Token | floor |
Token ID | 4314 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
officer | +0.028 |
salon | +0.024 |
accident | +0.022 |
ople | +0.022 |
ma | +0.022 |
Neg logit contributions | |
Fel | -0.031 |
Bet | -0.030 |
tails | -0.029 |
Louise | -0.028 |
June | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
officer | +0.316 |
sir | +0.279 |
ma | +0.271 |
iza | +0.264 |
ateful | +0.249 |
Neg logit contributions | |
tails | -0.293 |
buzzing | -0.289 |
Fel | -0.269 |
webs | -0.267 |
Bet | -0.262 |
Token | They |
Token ID | 1119 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
officer | +0.004 |
ma | +0.004 |
salon | +0.003 |
sir | +0.003 |
ily | +0.003 |
Neg logit contributions | |
Fel | -0.006 |
tails | -0.006 |
Bet | -0.006 |
June | -0.005 |
buzzing | -0.005 |
Token | talk |
Token ID | 1561 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
tails | +0.133 |
Fel | +0.130 |
buzzing | +0.122 |
Bet | +0.120 |
Louise | +0.118 |
Neg logit contributions | |
officer | -0.090 |
sir | -0.081 |
ma | -0.079 |
salon | -0.075 |
ily | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Fel | +0.267 |
tails | +0.265 |
Bet | +0.256 |
buzzing | +0.248 |
June | +0.245 |
Neg logit contributions | |
officer | -0.169 |
salon | -0.142 |
ma | -0.141 |
iza | -0.138 |
sir | -0.134 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
officer | +0.011 |
ma | +0.008 |
salon | +0.008 |
sir | +0.008 |
ily | +0.008 |
Neg logit contributions | |
Fel | -0.018 |
tails | -0.018 |
Bet | -0.018 |
June | -0.017 |
buzzing | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Fel | +1.429 |
tails | +1.405 |
Bet | +1.388 |
June | +1.318 |
buzzing | +1.297 |
Neg logit contributions | |
officer | -0.698 |
ma | -0.537 |
salon | -0.526 |
sir | -0.516 |
kids | -0.497 |
Token | soft |
Token ID | 2705 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
officer | +0.092 |
kids | +0.074 |
ma | +0.072 |
Dad | +0.070 |
accident | +0.069 |
Neg logit contributions | |
Fel | -0.196 |
tails | -0.195 |
Bet | -0.192 |
June | -0.181 |
buzzing | -0.176 |
Token | voices |
Token ID | 10839 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
Fel | +0.239 |
Bet | +0.233 |
tails | +0.221 |
June | +0.216 |
buzzing | +0.210 |
Neg logit contributions | |
officer | -0.119 |
kids | -0.110 |
ma | -0.095 |
Dad | -0.095 |
accident | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
tails | +0.008 |
Fel | +0.008 |
Bet | +0.007 |
buzzing | +0.007 |
June | +0.007 |
Neg logit contributions | |
officer | -0.005 |
ma | -0.004 |
salon | -0.004 |
sir | -0.004 |
iza | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
tails | +0.018 |
Fel | +0.018 |
buzzing | +0.017 |
Bet | +0.017 |
leaping | +0.016 |
Neg logit contributions | |
officer | -0.008 |
Dad | -0.007 |
ma | -0.007 |
ily | -0.007 |
sir | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
tails | +0.067 |
Fel | +0.066 |
Bet | +0.064 |
buzzing | +0.061 |
June | +0.061 |
Neg logit contributions | |
officer | -0.041 |
ma | -0.033 |
salon | -0.032 |
sir | -0.031 |
ily | -0.031 |
Token | house |
Token ID | 2156 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
Fel | +0.217 |
tails | +0.217 |
Bet | +0.210 |
buzzing | +0.200 |
June | +0.199 |
Neg logit contributions | |
officer | -0.130 |
ma | -0.105 |
salon | -0.100 |
ily | -0.100 |
sir | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
officer | +0.045 |
ily | +0.038 |
iza | +0.038 |
ma | +0.038 |
salon | +0.036 |
Neg logit contributions | |
tails | -0.055 |
buzzing | -0.051 |
Bet | -0.051 |
Fel | -0.049 |
Louise | -0.048 |
Token | We |
Token ID | 775 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Fel | +0.011 |
tails | +0.011 |
Bet | +0.011 |
June | +0.010 |
buzzing | +0.010 |
Neg logit contributions | |
officer | -0.009 |
ma | -0.008 |
salon | -0.008 |
sir | -0.008 |
ily | -0.007 |
Token | found |
Token ID | 1043 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
tails | +0.132 |
Fel | +0.127 |
Bet | +0.124 |
buzzing | +0.118 |
webs | +0.116 |
Neg logit contributions | |
officer | -0.102 |
ma | -0.092 |
salon | -0.089 |
sir | -0.088 |
line | -0.082 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
officer | +0.023 |
kids | +0.020 |
Dad | +0.020 |
ily | +0.019 |
ma | +0.019 |
Neg logit contributions | |
Fel | -0.048 |
tails | -0.046 |
Bet | -0.046 |
June | -0.043 |
buzzing | -0.042 |
Token | in |
Token ID | 287 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
tails | +1.311 |
Fel | +1.302 |
Bet | +1.255 |
buzzing | +1.213 |
June | +1.196 |
Neg logit contributions | |
officer | -0.782 |
ma | -0.629 |
sir | -0.606 |
salon | -0.606 |
iza | -0.589 |
Token | a |
Token ID | 257 |
Feature activation | +5.09e-03 |
Pos logit contributions | |
officer | +0.097 |
ma | +0.079 |
salon | +0.077 |
kids | +0.076 |
sir | +0.075 |
Neg logit contributions | |
Fel | -0.193 |
tails | -0.191 |
Bet | -0.186 |
June | -0.177 |
buzzing | -0.175 |
Token | box |
Token ID | 3091 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
Fel | +0.000 |
tails | +0.000 |
Bet | +0.000 |
June | +0.000 |
Louise | +0.000 |
Neg logit contributions | |
officer | -0.000 |
salon | -0.000 |
store | -0.000 |
ma | -0.000 |
boy | -0.000 |
Token | in |
Token ID | 287 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
officer | +0.188 |
ma | +0.162 |
ateful | +0.158 |
salesman | +0.155 |
iza | +0.154 |
Neg logit contributions | |
tails | -0.216 |
buzzing | -0.210 |
Bet | -0.194 |
Louise | -0.188 |
ches | -0.183 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
officer | +0.102 |
ma | +0.082 |
salon | +0.079 |
kids | +0.079 |
sir | +0.077 |
Neg logit contributions | |
Fel | -0.199 |
tails | -0.195 |
Bet | -0.190 |
June | -0.180 |
buzzing | -0.179 |
Token | water |
Token ID | 1660 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
Fel | +1.347 |
tails | +1.328 |
Bet | +1.304 |
June | +1.240 |
buzzing | +1.223 |
Neg logit contributions | |
officer | -0.754 |
ma | -0.600 |
salon | -0.582 |
sir | -0.580 |
ily | -0.571 |
Token | and |
Token ID | 290 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
officer | +0.035 |
ma | +0.028 |
salon | +0.028 |
sir | +0.027 |
iza | +0.026 |
Neg logit contributions | |
Fel | -0.056 |
tails | -0.056 |
Bet | -0.054 |
buzzing | -0.052 |
June | -0.051 |
Token | food |
Token ID | 2057 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
officer | +0.003 |
ma | +0.003 |
kids | +0.003 |
ily | +0.003 |
sir | +0.003 |
Neg logit contributions | |
Fel | -0.005 |
Bet | -0.005 |
tails | -0.005 |
June | -0.005 |
buzzing | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
tails | +0.299 |
Fel | +0.297 |
Bet | +0.289 |
buzzing | +0.282 |
Louise | +0.270 |
Neg logit contributions | |
officer | -0.192 |
ma | -0.157 |
salon | -0.155 |
iza | -0.149 |
sir | -0.147 |
Token | but |
Token ID | 475 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Fel | +0.035 |
tails | +0.034 |
Bet | +0.033 |
June | +0.032 |
buzzing | +0.032 |
Neg logit contributions | |
officer | -0.018 |
ma | -0.014 |
salon | -0.014 |
sir | -0.014 |
ily | -0.013 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
officer | +0.017 |
ma | +0.014 |
salon | +0.014 |
kids | +0.014 |
ily | +0.014 |
Neg logit contributions | |
Fel | -0.030 |
tails | -0.030 |
Bet | -0.029 |
