0.047 |
ita | +0.045 |
umper | +0.043 |
ems | +0.043 |
zo | +0.042 |
Neg logit contributions | |
fountain | -0.052 |
bucket | -0.042 |
tray | -0.042 |
jug | -0.042 |
bin | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
ascal | +0.128 |
ita | +0.124 |
ems | +0.120 |
umper | +0.119 |
zo | +0.119 |
Neg logit contributions | |
fountain | -0.093 |
bucket | -0.072 |
jug | -0.070 |
tray | -0.070 |
bin | -0.069 |
Token | birds |
Token ID | 10087 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
fountain | +0.056 |
bucket | +0.048 |
jug | +0.047 |
tray | +0.047 |
cup | +0.047 |
Neg logit contributions | |
ascal | -0.032 |
ita | -0.031 |
zo | -0.029 |
umper | -0.028 |
ems | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
fountain | +0.026 |
bucket | +0.022 |
tray | +0.022 |
bin | +0.021 |
jug | +0.021 |
Neg logit contributions | |
ita | -0.024 |
ascal | -0.023 |
zo | -0.023 |
ems | -0.023 |
melodies | -0.022 |
Token | The |
Token ID | 383 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
fountain | +0.033 |
bucket | +0.027 |
tray | +0.027 |
jug | +0.026 |
cup | +0.026 |
Neg logit contributions | |
ascal | -0.035 |
ita | -0.035 |
zo | -0.034 |
umper | -0.033 |
ems | -0.033 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
fountain | +0.042 |
bucket | +0.036 |
tray | +0.035 |
jug | +0.035 |
cup | +0.035 |
Neg logit contributions | |
ascal | -0.023 |
ita | -0.022 |
zo | -0.020 |
umper | -0.020 |
ems | -0.020 |
Token | were |
Token ID | 547 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ascal | +0.012 |
ita | +0.012 |
umper | +0.012 |
ems | +0.011 |
zo | +0.011 |
Neg logit contributions | |
fountain | -0.009 |
bucket | -0.007 |
jug | -0.007 |
tray | -0.007 |
bin | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
fountain | +0.101 |
bucket | +0.083 |
bin | +0.082 |
tray | +0.081 |
jug | +0.080 |
Neg logit contributions | |
ita | -0.121 |
ascal | -0.121 |
zo | -0.111 |
umper | -0.109 |
iny | -0.107 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ita | +0.001 |
ascal | +0.001 |
zo | +0.001 |
aware | +0.001 |
melodies | +0.001 |
Neg logit contributions | |
fountain | -0.001 |
bin | -0.000 |
tray | -0.000 |
bucket | -0.000 |
cup | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
fountain | +0.069 |
bucket | +0.053 |
tray | +0.052 |
jug | +0.052 |
bin | +0.051 |
Neg logit contributions | |
ascal | -0.091 |
ita | -0.087 |
umper | -0.085 |
ems | -0.084 |
zo | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
ities | +0.042 |
ita | +0.042 |
ascal | +0.041 |
ems | +0.040 |
itive | +0.040 |
Neg logit contributions | |
fountain | -0.055 |
bucket | -0.048 |
jug | -0.047 |
tray | -0.046 |
bin | -0.046 |
Token | She |
Token ID | 1375 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
fountain | +0.002 |
bucket | +0.001 |
tray | +0.001 |
jug | +0.001 |
bin | +0.001 |
Neg logit contributions | |
ascal | -0.002 |
ita | -0.002 |
umper | -0.002 |
ems | -0.002 |
zo | -0.002 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
ita | +0.034 |
ascal | +0.033 |
zo | +0.033 |
umper | +0.031 |
ems | +0.030 |
Neg logit contributions | |
fountain | -0.043 |
tray | -0.037 |
bin | -0.036 |
jug | -0.035 |
rack | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
ascal | +0.038 |
ita | +0.037 |
umper | +0.035 |
ems | +0.035 |
zo | +0.035 |
Neg logit contributions | |
fountain | -0.033 |
bucket | -0.026 |
tray | -0.026 |
jug | -0.026 |
bin | -0.025 |
Token | said |
Token ID | 531 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
fountain | +0.003 |
tray | +0.003 |
jug | +0.003 |
bin | +0.003 |
bucket | +0.003 |
Neg logit contributions | |
ita | -0.003 |
ascal | -0.003 |
ems | -0.002 |
umper | -0.002 |
zo | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ascal | +0.018 |
ita | +0.018 |
ems | +0.017 |
Him | +0.017 |
umper | +0.017 |
Neg logit contributions | |
fountain | -0.015 |
bucket | -0.012 |
tray | -0.012 |
bin | -0.012 |
jug | -0.011 |
Token | � |
Token ID | 6184 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
fountain | +0.021 |
bucket | +0.016 |
tray | +0.016 |
jug | +0.016 |
bin | +0.016 |
Neg logit contributions | |
ascal | -0.027 |
ita | -0.026 |
umper | -0.025 |
ems | -0.025 |
zo | -0.025 |
Token | � |
Token ID | 95 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ascal | +0.017 |
ita | +0.016 |
ems | +0.016 |
umper | +0.015 |
zo | +0.015 |
Neg logit contributions | |
fountain | -0.019 |
bucket | -0.016 |
tray | -0.015 |
jug | -0.015 |
cup | -0.015 |
Token | € |
Token ID | 26391 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
ascal | +0.030 |
ita | +0.028 |
umper | +0.027 |
ems | +0.027 |
zo | +0.027 |
Neg logit contributions | |
fountain | -0.032 |
bucket | -0.026 |
jug | -0.025 |
tray | -0.025 |
bin | -0.025 |
Token | � |
Token ID | 129 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ascal | +0.128 |
ita | +0.126 |
ems | +0.122 |
zo | +0.118 |
umper | +0.114 |
Neg logit contributions | |
fountain | -0.152 |
jug | -0.124 |
tray | -0.124 |
bucket | -0.124 |
bin | -0.121 |
Token | � |
Token ID | 241 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
fountain | +0.016 |
bucket | +0.013 |
jug | +0.013 |
tray | +0.013 |
bin | +0.013 |
Neg logit contributions | |
ascal | -0.012 |
ita | -0.012 |
umper | -0.011 |
ems | -0.011 |
zo | -0.011 |
Token | him |
Token ID | 683 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
fountain | +0.032 |
bucket | +0.026 |
tray | +0.025 |
case | +0.025 |
jug | +0.025 |
Neg logit contributions | |
ascal | -0.034 |
umper | -0.033 |
ities | -0.032 |
ita | -0.032 |
Him | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ita | +0.012 |
ascal | +0.012 |
ities | +0.012 |
ems | +0.012 |
zo | +0.012 |
Neg logit contributions | |
fountain | -0.014 |
tray | -0.011 |
bucket | -0.011 |
jug | -0.011 |
bin | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
fountain | +0.045 |
tray | +0.038 |
bucket | +0.037 |
banner | +0.036 |
jug | +0.035 |
Neg logit contributions | |
ior | -0.033 |
ascal | -0.032 |
ita | -0.030 |
umper | -0.030 |
gie | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
fountain | +0.031 |
bucket | +0.024 |
tray | +0.024 |
jug | +0.024 |
bin | +0.024 |
Neg logit contributions | |
ascal | -0.037 |
ita | -0.035 |
umper | -0.034 |
zo | -0.034 |
ems | -0.033 |
Token | His |
Token ID | 6653 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
fountain | +0.021 |
tray | +0.017 |
jug | +0.017 |
bucket | +0.017 |
bin | +0.017 |
Neg logit contributions | |
ascal | -0.011 |
ita | -0.011 |
zo | -0.010 |
umper | -0.010 |
iny | -0.010 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ascal | +0.010 |
ita | +0.010 |
umper | +0.009 |
ems | +0.009 |
zo | +0.009 |
Neg logit contributions | |
fountain | -0.006 |
bucket | -0.004 |
tray | -0.004 |
jug | -0.004 |
bin | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
fountain | +0.018 |
bucket | +0.014 |
tray | +0.014 |
jug | +0.014 |
bin | +0.013 |
Neg logit contributions | |
ascal | -0.016 |
ita | -0.015 |
umper | -0.015 |
ems | -0.014 |
zo | -0.014 |
Token | no |
Token ID | 645 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