June | -0.028 |
buzzing | -0.027 |
Token | did |
Token ID | 750 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
Fel | +1.332 |
tails | +1.315 |
Bet | +1.275 |
buzzing | +1.237 |
Louise | +1.209 |
Neg logit contributions | |
officer | -0.755 |
ma | -0.603 |
salon | -0.593 |
sir | -0.588 |
iza | -0.540 |
Token | not |
Token ID | 407 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
officer | +0.085 |
accident | +0.060 |
ily | +0.060 |
salon | +0.058 |
ma | +0.055 |
Neg logit contributions | |
Fel | -0.421 |
Bet | -0.421 |
tails | -0.413 |
June | -0.405 |
Lou | -0.386 |
Token | want |
Token ID | 765 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
officer | +0.053 |
salon | +0.044 |
ma | +0.043 |
sir | +0.041 |
iza | +0.040 |
Neg logit contributions | |
tails | -0.094 |
Fel | -0.092 |
Bet | -0.091 |
buzzing | -0.088 |
June | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
officer | +0.016 |
ily | +0.015 |
Dad | +0.014 |
kids | +0.014 |
dad | +0.012 |
Neg logit contributions | |
Bet | -0.060 |
Fel | -0.060 |
tails | -0.060 |
June | -0.057 |
elope | -0.055 |
Token | play |
Token ID | 711 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
officer | +0.024 |
ma | +0.020 |
salon | +0.020 |
sir | +0.019 |
ily | +0.019 |
Neg logit contributions | |
tails | -0.030 |
Bet | -0.028 |
Fel | -0.027 |
buzzing | -0.027 |
June | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
Fel | +0.386 |
tails | +0.379 |
Bet | +0.373 |
buzzing | +0.357 |
June | +0.350 |
Neg logit contributions | |
officer | -0.295 |
ma | -0.256 |
salon | -0.252 |
sir | -0.243 |
iza | -0.232 |
Token | fun |
Token ID | 1257 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
Fel | +0.052 |
tails | +0.052 |
Bet | +0.050 |
June | +0.047 |
buzzing | +0.047 |
Neg logit contributions | |
officer | -0.044 |
ma | -0.037 |
salon | -0.036 |
sir | -0.036 |
iza | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-03 |
Pos logit contributions | |
Fel | +0.082 |
tails | +0.081 |
Bet | +0.081 |
June | +0.077 |
Louise | +0.076 |
Neg logit contributions | |
officer | -0.030 |
kids | -0.023 |
ma | -0.022 |
ily | -0.022 |
accident | -0.022 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
tails | +0.000 |
Fel | +0.000 |
Bet | +0.000 |
buzzing | +0.000 |
June | +0.000 |
Neg logit contributions | |
officer | -0.000 |
ma | -0.000 |
Dad | -0.000 |
kids | -0.000 |
ily | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
Bet | +0.469 |
tails | +0.461 |
Fel | +0.459 |
June | +0.441 |
Louise | +0.413 |
Neg logit contributions | |
officer | -0.300 |
ma | -0.252 |
salon | -0.246 |
kids | -0.245 |
sir | -0.230 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
officer | +0.004 |
kids | +0.004 |
ma | +0.004 |
boy | +0.004 |
Dad | +0.004 |
Neg logit contributions | |
Bet | -0.005 |
Fel | -0.005 |
tails | -0.005 |
June | -0.005 |
buzzing | -0.004 |
Token | like |
Token ID | 588 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Fel | +1.347 |
tails | +1.333 |
Bet | +1.315 |
June | +1.252 |
buzzing | +1.223 |
Neg logit contributions | |
officer | -0.752 |
ma | -0.605 |
salon | -0.582 |
sir | -0.567 |
kids | -0.561 |
Token | each |
Token ID | 1123 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Fel | +0.050 |
tails | +0.050 |
Bet | +0.049 |
June | +0.046 |
elope | +0.045 |
Neg logit contributions | |
officer | -0.028 |
kids | -0.023 |
ily | -0.022 |
salon | -0.022 |
ma | -0.021 |
Token | other |
Token ID | 584 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
officer | +0.017 |
kids | +0.013 |
ma | +0.012 |
ily | +0.012 |
salon | +0.012 |
Neg logit contributions | |
Fel | -0.034 |
tails | -0.033 |
Bet | -0.033 |
June | -0.031 |
Louise | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
tails | +0.149 |
Fel | +0.148 |
Bet | +0.141 |
buzzing | +0.138 |
June | +0.135 |
Neg logit contributions | |
officer | -0.084 |
ma | -0.069 |
salon | -0.068 |
sir | -0.066 |
iza | -0.065 |
Token | They |
Token ID | 1119 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
tails | +0.002 |
Fel | +0.002 |
Bet | +0.002 |
buzzing | +0.002 |
June | +0.002 |
Neg logit contributions | |
officer | -0.001 |
Dad | -0.001 |
ma | -0.001 |
kids | -0.001 |
ily | -0.001 |
Token | bad |
Token ID | 2089 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
officer | +0.057 |
ma | +0.047 |
salon | +0.046 |
sir | +0.045 |
kids | +0.044 |
Neg logit contributions | |
Fel | -0.082 |
tails | -0.081 |
Bet | -0.079 |
June | -0.075 |
Louise | -0.073 |
Token | dog |
Token ID | 3290 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
officer | +0.046 |
salon | +0.038 |
ma | +0.038 |
iza | +0.038 |
ily | +0.036 |
Neg logit contributions | |
tails | -0.062 |
Fel | -0.062 |
Bet | -0.060 |
buzzing | -0.059 |
Louise | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
Fel | +0.347 |
tails | +0.345 |
Bet | +0.336 |
buzzing | +0.319 |
June | +0.317 |
Neg logit contributions | |
officer | -0.228 |
ma | -0.190 |
salon | -0.186 |
sir | -0.182 |
iza | -0.176 |
Token | Anna |
Token ID | 11735 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
officer | +0.005 |
salon | +0.004 |
ma | +0.004 |
accident | +0.004 |
iza | +0.004 |
Neg logit contributions | |
Fel | -0.007 |
tails | -0.007 |
Bet | -0.007 |
June | -0.007 |
Louise | -0.007 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Fel | +0.057 |
tails | +0.056 |
Bet | +0.055 |
June | +0.052 |
buzzing | +0.052 |
Neg logit contributions | |
officer | -0.036 |
ma | -0.030 |
salon | -0.029 |
sir | -0.028 |
ily | -0.028 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
officer | +0.052 |
kids | +0.043 |
Dad | +0.042 |
ily | +0.039 |
dad | +0.039 |
Neg logit contributions | |
Fel | -0.117 |
Bet | -0.116 |
tails | -0.114 |
buzzing | -0.108 |
June | -0.107 |
Token | water |
Token ID | 1660 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
Fel | +1.347 |
tails | +1.328 |
Bet | +1.304 |
June | +1.240 |
buzzing | +1.223 |
Neg logit contributions | |
officer | -0.754 |
ma | -0.600 |
salon | -0.582 |
sir | -0.580 |
ily | -0.571 |
Token | and |
Token ID | 290 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
officer | +0.035 |
ma | +0.028 |
salon | +0.028 |
sir | +0.027 |
iza | +0.026 |
Neg logit contributions | |
Fel | -0.056 |
tails | -0.056 |
Bet | -0.054 |
buzzing | -0.052 |
June | -0.051 |
Token | food |
Token ID | 2057 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
officer | +0.003 |
ma | +0.003 |
kids | +0.003 |
ily | +0.003 |
sir | +0.003 |
Neg logit contributions | |
Fel | -0.005 |
Bet | -0.005 |
tails | -0.005 |
June | -0.005 |
buzzing | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
tails | +0.299 |
Fel | +0.297 |
Bet | +0.289 |
buzzing | +0.282 |
Louise | +0.270 |
Neg logit contributions | |
officer | -0.192 |
ma | -0.157 |
salon | -0.155 |
iza | -0.149 |
sir | -0.147 |
Token | but |
Token ID | 475 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Fel | +0.035 |
tails | +0.034 |
Bet | +0.033 |
June | +0.032 |
buzzing | +0.032 |
Neg logit contributions | |
officer | -0.018 |
ma | -0.014 |
salon | -0.014 |
sir | -0.014 |
ily | -0.013 |
Token | clay |
Token ID | 21558 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Fel | +0.224 |
Bet | +0.220 |
tails | +0.218 |
June | +0.209 |
Louise | +0.206 |