fountain | +0.002 |
bucket | +0.001 |
tray | +0.001 |
block | +0.001 |
bin | +0.001 |
Neg logit contributions | |
ascal | -0.002 |
ita | -0.002 |
ems | -0.002 |
Him | -0.002 |
ities | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
fountain | +0.104 |
cup | +0.077 |
bucket | +0.072 |
bin | +0.070 |
jug | +0.068 |
Neg logit contributions | |
ascal | -0.200 |
umper | -0.189 |
ems | -0.186 |
ita | -0.185 |
Mic | -0.180 |
Token | they |
Token ID | 484 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
fountain | +0.033 |
bucket | +0.026 |
bin | +0.026 |
cup | +0.026 |
jug | +0.026 |
Neg logit contributions | |
ascal | -0.033 |
ita | -0.032 |
umper | -0.031 |
zo | -0.030 |
ems | -0.030 |
Token | didn |
Token ID | 1422 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
fountain | +0.120 |
tray | +0.100 |
cup | +0.096 |
bucket | +0.095 |
soda | +0.095 |
Neg logit contributions | |
ascal | -0.076 |
ita | -0.074 |
ems | -0.074 |
umper | -0.072 |
zo | -0.072 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ascal | +0.014 |
zo | +0.014 |
aware | +0.014 |
ita | +0.014 |
melodies | +0.013 |
Neg logit contributions | |
fountain | -0.015 |
tray | -0.014 |
bin | -0.013 |
bucket | -0.013 |
stack | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
fountain | +0.069 |
bucket | +0.054 |
tray | +0.054 |
jug | +0.053 |
bin | +0.052 |
Neg logit contributions | |
ascal | -0.094 |
ita | -0.091 |
zo | -0.087 |
ems | -0.087 |
umper | -0.087 |
Token | they |
Token ID | 484 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
fountain | +0.073 |
tray | +0.061 |
bucket | +0.058 |
bin | +0.057 |
block | +0.057 |
Neg logit contributions | |
ita | -0.074 |
ascal | -0.073 |
zo | -0.073 |
melodies | -0.069 |
umper | -0.069 |
Token | couldn |
Token ID | 3521 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
fountain | +0.095 |
tray | +0.080 |
bucket | +0.077 |
cup | +0.077 |
jug | +0.075 |
Neg logit contributions | |
ascal | -0.096 |
ita | -0.095 |
zo | -0.095 |
umper | -0.094 |
ems | -0.091 |
Token | 't |
Token ID | 470 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
zo | +0.031 |
umper | +0.030 |
ita | +0.030 |
ascal | +0.030 |
iny | +0.029 |
Neg logit contributions | |
fountain | -0.032 |
bucket | -0.029 |
tray | -0.028 |
buckets | -0.027 |
cup | -0.027 |
Token | wait |
Token ID | 4043 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ascal | +0.000 |
ita | +0.000 |
zo | +0.000 |
umper | +0.000 |
matter | +0.000 |
Neg logit contributions | |
fountain | -0.000 |
tray | -0.000 |
bucket | -0.000 |
cup | -0.000 |
jug | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
fountain | +0.053 |
jug | +0.042 |
bin | +0.042 |
bucket | +0.042 |
tray | +0.042 |
Neg logit contributions | |
ascal | -0.056 |
ita | -0.054 |
ems | -0.052 |
zo | -0.051 |
umper | -0.051 |
Token | see |
Token ID | 766 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
fountain | +0.013 |
tray | +0.010 |
bucket | +0.010 |
jug | +0.010 |
cup | +0.009 |
Neg logit contributions | |
ascal | -0.018 |
ita | -0.017 |
umper | -0.017 |
zo | -0.017 |
ems | -0.017 |
Token | what |
Token ID | 644 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
fountain | +0.043 |
bucket | +0.033 |
tray | +0.033 |
case | +0.033 |
pitcher | +0.032 |
Neg logit contributions | |
ascal | -0.051 |
umper | -0.051 |
Him | -0.051 |
ita | -0.051 |
zo | -0.050 |
Token | else |
Token ID | 2073 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
fountain | +0.028 |
tray | +0.022 |
rack | +0.022 |
bucket | +0.022 |
room | +0.021 |
Neg logit contributions | |