Neg logit contributions | |
officer | -0.098 |
kids | -0.078 |
ma | -0.073 |
salon | -0.073 |
sir | -0.070 |
Token | balls |
Token ID | 11333 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
Fel | +0.136 |
tails | +0.132 |
Bet | +0.131 |
June | +0.124 |
buzzing | +0.123 |
Neg logit contributions | |
officer | -0.086 |
ma | -0.069 |
sir | -0.069 |
salon | -0.068 |
kids | -0.067 |
Token | together |
Token ID | 1978 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
tails | +0.193 |
Fel | +0.187 |
Bet | +0.184 |
ches | +0.174 |
buzzing | +0.174 |
Neg logit contributions | |
officer | -0.189 |
ma | -0.168 |
iza | -0.168 |
ateful | -0.158 |
salon | -0.156 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Fel | +0.091 |
tails | +0.090 |
Bet | +0.088 |
June | +0.083 |
buzzing | +0.082 |
Neg logit contributions | |
officer | -0.075 |
ma | -0.062 |
salon | -0.061 |
sir | -0.060 |
ily | -0.059 |
Token | But |
Token ID | 887 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Fel | +0.256 |
tails | +0.253 |
buzzing | +0.249 |
Bet | +0.245 |
June | +0.230 |
Neg logit contributions | |
officer | -0.208 |
ma | -0.174 |
kids | -0.171 |
sir | -0.167 |
Dad | -0.167 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Fel | +0.016 |
Bet | +0.015 |
buzzing | +0.015 |
tails | +0.015 |
June | +0.014 |
Neg logit contributions | |
officer | -0.013 |
kids | -0.011 |
salon | -0.011 |
dad | -0.011 |
sir | -0.011 |
Token | ignored |
Token ID | 9514 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
Fel | +1.382 |
tails | +1.360 |
Bet | +1.330 |
buzzing | +1.268 |
June | +1.261 |
Neg logit contributions | |
officer | -0.705 |
ma | -0.558 |
salon | -0.553 |
sir | -0.535 |
iza | -0.512 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
officer | +0.179 |
Dad | +0.141 |
kids | +0.136 |
dad | +0.134 |
Tommy | +0.130 |
Neg logit contributions | |
Bet | -0.483 |
tails | -0.461 |
Fel | -0.459 |
buzzing | -0.440 |
June | -0.438 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
Fel | +0.506 |
Bet | +0.492 |
tails | +0.490 |
June | +0.466 |
buzzing | +0.455 |
Neg logit contributions | |
officer | -0.261 |
ma | -0.198 |
salon | -0.195 |
sir | -0.191 |
kids | -0.188 |
Token | She |
Token ID | 1375 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
tails | +0.003 |
buzzing | +0.003 |
Fel | +0.003 |
odic | +0.003 |
hovering | +0.003 |
Neg logit contributions | |
Dad | -0.001 |
officer | -0.001 |
ma | -0.001 |
kids | -0.001 |
Tom | -0.001 |
Token | did |
Token ID | 750 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
Fel | +0.092 |
tails | +0.091 |
Bet | +0.090 |
June | +0.086 |
buzzing | +0.085 |
Neg logit contributions | |
officer | -0.044 |
ma | -0.033 |
salon | -0.032 |
ily | -0.031 |
kids | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
tails | +0.262 |
Fel | +0.261 |
Bet | +0.253 |
buzzing | +0.240 |
Louise | +0.238 |
Neg logit contributions | |
officer | -0.182 |
salon | -0.147 |
ma | -0.146 |
sir | -0.142 |
iza | -0.138 |
Token | I |
Token ID | 314 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Fel | +0.008 |
tails | +0.007 |
Bet | +0.007 |
Louise | +0.007 |
buzzing | +0.007 |
Neg logit contributions | |
officer | -0.005 |
salon | -0.004 |
ateful | -0.004 |
ma | -0.004 |
ople | -0.004 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
officer | +0.104 |
ma | +0.086 |
salon | +0.085 |
sir | +0.083 |
ily | +0.079 |
Neg logit contributions | |
Fel | -0.139 |
tails | -0.136 |
Bet | -0.133 |
buzzing | -0.125 |
June | -0.124 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Fel | +0.138 |
tails | +0.137 |
Bet | +0.134 |
June | +0.127 |
buzzing | +0.126 |
Neg logit contributions | |
officer | -0.077 |
ma | -0.062 |
salon | -0.060 |
sir | -0.059 |
ily | -0.057 |
Token | ," |
Token ID | 553 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
officer | +0.086 |
ma | +0.071 |
sir | +0.071 |
kids | +0.069 |
Dad | +0.066 |
Neg logit contributions | |
Fel | -0.172 |
tails | -0.170 |
Bet | -0.168 |
June | -0.161 |
buzzing | -0.155 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
officer | +0.196 |
salon | +0.165 |
ma | +0.159 |
ople | +0.151 |
sir | +0.149 |
Neg logit contributions | |
Fel | -0.286 |
tails | -0.283 |
Bet | -0.278 |
Louise | -0.272 |
buzzing | -0.264 |
Token | says |
Token ID | 1139 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Fel | +1.186 |
tails | +1.165 |
Bet | +1.127 |
Louise | +1.098 |
buzzing | +1.088 |
Neg logit contributions | |
officer | -0.879 |
salon | -0.740 |
ma | -0.729 |
sir | -0.701 |
iza | -0.688 |
Token | . |
Token ID | 13 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
tails | +0.212 |
Fel | +0.211 |
buzzing | +0.204 |
Bet | +0.201 |
Louise | +0.199 |
Neg logit contributions | |
officer | -0.151 |
salon | -0.130 |
ma | -0.126 |
sir | -0.118 |
ople | -0.118 |
Token | " |
Token ID | 366 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
officer | +0.001 |
Dad | +0.001 |
ily | +0.001 |
ma | +0.001 |
sir | +0.001 |
Neg logit contributions | |
tails | -0.004 |
Fel | -0.004 |
eds | -0.004 |
Bet | -0.004 |
ches | -0.004 |
Token | I |
Token ID | 40 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Fel | +0.025 |
Bet | +0.024 |
June | +0.023 |
tails | +0.023 |
buzzing | +0.022 |
Neg logit contributions | |
officer | -0.024 |
ma | -0.020 |
sir | -0.020 |
salon | -0.020 |
ople | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
officer | +0.064 |
ma | +0.054 |
salon | +0.053 |
sir | +0.052 |
kids | +0.049 |
Neg logit contributions | |
Fel | -0.100 |
tails | -0.098 |
Bet | -0.097 |
buzzing | -0.091 |
June | -0.091 |
Token | " |
Token ID | 366 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
tails | +0.040 |
Fel | +0.040 |
Bet | +0.039 |
June | +0.037 |
Louise | +0.036 |
Neg logit contributions | |
officer | -0.022 |
ma | -0.019 |
sir | -0.018 |
salon | -0.017 |
Dad | -0.017 |
Token | We |
Token ID | 1135 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
tails | +0.030 |
Fel | +0.029 |
Bet | +0.028 |
buzzing | +0.027 |
Louise | +0.027 |
Neg logit contributions | |
officer | -0.019 |
kids | -0.015 |
salon | -0.015 |
ma | -0.015 |
ily | -0.015 |
Token | are |
Token ID | 389 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
tails | +0.127 |
Fel | +0.127 |
Bet | +0.122 |
buzzing | +0.116 |
June | +0.116 |
Neg logit contributions | |
officer | -0.083 |
ma | -0.069 |
salon | -0.068 |
sir | -0.066 |
line | -0.062 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
officer | +0.128 |
kids | +0.109 |
ma | +0.106 |
Dad | +0.101 |
ily | +0.101 |
Neg logit contributions | |
Fel | -0.233 |
tails | -0.225 |
Bet | -0.225 |
June | -0.211 |
Louise | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
officer | +0.089 |
kids | +0.076 |
sir | +0.075 |
Dad | +0.072 |
ma | +0.072 |
Neg logit contributions | |
Fel | -0.217 |
Bet | -0.217 |
tails | -0.213 |
June | -0.206 |
buzzing | -0.197 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
tails | +0.018 |
Fel | +0.017 |
Bet | +0.016 |
itching | +0.015 |
Mo | +0.015 |
Neg logit contributions | |
officer | -0.027 |
sir | -0.026 |
kids | -0.026 |
ma | -0.025 |
dad | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Fel | +1.448 |
tails | +1.417 |
Bet | +1.406 |
June | +1.347 |
buzzing | +1.311 |
Neg logit contributions | |
officer | -0.658 |
ma | -0.522 |
sir | -0.501 |
kids | -0.492 |
ily | -0.482 |
Token | We |
Token ID | 775 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Fel | +0.017 |
tails | +0.017 |
Bet | +0.017 |
buzzing | +0.016 |
leaping | +0.016 |
Neg logit contributions | |
officer | -0.008 |
Dad | -0.007 |
sir | -0.007 |
ma | -0.007 |
kids | -0.007 |
Token | want |
Token ID | 765 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
tails | +0.128 |
Fel | +0.125 |
Bet | +0.121 |
buzzing | +0.116 |
June | +0.113 |
Neg logit contributions | |
officer | -0.086 |
ma | -0.076 |
salon | -0.074 |
sir | -0.073 |
line | -0.071 |
Token | to |
Token ID | 284 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
officer | +0.024 |
Dad | +0.019 |
kids | +0.019 |
dad | +0.018 |
sir | +0.018 |
Neg logit contributions | |
Fel | -0.065 |
Bet | -0.063 |
tails | -0.063 |
June | -0.059 |
buzzing | -0.058 |
Token | be |
Token ID | 307 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
officer | +0.024 |
ma | +0.020 |
salon | +0.019 |
sir | +0.019 |
ily | +0.019 |
Neg logit contributions | |
tails | -0.032 |
Fel | -0.032 |
Bet | -0.031 |
buzzing | -0.029 |
June | -0.029 |
Token | am |
Token ID | 716 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
officer | +0.103 |
kids | +0.087 |
ily | +0.085 |
iza | +0.082 |
salon | +0.082 |
Neg logit contributions | |
Fel | -0.145 |
Bet | -0.144 |
tails | -0.144 |
June | -0.140 |
Louise | -0.138 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
tails | +0.160 |
Bet | +0.159 |
Fel | +0.157 |
June | +0.148 |
buzzing | +0.146 |
Neg logit contributions | |
officer | -0.082 |
ily | -0.068 |
kids | -0.067 |
sir | -0.066 |
Dad | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e-03 |
Pos logit contributions | |
tails | +0.109 |
Fel | +0.106 |
Bet | +0.104 |
buzzing | +0.100 |
June | +0.099 |
Neg logit contributions | |
officer | -0.062 |
salon | -0.051 |
ma | -0.050 |
iza | -0.047 |
sir | -0.047 |
Token | This |
Token ID | 770 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
Fel | +0.000 |
tails | +0.000 |
Bet | +0.000 |
buzzing | +0.000 |
June | +0.000 |
Neg logit contributions | |
officer | -0.000 |
ma | -0.000 |
sir | -0.000 |
salon | -0.000 |
ily | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
officer | +0.054 |
kids | +0.042 |
boy | +0.040 |
sir | +0.039 |
ma | +0.038 |
Neg logit contributions | |
Bet | -0.085 |
Fel | -0.084 |
tails | -0.081 |
June | -0.078 |
Louise | -0.076 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Fel | +0.136 |
tails | +0.135 |
Bet | +0.134 |
June | +0.125 |
buzzing | +0.122 |
Neg logit contributions | |
officer | -0.072 |
ma | -0.057 |
ily | -0.056 |
sir | -0.056 |
kids | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
Fel | +1.471 |
Bet | +1.440 |
tails | +1.436 |
June | +1.364 |
buzzing | +1.334 |
Neg logit contributions | |
officer | -0.643 |
ma | -0.485 |
sir | -0.465 |
salon | -0.462 |
kids | -0.458 |
Token | She |
Token ID | 1375 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
tails | +0.000 |
Fel | +0.000 |
Bet | +0.000 |
buzzing | +0.000 |
June | +0.000 |
Neg logit contributions | |
officer | -0.000 |
ma | -0.000 |
ily | -0.000 |
sir | -0.000 |
Dad | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Fel | +0.086 |
Bet | +0.085 |
tails | +0.083 |
June | +0.079 |
buzzing | +0.077 |
Neg logit contributions | |
officer | -0.061 |
ma | -0.049 |
kids | -0.048 |
salon | -0.047 |
sir | -0.047 |
Token | my |
Token ID | 616 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
Fel | +0.134 |
Bet | +0.131 |
tails | +0.129 |
June | +0.121 |
webs | +0.115 |
Neg logit contributions | |
officer | -0.076 |
kids | -0.064 |
ily | -0.063 |
ma | -0.062 |
dad | -0.059 |
Token | puppy |
Token ID | 26188 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Fel | +0.082 |
Bet | +0.081 |
tails | +0.080 |
June | +0.075 |
buzzing | +0.074 |
Neg logit contributions | |
officer | -0.053 |
kids | -0.042 |
sir | -0.041 |
ma | -0.040 |
salon | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Fel | +0.002 |
tails | +0.002 |
Bet | +0.002 |
Louise | +0.002 |
buzzing | +0.002 |
Neg logit contributions | |
officer | -0.002 |
salon | -0.002 |
iza | -0.002 |
ma | -0.002 |
ateful | -0.002 |
Token | please |
Token ID | 3387 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Fel | +0.018 |
tails | +0.017 |
Bet | +0.017 |
buzzing | +0.016 |
Louise | +0.016 |
Neg logit contributions | |
officer | -0.009 |
salon | -0.007 |
ma | -0.007 |
sir | -0.006 |
iza | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
officer | +0.083 |
ma | +0.065 |
sir | +0.062 |
salon | +0.062 |
ily | +0.060 |
Neg logit contributions | |
Fel | -0.167 |
tails | -0.164 |
Bet | -0.162 |
June | -0.154 |
buzzing | -0.152 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
officer | +0.001 |
sir | +0.001 |
ma | +0.001 |
ily | +0.001 |
Dad | +0.001 |
Neg logit contributions | |
Fel | -0.002 |
tails | -0.002 |
Bet | -0.002 |
buzzing | -0.001 |
June | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
Fel | +0.434 |
tails | +0.427 |
Bet | +0.421 |
June | +0.396 |
buzzing | +0.391 |
Neg logit contributions | |
officer | -0.330 |
ma | -0.274 |
salon | -0.267 |
sir | -0.265 |
ily | -0.259 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
officer | +0.006 |
ma | +0.005 |
kids | +0.005 |
sir | +0.005 |
ily | +0.004 |
Neg logit contributions | |
Bet | -0.009 |
tails | -0.009 |
Fel | -0.008 |
buzzing | -0.008 |
June | -0.008 |
Token | can |
Token ID | 460 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
tails | +1.282 |
Fel | +1.278 |
Bet | +1.213 |
buzzing | +1.188 |
Louise | +1.154 |
Neg logit contributions | |
officer | -0.779 |
salon | -0.633 |
ma | -0.625 |
sir | -0.617 |
iza | -0.595 |
Token | be |
Token ID | 307 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Fel | +0.043 |
tails | +0.042 |
Bet | +0.041 |
June | +0.039 |
buzzing | +0.039 |
Neg logit contributions | |
officer | -0.029 |
ma | -0.023 |
salon | -0.023 |
sir | -0.022 |
ily | -0.022 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
officer | +0.099 |
kids | +0.082 |
ily | +0.078 |
ma | +0.074 |
dad | +0.073 |
Neg logit contributions | |
Fel | -0.185 |
Bet | -0.178 |
tails | -0.175 |
June | -0.166 |
Louise | -0.162 |
Token | too |
Token ID | 1165 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
tails | +0.228 |
Fel | +0.227 |
Bet | +0.217 |
buzzing | +0.214 |
June | +0.209 |
Neg logit contributions | |
officer | -0.144 |
ma | -0.122 |
salon | -0.117 |
iza | -0.114 |
sir | -0.113 |
Token | ," |
Token ID | 553 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
officer | +0.009 |
ma | +0.007 |
sir | +0.006 |
salon | +0.006 |
kids | +0.006 |
Neg logit contributions | |
Fel | -0.020 |
tails | -0.019 |
Bet | -0.019 |
June | -0.018 |
buzzing | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
officer | +0.290 |
ma | +0.242 |
salon | +0.237 |
sir | +0.234 |
ily | +0.229 |
Neg logit contributions | |
Fel | -0.372 |
tails | -0.367 |
Bet | -0.358 |
June | -0.338 |
buzzing | -0.335 |
Token | a |
Token ID | 257 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Fel | +0.147 |
tails | +0.146 |
Bet | +0.141 |
June | +0.134 |
buzzing | +0.133 |
Neg logit contributions | |