zo | -0.035 |
ita | -0.035 |
matter | -0.035 |
ascal | -0.034 |
melodies | -0.032 |
Token | might |
Token ID | 1244 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
fountain | +0.093 |
tray | +0.076 |
bucket | +0.073 |
bin | +0.071 |
jug | +0.071 |
Neg logit contributions | |
zo | -0.113 |
ita | -0.113 |
ascal | -0.112 |
ems | -0.110 |
umper | -0.106 |
Token | even |
Token ID | 772 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
ascal | +0.089 |
umper | +0.084 |
ita | +0.084 |
zo | +0.081 |
ities | +0.080 |
Neg logit contributions | |
fountain | -0.064 |
tray | -0.049 |
bucket | -0.048 |
bin | -0.046 |
jug | -0.046 |
Token | more |
Token ID | 517 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ascal | +0.036 |
ita | +0.034 |
ities | +0.033 |
ems | +0.033 |
umper | +0.033 |
Neg logit contributions | |
fountain | -0.022 |
bucket | -0.016 |
cup | -0.016 |
jug | -0.015 |
bin | -0.015 |
Token | sad |
Token ID | 6507 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
fountain | +0.066 |
bucket | +0.053 |
jug | +0.052 |
cup | +0.051 |
bin | +0.051 |
Neg logit contributions | |
ascal | -0.069 |
ita | -0.067 |
ems | -0.066 |
umper | -0.065 |
zo | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
fountain | +0.022 |
cup | +0.016 |
bucket | +0.016 |
are | +0.015 |
jug | +0.015 |
Neg logit contributions | |
ascal | -0.041 |
ita | -0.040 |
umper | -0.039 |
zo | -0.038 |
ems | -0.038 |
Token | wished |
Token ID | 16555 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
fountain | +0.099 |
tray | +0.082 |
bucket | +0.080 |
jug | +0.079 |
bin | +0.079 |
Neg logit contributions | |
ascal | -0.083 |
ita | -0.079 |
umper | -0.077 |
zo | -0.075 |
ems | -0.075 |
Token | he |
Token ID | 339 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
fountain | +0.034 |
bucket | +0.027 |
tray | +0.027 |
jug | +0.027 |
bin | +0.026 |
Neg logit contributions | |
ascal | -0.030 |
ita | -0.028 |
umper | -0.028 |
Him | -0.027 |
zo | -0.027 |
Token | could |
Token ID | 714 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
fountain | +0.055 |
bucket | +0.042 |
jug | +0.040 |
bin | +0.040 |
cup | +0.040 |
Neg logit contributions | |
ascal | -0.080 |
ita | -0.076 |
umper | -0.074 |
ems | -0.073 |
ities | -0.072 |
Token | make |
Token ID | 787 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
fountain | +0.034 |
tray | +0.028 |
jug | +0.027 |
bin | +0.027 |
cup | +0.027 |
Neg logit contributions | |
ascal | -0.037 |
ita | -0.035 |
umper | -0.035 |
zo | -0.034 |
ems | -0.033 |
Token | his |
Token ID | 465 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ascal | +0.007 |
ita | +0.007 |
umper | +0.007 |
Him | +0.007 |
zo | +0.007 |
Neg logit contributions | |
fountain | -0.006 |
tray | -0.004 |
bucket | -0.004 |
jug | -0.004 |
case | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
fountain | +0.006 |
room | +0.005 |
he | +0.005 |
equally | +0.005 |
case | +0.005 |
Neg logit contributions | |
ascal | -0.005 |
ita | -0.005 |
matter | -0.005 |
emy | -0.005 |
actions | -0.005 |
Token | my |
Token ID | 1820 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
fountain | +0.050 |
tray | +0.042 |
bin | +0.041 |
bucket | +0.041 |
jug | +0.041 |
Neg logit contributions | |
ascal | -0.028 |
ita | -0.026 |
umper | -0.025 |
ems | -0.024 |
zo | -0.024 |
Token | gate |
Token ID | 8946 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
fountain | +0.012 |
jug | +0.010 |
equally | +0.010 |
room | +0.010 |
tray | +0.010 |
Neg logit contributions | |
ita | -0.012 |
ascal | -0.011 |
ems | -0.011 |