officer | -0.080 |
ma | -0.064 |
salon | -0.061 |
ily | -0.061 |
sir | -0.060 |
Token | little |
Token ID | 1310 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
officer | +0.020 |
ma | +0.016 |
sir | +0.015 |
boy | +0.015 |
kids | +0.015 |
Neg logit contributions | |
tails | -0.042 |
Fel | -0.042 |
Bet | -0.040 |
June | -0.039 |
Louise | -0.038 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
officer | +0.095 |
ma | +0.069 |
salon | +0.066 |
sir | +0.064 |
ily | +0.061 |
Neg logit contributions | |
Fel | -0.269 |
tails | -0.266 |
Bet | -0.261 |
June | -0.250 |
buzzing | -0.249 |
Token | named |
Token ID | 3706 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
officer | +0.110 |
salon | +0.088 |
ma | +0.087 |
kids | +0.086 |
ily | +0.085 |
Neg logit contributions | |
Fel | -0.169 |
Bet | -0.159 |
tails | -0.158 |
June | -0.150 |
Louise | -0.146 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Fel | +0.328 |
tails | +0.324 |
Bet | +0.315 |
buzzing | +0.301 |
June | +0.298 |
Neg logit contributions | |
officer | -0.175 |
ma | -0.141 |
salon | -0.136 |
ily | -0.135 |
sir | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Fel | +1.347 |
tails | +1.338 |
Bet | +1.306 |
June | +1.243 |
buzzing | +1.242 |
Neg logit contributions | |
officer | -0.733 |
ma | -0.591 |
salon | -0.585 |
sir | -0.565 |
iza | -0.534 |
Token | She |
Token ID | 1375 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ily | +0.034 |
ma | +0.031 |
kids | +0.030 |
Sara | +0.030 |
Tom | +0.030 |
Neg logit contributions | |
odic | -0.035 |
tails | -0.034 |
itching | -0.033 |
hovering | -0.033 |
buzzing | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Fel | +0.072 |
tails | +0.071 |
Bet | +0.069 |
June | +0.066 |
buzzing | +0.065 |
Neg logit contributions | |
officer | -0.037 |
ma | -0.029 |
ily | -0.028 |
salon | -0.028 |
kids | -0.027 |
Token | only |
Token ID | 691 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
Fel | +0.150 |
tails | +0.145 |
Bet | +0.142 |
June | +0.135 |
ches | +0.131 |
Neg logit contributions | |
officer | -0.069 |
ma | -0.056 |
kids | -0.055 |
salon | -0.054 |
ily | -0.054 |
Token | three |
Token ID | 1115 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
officer | +0.101 |
ma | +0.066 |
salon | +0.063 |
sir | +0.060 |
ily | +0.056 |
Neg logit contributions | |
Fel | -0.387 |
tails | -0.382 |
Bet | -0.377 |
June | -0.361 |
buzzing | -0.358 |
Token | You |
Token ID | 921 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
tails | +0.001 |
Fel | +0.001 |
Bet | +0.001 |
buzzing | +0.001 |
June | +0.001 |
Neg logit contributions | |
officer | -0.000 |
ma | -0.000 |
ily | -0.000 |
sir | -0.000 |
kids | -0.000 |
Token | are |
Token ID | 389 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
officer | +0.016 |
salon | +0.013 |
ma | +0.013 |
sir | +0.012 |
iza | +0.012 |
Neg logit contributions | |
Fel | -0.028 |
tails | -0.028 |
Bet | -0.027 |
buzzing | -0.026 |
June | -0.026 |
Token | good |
Token ID | 922 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
officer | +0.136 |
ma | +0.114 |
kids | +0.112 |
ily | +0.110 |
sir | +0.107 |
Neg logit contributions | |
Fel | -0.246 |
tails | -0.239 |
Bet | -0.237 |
June | -0.221 |
buzzing | -0.217 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
tails | +0.006 |
Fel | +0.005 |
Bet | +0.005 |
buzzing | +0.005 |
Louise | +0.005 |
Neg logit contributions | |
officer | -0.003 |
salon | -0.003 |
ma | -0.003 |
iza | -0.003 |
line | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
Fel | +0.230 |
tails | +0.228 |
Bet | +0.220 |
buzzing | +0.215 |
Louise | +0.214 |
Neg logit contributions | |
officer | -0.155 |
salon | -0.134 |
ma | -0.129 |
iza | -0.122 |
sir | -0.119 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
officer | +0.017 |
kids | +0.015 |
ma | +0.014 |
Dad | +0.013 |
dad | +0.013 |
Neg logit contributions | |
Fel | -0.037 |
tails | -0.035 |
Bet | -0.035 |
June | -0.034 |
buzzing | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
tails | +1.272 |
Fel | +1.266 |
Bet | +1.209 |
buzzing | +1.179 |
Louise | +1.171 |
Neg logit contributions | |
officer | -0.773 |
ma | -0.629 |
salon | -0.604 |
iza | -0.596 |
sir | -0.590 |
Token | I |
Token ID | 314 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
tails | +0.002 |
Fel | +0.002 |
Bet | +0.001 |
buzzing | +0.001 |
June | +0.001 |
Neg logit contributions | |
officer | -0.001 |
ily | -0.001 |
ma | -0.001 |
Dad | -0.001 |
sir | -0.001 |
Token | am |
Token ID | 716 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
officer | +0.102 |
ma | +0.083 |
salon | +0.081 |
sir | +0.080 |
ily | +0.080 |
Neg logit contributions | |
Fel | -0.139 |
tails | -0.137 |
Bet | -0.135 |
June | -0.128 |
Louise | -0.125 |
Token | proud |
Token ID | 6613 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
Fel | +0.155 |
tails | +0.152 |
Bet | +0.148 |
June | +0.140 |
Louise | +0.137 |
Neg logit contributions | |
officer | -0.097 |
ma | -0.080 |
sir | -0.077 |
salon | -0.077 |
ily | -0.076 |
Token | of |
Token ID | 286 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
Fel | +0.071 |
tails | +0.069 |
Bet | +0.069 |
buzzing | +0.067 |
Louise | +0.066 |
Neg logit contributions | |
officer | -0.049 |
salon | -0.040 |
ma | -0.039 |
sir | -0.038 |
iza | -0.038 |
Token | mist |
Token ID | 4020 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Fel | +0.027 |
tails | +0.027 |
Bet | +0.026 |
buzzing | +0.025 |
June | +0.024 |
Neg logit contributions | |
officer | -0.020 |
ma | -0.017 |
salon | -0.017 |
ily | -0.016 |
sir | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
tails | +0.269 |
Fel | +0.264 |
Bet | +0.260 |
buzzing | +0.248 |
Louise | +0.245 |
Neg logit contributions | |
officer | -0.185 |
ma | -0.153 |
salon | -0.147 |
sir | -0.143 |
ily | -0.143 |
Token | go |
Token ID | 467 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
officer | +0.019 |
salon | +0.016 |
ily | +0.015 |
ople | +0.015 |
salesman | +0.015 |
Neg logit contributions | |
Bet | -0.023 |
tails | -0.023 |
Fel | -0.023 |
buzzing | -0.022 |
Louise | -0.021 |
Token | away |
Token ID | 1497 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
tails | +0.050 |
Fel | +0.049 |
Bet | +0.048 |
buzzing | +0.045 |
June | +0.045 |
Neg logit contributions | |
officer | -0.044 |
ma | -0.040 |
salon | -0.039 |
sir | -0.038 |
ily | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
officer | +0.009 |
salon | +0.007 |
ma | +0.007 |
sir | +0.007 |
iza | +0.007 |
Neg logit contributions | |
tails | -0.013 |
Fel | -0.013 |
Bet | -0.013 |
buzzing | -0.013 |
Louise | -0.012 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
officer | +0.008 |
ma | +0.007 |
sir | +0.006 |
salon | +0.006 |
ily | +0.006 |
Neg logit contributions | |
Fel | -0.010 |
tails | -0.010 |
Bet | -0.010 |
buzzing | -0.009 |
June | -0.009 |
Token | knew |
Token ID | 2993 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
Fel | +1.239 |
tails | +1.222 |
Bet | +1.191 |
buzzing | +1.138 |
Louise | +1.126 |
Neg logit contributions | |
officer | -0.832 |
ma | -0.686 |
salon | -0.676 |
sir | -0.676 |
iza | -0.638 |
Token | something |
Token ID | 1223 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
Fel | +0.093 |
tails | +0.092 |
Bet | +0.090 |