matter | -0.011 |
ities | -0.011 |
Token | reminded |
Token ID | 14516 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
fountain | +0.206 |
tray | +0.186 |
jug | +0.186 |
pitcher | +0.179 |
ocolate | +0.178 |
Neg logit contributions | |
beating | -0.193 |
matter | -0.183 |
ita | -0.178 |
ems | -0.177 |
melodies | -0.173 |
Token | them |
Token ID | 606 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
ascal | +0.097 |
ita | +0.094 |
umper | +0.091 |
zo | +0.090 |
Him | +0.089 |
Neg logit contributions | |
fountain | -0.097 |
bucket | -0.080 |
tray | -0.077 |
jug | -0.077 |
pitcher | -0.074 |
Token | how |
Token ID | 703 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
fountain | +0.059 |
pitcher | +0.050 |
tray | +0.049 |
jug | +0.048 |
bucket | +0.048 |
Neg logit contributions | |
ita | -0.045 |
ems | -0.043 |
ascal | -0.043 |
zo | -0.043 |
Him | -0.041 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
zo | +0.012 |
ascal | +0.012 |
ita | +0.011 |
aware | +0.011 |
Him | +0.011 |
Neg logit contributions | |
fountain | -0.010 |
tray | -0.009 |
room | -0.008 |
bin | -0.008 |
jug | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
fountain | +0.141 |
bucket | +0.105 |
tray | +0.103 |
jug | +0.102 |
cup | +0.100 |
Neg logit contributions | |
ascal | -0.238 |
ita | -0.231 |
ems | -0.224 |
umper | -0.224 |
zo | -0.223 |
Token | were |
Token ID | 547 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
fountain | +0.143 |
bucket | +0.104 |
tray | +0.103 |
jug | +0.101 |
cup | +0.101 |
Neg logit contributions | |
ascal | -0.245 |
ita | -0.237 |
umper | -0.232 |
ems | -0.230 |
zo | -0.228 |
Token | to |
Token ID | 284 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
fountain | +0.170 |
jug | +0.140 |
tray | +0.137 |
pitcher | +0.136 |
bucket | +0.135 |
Neg logit contributions | |
ita | -0.164 |
ascal | -0.154 |
ems | -0.151 |
zo | -0.151 |
aware | -0.147 |
Token | be |
Token ID | 307 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
fountain | +0.036 |
tray | +0.030 |
jug | +0.030 |
cup | +0.030 |
pitcher | +0.029 |
Neg logit contributions | |
ita | -0.035 |
zo | -0.033 |
ascal | -0.033 |
ems | -0.032 |
umper | -0.031 |
Token | there |
Token ID | 612 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
ita | +0.106 |
ascal | +0.102 |
zo | +0.098 |
umper | +0.096 |
ems | +0.096 |
Neg logit contributions | |
fountain | -0.091 |
jug | -0.073 |
tray | -0.071 |
bin | -0.070 |
Mine | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
fountain | +0.005 |
bucket | +0.004 |
jug | +0.004 |
bin | +0.004 |
pitcher | +0.004 |
Neg logit contributions | |
ita | -0.005 |
ascal | -0.004 |
zo | -0.004 |
ems | -0.004 |
ities | -0.004 |
Token | They |
Token ID | 2990 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ascal | +0.002 |
ita | +0.002 |
emy | +0.002 |
Mic | +0.002 |
zo | +0.002 |
Neg logit contributions | |
fountain | -0.003 |
jug | -0.003 |
tray | -0.003 |
bucket | -0.003 |
cup | -0.003 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
fountain | +0.082 |
tray | +0.066 |
jug | +0.065 |
cup | +0.064 |
bucket | +0.064 |
Neg logit contributions | |
ascal | -0.082 |
ita | -0.079 |
umper | -0.077 |
zo | -0.077 |
ems | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
fountain | +0.063 |
jug | +0.054 |
tray | +0.052 |
pitcher | +0.052 |
bucket | +0.052 |
Neg logit contributions | |
ita | -0.044 |
ascal | -0.043 |
zo | -0.043 |
aware | -0.042 |
though | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Him | +0.038 |
matter | +0.037 |
Horse | +0.035 |
ior | +0.035 |