June | +0.085 |
buzzing | +0.084 |
Neg logit contributions | |
officer | -0.051 |
ily | -0.041 |
ma | -0.040 |
salon | -0.039 |
sir | -0.039 |
Token | good |
Token ID | 922 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
officer | +0.029 |
ma | +0.024 |
ily | +0.024 |
kids | +0.023 |
accident | +0.023 |
Neg logit contributions | |
tails | -0.046 |
Fel | -0.046 |
Bet | -0.044 |
June | -0.042 |
Louise | -0.040 |
Token | would |
Token ID | 561 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Fel | +0.019 |
tails | +0.019 |
Bet | +0.019 |
Louise | +0.018 |
buzzing | +0.018 |
Neg logit contributions | |
officer | -0.016 |
salon | -0.014 |
ma | -0.014 |
sir | -0.013 |
iza | -0.013 |
Token | come |
Token ID | 1282 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
tails | +0.237 |
Fel | +0.235 |
Bet | +0.234 |
buzzing | +0.226 |
June | +0.219 |
Neg logit contributions | |
officer | -0.193 |
salon | -0.166 |
ma | -0.160 |
sir | -0.158 |
iza | -0.153 |
Token | to |
Token ID | 284 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Fel | +0.159 |
Bet | +0.151 |
tails | +0.148 |
June | +0.144 |
Louise | +0.140 |
Neg logit contributions | |
officer | -0.086 |
kids | -0.070 |
ma | -0.069 |
salon | -0.068 |
sir | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
officer | +0.015 |
kids | +0.013 |
dad | +0.012 |
Dad | +0.012 |
salon | +0.011 |
Neg logit contributions | |
Fel | -0.054 |
tails | -0.052 |
Bet | -0.052 |
ches | -0.049 |
June | -0.049 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Fel | +0.006 |
tails | +0.006 |
Bet | +0.006 |
June | +0.005 |
Louise | +0.005 |
Neg logit contributions | |
officer | -0.005 |
ma | -0.004 |
salon | -0.004 |
kids | -0.004 |
sir | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Fel | +0.177 |
tails | +0.172 |
Bet | +0.169 |
June | +0.162 |
buzzing | +0.160 |
Neg logit contributions | |
officer | -0.079 |
ma | -0.060 |
salon | -0.060 |
sir | -0.058 |
ily | -0.056 |
Token | But |
Token ID | 887 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ily | +0.029 |
Dad | +0.027 |
Tom | +0.027 |
Sara | +0.027 |
kids | +0.027 |
Neg logit contributions | |
odic | -0.024 |
eds | -0.024 |
leaping | -0.023 |
hovering | -0.023 |
tails | -0.023 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Bet | +0.018 |
oing | +0.018 |
tails | +0.018 |
Fel | +0.018 |
pill | +0.017 |
Neg logit contributions | |
ily | -0.021 |
officer | -0.019 |
kids | -0.019 |
did | -0.019 |
first | -0.018 |
Token | does |
Token ID | 857 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Fel | +1.289 |
Bet | +1.282 |
tails | +1.275 |
June | +1.220 |
Louise | +1.153 |
Neg logit contributions | |
officer | -0.782 |
ma | -0.649 |
salon | -0.630 |
kids | -0.628 |
sir | -0.615 |
Token | not |
Token ID | 407 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Fel | +0.126 |
tails | +0.125 |
Bet | +0.123 |
June | +0.118 |
Louise | +0.115 |
Neg logit contributions | |
officer | -0.051 |
ma | -0.039 |
salon | -0.037 |
sir | -0.037 |
ily | -0.035 |
Token | want |
Token ID | 765 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
officer | +0.064 |
salon | +0.058 |
ople | +0.056 |
cash | +0.054 |
cubes | +0.054 |
Neg logit contributions | |
tails | -0.091 |
buzzing | -0.088 |
Bet | -0.088 |
Fel | -0.087 |
Louise | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
ily | +0.014 |
officer | +0.014 |
kids | +0.012 |
Dad | +0.012 |
dad | +0.010 |
Neg logit contributions | |
Fel | -0.072 |
Bet | -0.071 |
tails | -0.070 |
oing | -0.067 |
oc | -0.066 |
Token | see |
Token ID | 766 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
officer | +0.029 |
salon | +0.024 |
isher | +0.024 |
ma | +0.024 |
iza | +0.023 |
Neg logit contributions | |
tails | -0.040 |
Bet | -0.038 |
Fel | -0.037 |
buzzing | -0.036 |
Louise | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
ily | +0.017 |
Dad | +0.014 |
kids | +0.014 |
Sara | +0.014 |
Tom | +0.014 |
Neg logit contributions | |
tails | -0.032 |
Fel | -0.030 |
odic | -0.030 |
buzzing | -0.030 |
leaping | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
tails | +0.068 |
Fel | +0.062 |
buzzing | +0.061 |
webs | +0.060 |
Bet | +0.060 |
Neg logit contributions | |
ily | -0.020 |
officer | -0.015 |
Dad | -0.014 |
kids | -0.013 |
ma | -0.012 |
Token | " |
Token ID | 1 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
tails | +0.051 |
tal | +0.046 |
Fel | +0.045 |
buzzing | +0.045 |
webs | +0.044 |
Neg logit contributions | |
ily | -0.032 |
kids | -0.025 |
Dad | -0.024 |
ma | -0.024 |
officer | -0.024 |
Token | Look |
Token ID | 8567 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
tails | +0.088 |
Fel | +0.079 |
Louise | +0.076 |
buzzing | +0.075 |
Bet | +0.074 |
Neg logit contributions | |
officer | -0.065 |
ily | -0.061 |
kids | -0.055 |
boy | -0.053 |
salon | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Bet | +0.039 |
Fel | +0.038 |
tails | +0.038 |
June | +0.038 |
buzzing | +0.036 |
Neg logit contributions | |
kids | -0.010 |
ily | -0.010 |
Dad | -0.010 |
dad | -0.009 |
officer | -0.009 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Fel | +0.002 |
tails | +0.002 |
Bet | +0.002 |
June | +0.002 |
itching | +0.002 |
Neg logit contributions | |
officer | -0.002 |
kids | -0.002 |
ily | -0.002 |
sir | -0.002 |
ma | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
Fel | +1.199 |
Bet | +1.134 |
tails | +1.129 |
June | +1.113 |
buzzing | +1.025 |
Neg logit contributions | |
officer | -0.878 |
ma | -0.798 |
sir | -0.769 |
kids | -0.755 |
ily | -0.747 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Fel | +0.005 |
tails | +0.004 |
Bet | +0.004 |
buzzing | +0.004 |
Louise | +0.004 |
Neg logit contributions | |
officer | -0.003 |
salon | -0.002 |
ma | -0.002 |
iza | -0.002 |
sir | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Fel | +0.106 |
tails | +0.101 |
Bet | +0.100 |
June | +0.096 |
Louise | +0.093 |
Neg logit contributions | |
officer | -0.088 |
ma | -0.076 |
kids | -0.073 |
sir | -0.073 |
salon | -0.073 |
Token | Mia |
Token ID | 32189 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
Fel | +0.290 |
tails | +0.290 |
Bet | +0.277 |
leaping | +0.271 |
eds | +0.269 |
Neg logit contributions | |
ily | -0.157 |
officer | -0.154 |
kids | -0.148 |
Dad | -0.136 |
ma | -0.132 |
Token | says |
Token ID | 1139 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Bet | +0.548 |
Fel | +0.546 |
tails | +0.535 |
June | +0.510 |
buzzing | +0.486 |
Neg logit contributions | |
officer | -0.341 |
ma | -0.274 |
kids | -0.274 |
sir | -0.269 |
salon | -0.266 |
Token | lady |
Token ID | 10846 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
officer | +0.002 |
ma | +0.002 |
salon | +0.002 |
sir | +0.002 |
ily | +0.002 |
Neg logit contributions | |
Fel | -0.003 |
tails | -0.003 |
Bet | -0.003 |
buzzing | -0.003 |
June | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
officer | +0.189 |
ma | +0.156 |
salon | +0.151 |
sir | +0.147 |
accident | +0.143 |
Neg logit contributions | |
tails | -0.300 |
Fel | -0.296 |
Bet | -0.289 |
June | -0.274 |
buzzing | -0.274 |
Token | come |
Token ID | 1282 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
officer | +0.029 |
salon | +0.023 |
ma | +0.023 |
sir | +0.023 |
ily | +0.022 |
Neg logit contributions | |