Bun | +0.034 |
Neg logit contributions | |
case | -0.047 |
fountain | -0.046 |
pitcher | -0.043 |
frame | -0.040 |
ase | -0.040 |
Token | bench |
Token ID | 7624 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
ascal | +0.053 |
ita | +0.050 |
Horse | +0.049 |
die | +0.049 |
owl | +0.048 |
Neg logit contributions | |
fountain | -0.043 |
equally | -0.039 |
aney | -0.038 |
room | -0.037 |
oor | -0.036 |
Token | where |
Token ID | 810 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
fountain | +0.219 |
Mine | +0.219 |
jug | +0.203 |
are | +0.200 |
prise | +0.199 |
Neg logit contributions | |
though | -0.084 |
aware | -0.070 |
ita | -0.068 |
since | -0.060 |
ly | -0.058 |
Token | their |
Token ID | 511 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
fountain | +0.158 |
rack | +0.149 |
� | +0.148 |
pitcher | +0.146 |
tray | +0.144 |
Neg logit contributions | |
Him | -0.137 |
God | -0.127 |
though | -0.122 |
matter | -0.122 |
Horse | -0.121 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
fountain | +0.202 |
room | +0.168 |
he | +0.167 |
equally | +0.159 |
are | +0.157 |
Neg logit contributions | |
ascal | -0.216 |
ita | -0.209 |
emy | -0.200 |
zo | -0.200 |
Horse | -0.198 |
Token | was |
Token ID | 373 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
fountain | +0.131 |
bucket | +0.105 |
jug | +0.103 |
tray | +0.103 |
pitcher | +0.101 |
Neg logit contributions | |
ascal | -0.131 |
ita | -0.130 |
umper | -0.127 |
ems | -0.125 |
zo | -0.121 |
Token | sitting |
Token ID | 5586 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
fountain | +0.098 |
bucket | +0.080 |
jug | +0.079 |
tray | +0.079 |
cup | +0.076 |
Neg logit contributions | |
ascal | -0.104 |
ita | -0.099 |
umper | -0.096 |
ities | -0.091 |
ems | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ascal | +0.027 |
umper | +0.025 |
ita | +0.025 |
ities | +0.024 |
ems | +0.023 |
Neg logit contributions | |
fountain | -0.028 |
tray | -0.023 |
soda | -0.022 |
banner | -0.022 |
jug | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ascal | +0.000 |
ita | +0.000 |
Him | +0.000 |
ems | +0.000 |
zo | +0.000 |
Neg logit contributions | |
fountain | -0.000 |
bucket | -0.000 |
jug | -0.000 |
pitcher | -0.000 |
bin | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
fountain | +0.008 |
bucket | +0.006 |
tray | +0.006 |
jug | +0.006 |
bin | +0.006 |
Neg logit contributions | |
ascal | -0.010 |
ita | -0.009 |
ems | -0.009 |
umper | -0.009 |
zo | -0.009 |
Token | Ben |
Token ID | 11696 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
ascal | +0.033 |
umper | +0.031 |
ita | +0.031 |
ems | +0.030 |
zo | +0.029 |
Neg logit contributions | |
fountain | -0.047 |
bucket | -0.039 |
jug | -0.039 |
tray | -0.039 |
bin | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
fountain | +0.002 |
bucket | +0.002 |
jug | +0.001 |
bin | +0.001 |
tray | +0.001 |
Neg logit contributions | |
ascal | -0.003 |
ita | -0.003 |
ems | -0.002 |
umper | -0.002 |
zo | -0.002 |
Token | where |
Token ID | 810 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ems | +0.079 |
ascal | +0.078 |
umper | +0.074 |
Him | +0.073 |
matter | +0.071 |
Neg logit contributions | |
fountain | -0.073 |
equally | -0.061 |
case | -0.061 |
pitcher | -0.059 |
he | -0.058 |
Token | are |
Token ID | 389 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
fountain | +0.086 |
rack | +0.076 |
tray | +0.070 |
equally | +0.068 |
� | +0.068 |
Neg logit contributions | |
ems | -0.125 |
zo | -0.123 |
ascal | -0.118 |
umper | -0.118 |
ita | -0.117 |
Token | you |
Token ID | 345 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
fountain | +0.171 |
tray | +0.133 |
bucket | +0.131 |
case | +0.130 |
he | +0.129 |
Neg logit contributions | |
ascal | -0.194 |
ita | -0.186 |
umper | -0.185 |
zo | -0.183 |
ems | -0.181 |
Token | ? |
Token ID | 30 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
fountain | +0.017 |
bucket | +0.014 |
tray | +0.014 |
jug | +0.014 |
bin | +0.014 |
Neg logit contributions | |
ascal | -0.014 |
ita | -0.013 |
umper | -0.013 |
ems | -0.013 |
zo | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ascal | +0.102 |
umper | +0.096 |
ems | +0.096 |
ita | +0.096 |
zo | +0.091 |
Neg logit contributions | |
fountain | -0.117 |
bucket | -0.096 |
tray | -0.095 |
bin | -0.093 |
jug | -0.093 |
Token | can |
Token ID | 460 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ascal | +0.025 |
ems | +0.025 |
ita | +0.024 |
zo | +0.024 |
umper | +0.024 |
Neg logit contributions | |
fountain | -0.025 |
tray | -0.021 |
rack | -0.020 |
jug | -0.020 |
pitcher | -0.019 |
Token | 't |
Token ID | 470 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
ascal | +0.009 |
umper | +0.009 |
ita | +0.009 |
ems | +0.008 |
zo | +0.008 |
Neg logit contributions | |
fountain | -0.008 |
tray | -0.007 |
bin | -0.007 |
bucket | -0.006 |
cup | -0.006 |
Token | rules |
Token ID | 3173 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ascal | +0.012 |
ita | +0.011 |
umper | +0.011 |
ems | +0.011 |
zo | +0.011 |
Neg logit contributions | |
fountain | -0.011 |
bucket | -0.009 |
tray | -0.009 |
jug | -0.009 |
bin | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
fountain | +0.067 |
bucket | +0.057 |
jug | +0.057 |
tray | +0.055 |
pitcher | +0.055 |
Neg logit contributions | |
zo | -0.057 |
ita | -0.057 |
ems | -0.056 |
ascal | -0.054 |
umper | -0.054 |
Token | even |
Token ID | 772 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
fountain | +0.016 |
tray | +0.014 |
jug | +0.013 |
bucket | +0.013 |
bin | +0.013 |
Neg logit contributions | |
ascal | -0.014 |
ita | -0.014 |
ems | -0.013 |
zo | -0.013 |
ities | -0.013 |
Token | if |
Token ID | 611 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ascal | +0.047 |
ita | +0.043 |
umper | +0.043 |
ems | +0.042 |
zo | +0.042 |
Neg logit contributions | |
fountain | -0.029 |
their | -0.026 |
bucket | -0.023 |
are | -0.023 |
cup | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
fountain | +0.045 |
bucket | +0.034 |
tray | +0.034 |
jug | +0.033 |
bin | +0.033 |
Neg logit contributions | |
ascal | -0.065 |
ita | -0.063 |
umper | -0.061 |
ems | -0.060 |
zo | -0.060 |
Token | is |
Token ID | 318 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
fountain | +0.101 |
bucket | +0.082 |
tray | +0.081 |
jug | +0.079 |
cup | +0.079 |
Neg logit contributions | |
ascal | -0.106 |
ita | -0.105 |
ems | -0.102 |
zo | -0.101 |
umper | -0.100 |
Token | not |
Token ID | 407 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
fountain | +0.178 |
bucket | +0.138 |
tray | +0.135 |
jug | +0.135 |
cup | +0.134 |
Neg logit contributions | |
ascal | -0.229 |
ita | -0.219 |
umper | -0.214 |
ems | -0.211 |
zo | -0.209 |
Token | what |
Token ID | 644 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
fountain | +0.037 |
bucket | +0.028 |
tray | +0.028 |
jug | +0.028 |
bin | +0.027 |
Neg logit contributions | |
ascal | -0.048 |
ita | -0.045 |
umper | -0.044 |
ems | -0.044 |
zo | -0.043 |
Token | we |
Token ID | 356 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
fountain | +0.001 |
bucket | +0.001 |