tails | -0.041 |
Fel | -0.041 |
Bet | -0.040 |
buzzing | -0.037 |
June | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
officer | +0.012 |
ma | +0.009 |
sir | +0.009 |
ily | +0.008 |
Dad | +0.008 |
Neg logit contributions | |
Fel | -0.030 |
tails | -0.029 |
Bet | -0.029 |
June | -0.028 |
buzzing | -0.027 |
Token | take |
Token ID | 1011 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
officer | +0.009 |
ma | +0.007 |
salon | +0.007 |
sir | +0.007 |
kids | +0.006 |
Neg logit contributions | |
Fel | -0.014 |
tails | -0.014 |
Bet | -0.013 |
June | -0.013 |
buzzing | -0.013 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
officer | +0.025 |
kids | +0.024 |
ily | +0.023 |
Dad | +0.023 |
dad | +0.021 |
Neg logit contributions | |
Bet | -0.060 |
Fel | -0.058 |
buzzing | -0.055 |
tails | -0.055 |
ousy | -0.054 |
Token | home |
Token ID | 1363 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Fel | +1.327 |
tails | +1.307 |
Bet | +1.284 |
June | +1.218 |
buzzing | +1.208 |
Neg logit contributions | |
officer | -0.761 |
ma | -0.607 |
salon | -0.595 |
sir | -0.584 |
ily | -0.567 |
Token | . |
Token ID | 13 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
officer | +0.121 |
ma | +0.106 |
salon | +0.099 |
sir | +0.099 |
ople | +0.098 |
Neg logit contributions | |
tails | -0.142 |
Fel | -0.131 |
buzzing | -0.130 |
Bet | -0.130 |
Louise | -0.123 |
Token | They |
Token ID | 1119 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Dad | +0.003 |
officer | +0.003 |
ma | +0.003 |
dad | +0.002 |
ily | +0.002 |
Neg logit contributions | |
tails | -0.010 |
Fel | -0.009 |
Bet | -0.009 |
buzzing | -0.009 |
leaping | -0.009 |
Token | are |
Token ID | 389 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Fel | +0.097 |
tails | +0.097 |
Bet | +0.094 |
buzzing | +0.089 |
Louise | +0.088 |
Neg logit contributions | |
officer | -0.065 |
ma | -0.053 |
salon | -0.053 |
sir | -0.052 |
ily | -0.051 |
Token | glad |
Token ID | 9675 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
officer | +0.137 |
ma | +0.116 |
kids | +0.111 |
ily | +0.110 |
sir | +0.107 |
Neg logit contributions | |
Fel | -0.250 |
tails | -0.242 |
Bet | -0.239 |
June | -0.226 |
Louise | -0.218 |
Token | They |
Token ID | 1119 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
tails | +0.008 |
Fel | +0.008 |
buzzing | +0.008 |
Bet | +0.007 |
leaping | +0.007 |
Neg logit contributions | |
officer | -0.003 |
Dad | -0.003 |
ma | -0.003 |
kids | -0.003 |
sir | -0.003 |
Token | jog |
Token ID | 48342 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
Fel | +0.101 |
tails | +0.100 |
Bet | +0.096 |
buzzing | +0.091 |
June | +0.091 |
Neg logit contributions | |
officer | -0.071 |
ma | -0.058 |
salon | -0.058 |
sir | -0.057 |
ily | -0.056 |
Token | with |
Token ID | 351 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
officer | +0.052 |
ma | +0.046 |
sir | +0.044 |
salon | +0.043 |
accident | +0.043 |
Neg logit contributions | |
Fel | -0.067 |
tails | -0.066 |
Bet | -0.062 |
buzzing | -0.060 |
June | -0.060 |
Token | Rex |
Token ID | 17853 |
Feature activation | +7.54e+00 |
Pos logit contributions | |
officer | +0.003 |
kids | +0.003 |
dad | +0.002 |
Dad | +0.002 |
ily | +0.002 |
Neg logit contributions | |
Fel | -0.005 |
Bet | -0.005 |
tails | -0.005 |
oing | -0.005 |
June | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
Fel | +0.789 |
tails | +0.780 |
Bet | +0.765 |
June | +0.728 |
buzzing | +0.723 |
Neg logit contributions | |
officer | -0.403 |
ma | -0.317 |
salon | -0.308 |
sir | -0.302 |
ily | -0.292 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
tails | +0.010 |
buzzing | +0.010 |
Fel | +0.010 |
Bet | +0.010 |
leaping | +0.009 |
Neg logit contributions | |
officer | -0.004 |
Dad | -0.004 |
ma | -0.004 |
kids | -0.003 |
ily | -0.003 |
Token | waves |
Token ID | 9813 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
Fel | +1.108 |
tails | +1.092 |
Bet | +1.061 |
June | +0.998 |
buzzing | +0.993 |
Neg logit contributions | |
officer | -0.972 |
ma | -0.821 |
salon | -0.806 |
sir | -0.797 |
ily | -0.779 |
Token | to |
Token ID | 284 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
officer | +0.038 |
ma | +0.030 |
salon | +0.029 |
sir | +0.029 |
kids | +0.029 |
Neg logit contributions | |
Fel | -0.067 |
tails | -0.066 |
Bet | -0.065 |
June | -0.062 |
buzzing | -0.061 |
Token | them |
Token ID | 606 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
officer | +0.018 |
kids | +0.015 |
dad | +0.014 |
ily | +0.013 |
Dad | +0.013 |
Neg logit contributions | |
Fel | -0.033 |
tails | -0.032 |
Bet | -0.032 |
oing | -0.030 |
June | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
officer | +0.030 |
ma | +0.025 |
sir | +0.024 |
salon | +0.024 |
iza | +0.023 |
Neg logit contributions | |
Fel | -0.053 |
tails | -0.053 |
Bet | -0.050 |
buzzing | -0.049 |
June | -0.048 |
Token | She |
Token ID | 1375 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
tails | +0.011 |
buzzing | +0.011 |
Fel | +0.011 |
itching | +0.011 |
Bet | +0.011 |
Neg logit contributions | |
officer | -0.004 |
Dad | -0.004 |
ily | -0.003 |
ma | -0.003 |
Tommy | -0.003 |
Token | say |
Token ID | 910 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Fel | +0.100 |
tails | +0.099 |
Bet | +0.097 |
buzzing | +0.091 |
June | +0.091 |
Neg logit contributions | |
officer | -0.060 |
ma | -0.048 |
salon | -0.047 |
sir | -0.046 |
ily | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Fel | +0.156 |
tails | +0.154 |
Bet | +0.150 |
June | +0.142 |
buzzing | +0.142 |
Neg logit contributions | |
officer | -0.098 |
ma | -0.080 |
salon | -0.079 |
sir | -0.077 |
ily | -0.074 |
Token | " |
Token ID | 366 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
tails | +0.020 |
Fel | +0.019 |
Bet | +0.018 |
June | +0.018 |
webs | +0.017 |
Neg logit contributions | |
officer | -0.011 |
ma | -0.009 |
sir | -0.008 |
Dad | -0.008 |
kids | -0.008 |
Token | Hello |
Token ID | 15496 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
tails | +0.022 |
Fel | +0.022 |
Bet | +0.020 |
Louise | +0.020 |
webs | +0.020 |
Neg logit contributions | |
officer | -0.012 |
ily | -0.009 |
ma | -0.009 |
kids | -0.009 |
boy | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
kids | +0.100 |
sir | +0.084 |
Dad | +0.081 |
boy | +0.079 |
ma | +0.077 |
Neg logit contributions | |
Bet | -0.388 |
tails | -0.383 |
June | -0.377 |
Fel | -0.374 |
buzzing | -0.355 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
tails | +0.017 |
Bet | +0.016 |
Fel | +0.016 |
June | +0.015 |
itching | +0.015 |
Neg logit contributions | |
kids | -0.014 |
officer | -0.014 |
ma | -0.013 |
sir | -0.013 |
ily | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
Fel | +1.494 |
tails | +1.470 |
Bet | +1.454 |
June | +1.407 |
buzzing | +1.349 |
Neg logit contributions | |
officer | -0.589 |
ma | -0.458 |
sir | -0.448 |
kids | -0.444 |
ily | -0.435 |
Token | We |
Token ID | 775 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
officer | +0.002 |
ma | +0.001 |
ily | +0.001 |
kids | +0.001 |
sir | +0.001 |
Neg logit contributions | |
tails | -0.003 |
Fel | -0.003 |
Bet | -0.003 |
buzzing | -0.003 |
June | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Fel | +0.137 |
tails | +0.136 |