tray | +0.001 |
jug | +0.001 |
bin | +0.001 |
Neg logit contributions | |
ascal | -0.002 |
ita | -0.002 |
umper | -0.002 |
ems | -0.002 |
zo | -0.002 |
Token | want |
Token ID | 765 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
fountain | +0.138 |
tray | +0.106 |
bucket | +0.105 |
cup | +0.105 |
jug | +0.104 |
Neg logit contributions | |
ascal | -0.171 |
ita | -0.165 |
umper | -0.163 |
ems | -0.162 |
zo | -0.159 |
Token | to |
Token ID | 284 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
fountain | +0.142 |
tray | +0.112 |
bucket | +0.110 |
jug | +0.107 |
bin | +0.105 |
Neg logit contributions | |
ascal | -0.154 |
ita | -0.151 |
umper | -0.149 |
ems | -0.148 |
ities | -0.146 |
Token | Finally |
Token ID | 11158 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
fountain | +0.002 |
bucket | +0.001 |
tray | +0.001 |
cup | +0.001 |
bin | +0.001 |
Neg logit contributions | |
ascal | -0.001 |
ita | -0.001 |
umper | -0.001 |
ems | -0.001 |
ities | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
ascal | +0.025 |
ita | +0.024 |
umper | +0.024 |
ems | +0.023 |
zo | +0.023 |
Neg logit contributions | |
fountain | -0.019 |
tray | -0.015 |
bucket | -0.014 |
jug | -0.014 |
cup | -0.014 |
Token | Jack |
Token ID | 3619 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
fountain | +0.005 |
tray | +0.004 |
jug | +0.004 |
bin | +0.004 |
bucket | +0.004 |
Neg logit contributions | |
ascal | -0.005 |
ita | -0.005 |
umper | -0.005 |
zo | -0.005 |
ems | -0.005 |
Token | reached |
Token ID | 4251 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ascal | +0.003 |
ita | +0.003 |
umper | +0.003 |
zo | +0.003 |
ems | +0.003 |
Neg logit contributions | |
fountain | -0.003 |
tray | -0.002 |
jug | -0.002 |
bucket | -0.002 |
bin | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
fountain | +0.005 |
jug | +0.004 |
tray | +0.004 |
bin | +0.004 |
bucket | +0.003 |
Neg logit contributions | |
ita | -0.007 |
ascal | -0.007 |
umper | -0.007 |
zo | -0.007 |
ems | -0.007 |
Token | top |
Token ID | 1353 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ita | +0.033 |
matter | +0.032 |
ems | +0.030 |
ascal | +0.030 |
ities | +0.029 |
Neg logit contributions | |
fountain | -0.020 |
room | -0.016 |
Megan | -0.015 |
rack | -0.015 |
soda | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
fountain | +0.156 |
jug | +0.135 |
bin | +0.131 |
tray | +0.128 |
bucket | +0.123 |
Neg logit contributions | |
ita | -0.170 |
zo | -0.160 |
matter | -0.159 |
iny | -0.158 |
though | -0.149 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
fountain | +0.110 |
case | +0.103 |
room | +0.088 |
tray | +0.088 |
aney | +0.088 |
Neg logit contributions | |
matter | -0.110 |
umper | -0.102 |
ita | -0.100 |
die | -0.099 |
Horse | -0.098 |
Token | vine |
Token ID | 17793 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ita | +0.008 |
ascal | +0.007 |
matter | +0.007 |
ems | +0.007 |
umper | +0.007 |
Neg logit contributions | |
fountain | -0.005 |
room | -0.004 |
rack | -0.004 |
jug | -0.004 |
tray | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
fountain | +0.106 |
jug | +0.093 |
tray | +0.089 |
Mine | +0.088 |
prise | +0.087 |
Neg logit contributions | |
ita | -0.077 |
zo | -0.072 |
iny | -0.069 |
ities | -0.068 |
beating | -0.066 |
Token | He |
Token ID | 679 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
fountain | +0.022 |
bucket | +0.018 |
tray | +0.018 |
jug | +0.018 |
cup | +0.018 |
Neg logit contributions | |
ascal | -0.022 |
ita | -0.021 |
umper | -0.020 |
ems | -0.020 |
zo | -0.020 |