Bet | +0.133 |
June | +0.126 |
buzzing | +0.125 |
Neg logit contributions | |
officer | -0.077 |
ma | -0.061 |
salon | -0.060 |
sir | -0.059 |
ily | -0.056 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
officer | +0.119 |
kids | +0.114 |
ily | +0.107 |
ma | +0.101 |
Dad | +0.101 |
Neg logit contributions | |
Fel | -0.267 |
tails | -0.257 |
Bet | -0.255 |
June | -0.240 |
ches | -0.233 |
Token | to |
Token ID | 284 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
officer | +0.029 |
ma | +0.023 |
salon | +0.022 |
sir | +0.022 |
ily | +0.021 |
Neg logit contributions | |
Fel | -0.054 |
tails | -0.053 |
Bet | -0.052 |
June | -0.050 |
buzzing | -0.049 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Fel | +0.003 |
tails | +0.003 |
Bet | +0.003 |
June | +0.003 |
Louise | +0.003 |
Neg logit contributions | |
officer | -0.003 |
ma | -0.002 |
kids | -0.002 |
salon | -0.002 |
sir | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Fel | +0.140 |
Bet | +0.133 |
tails | +0.131 |
June | +0.128 |
Lou | +0.123 |
Neg logit contributions | |
officer | -0.052 |
ma | -0.039 |
kids | -0.039 |
sir | -0.038 |
salon | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
kids | +0.028 |
ily | +0.028 |
officer | +0.028 |
Dad | +0.026 |
boy | +0.026 |
Neg logit contributions | |
Fel | -0.027 |
odic | -0.026 |
leaping | -0.026 |
Bet | -0.026 |
buzzing | -0.026 |
Token | picks |
Token ID | 11103 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
Bet | +0.070 |
tails | +0.070 |
Fel | +0.070 |
June | +0.066 |
buzzing | +0.063 |
Neg logit contributions | |
officer | -0.049 |
ma | -0.041 |
kids | -0.040 |
salon | -0.040 |
sir | -0.039 |
Token | up |
Token ID | 510 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
kids | +0.030 |
ily | +0.029 |
officer | +0.029 |
right | +0.027 |
Dad | +0.025 |
Neg logit contributions | |
Fel | -0.110 |
Bet | -0.109 |
tails | -0.108 |
elope | -0.105 |
June | -0.102 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Fel | +0.228 |
Bet | +0.227 |
tails | +0.222 |
June | +0.214 |
elope | +0.209 |
Neg logit contributions | |
officer | -0.077 |
kids | -0.072 |
ily | -0.066 |
Dad | -0.064 |
dad | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Fel | +1.507 |
Bet | +1.493 |
tails | +1.468 |
June | +1.417 |
Lou | +1.335 |
Neg logit contributions | |
officer | -0.560 |
ma | -0.414 |
kids | -0.408 |
salon | -0.405 |
sir | -0.389 |
Token | carries |
Token ID | 10732 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
officer | +0.020 |
kids | +0.017 |
dad | +0.017 |
Dad | +0.016 |
ma | +0.016 |
Neg logit contributions | |
Bet | -0.039 |
Fel | -0.037 |
June | -0.036 |
tails | -0.035 |
buzzing | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Bet | +0.252 |
oing | +0.243 |
Fel | +0.242 |
itching | +0.239 |
odic | +0.239 |
Neg logit contributions | |
ily | -0.181 |
officer | -0.170 |
kids | -0.168 |
Dad | -0.158 |
Tom | -0.156 |
Token | to |
Token ID | 284 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Fel | +0.159 |
Bet | +0.151 |
tails | +0.148 |
June | +0.144 |
Louise | +0.140 |
Neg logit contributions | |
officer | -0.086 |
kids | -0.070 |
ma | -0.069 |
salon | -0.068 |
sir | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
officer | +0.015 |
kids | +0.013 |
dad | +0.012 |
Dad | +0.012 |
salon | +0.011 |
Neg logit contributions | |
Fel | -0.054 |
tails | -0.052 |
Bet | -0.052 |
ches | -0.049 |
June | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Fel | +0.141 |
Bet | +0.134 |
June | +0.130 |
tails | +0.130 |
Louise | +0.125 |
Neg logit contributions | |
officer | -0.050 |
kids | -0.039 |
salon | -0.036 |
accident | -0.036 |
ma | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
officer | +0.024 |
kids | +0.023 |
ily | +0.023 |
Dad | +0.022 |
ma | +0.022 |
Neg logit contributions | |
Fel | -0.035 |
tails | -0.034 |
Bet | -0.033 |
June | -0.033 |
odic | -0.033 |
Token | wants |
Token ID | 3382 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Bet | +0.076 |
Fel | +0.076 |
tails | +0.076 |
June | +0.071 |
buzzing | +0.068 |
Neg logit contributions | |
officer | -0.040 |
kids | -0.033 |
ma | -0.033 |
salon | -0.031 |
ily | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
Fel | +0.090 |
tails | +0.085 |
Bet | +0.084 |
oc | +0.082 |
elope | +0.082 |
Neg logit contributions | |
officer | -0.018 |
kids | -0.017 |
Dad | -0.016 |
dad | -0.015 |
ily | -0.014 |
Token | show |
Token ID | 905 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
officer | +0.026 |
ma | +0.022 |
kids | +0.021 |
salon | +0.021 |
sir | +0.021 |
Neg logit contributions | |
Fel | -0.046 |
tails | -0.044 |
Bet | -0.043 |
June | -0.042 |
Louise | -0.040 |
Token | Luna |
Token ID | 23694 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Bet | +0.171 |
Fel | +0.166 |
oing | +0.161 |
odic | +0.156 |
oc | +0.156 |
Neg logit contributions | |
officer | -0.163 |
kids | -0.160 |
ily | -0.156 |
dad | -0.152 |
Dad | -0.152 |
Token | the |
Token ID | 262 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
Fel | +1.449 |
Bet | +1.432 |
tails | +1.415 |
June | +1.358 |
buzzing | +1.293 |
Neg logit contributions | |
officer | -0.598 |
ily | -0.477 |
kids | -0.476 |
ma | -0.463 |
salon | -0.453 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Fel | +0.003 |
tails | +0.003 |
Bet | +0.003 |
June | +0.003 |
Louise | +0.003 |
Neg logit contributions | |
officer | -0.003 |
ma | -0.002 |
kids | -0.002 |
salon | -0.002 |
sir | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Fel | +0.140 |
Bet | +0.133 |
tails | +0.131 |
June | +0.128 |
Lou | +0.123 |
Neg logit contributions | |
officer | -0.052 |
ma | -0.039 |
kids | -0.039 |
sir | -0.038 |
salon | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
kids | +0.028 |
ily | +0.028 |
officer | +0.028 |
Dad | +0.026 |
boy | +0.026 |
Neg logit contributions | |
Fel | -0.027 |
odic | -0.026 |
leaping | -0.026 |
Bet | -0.026 |
buzzing | -0.026 |
Token | picks |
Token ID | 11103 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
Bet | +0.070 |
tails | +0.070 |
Fel | +0.070 |
June | +0.066 |
buzzing | +0.063 |
Neg logit contributions | |
officer | -0.049 |
ma | -0.041 |
kids | -0.040 |
salon | -0.040 |
sir | -0.039 |
Token | had |
Token ID | 550 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
Fel | +0.064 |
tails | +0.064 |
Bet | +0.062 |
June | +0.059 |
Louise | +0.058 |
Neg logit contributions | |
officer | -0.034 |
ma | -0.027 |
salon | -0.026 |
kids | -0.025 |
sir | -0.025 |
Token | done |
Token ID | 1760 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
Fel | +0.001 |
tails | +0.001 |
Bet | +0.001 |
buzzing | +0.001 |
June | +0.001 |
Neg logit contributions | |
officer | -0.000 |
sir | -0.000 |
ma | -0.000 |
salon | -0.000 |
ily | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
officer | +0.224 |
ma | +0.188 |
salon | +0.185 |
kids | +0.180 |
accident | +0.178 |
Neg logit contributions | |
Fel | -0.407 |
tails | -0.405 |
Bet | -0.402 |
June | -0.378 |
Louise | -0.361 |
Token | ! |
Token ID | 0 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
Fel | +0.077 |
tails | +0.076 |
Bet | +0.075 |
June | +0.069 |
buzzing | +0.068 |
Neg logit contributions | |
officer | -0.067 |
ma | -0.057 |
salon | -0.056 |
sir | -0.055 |
ily | -0.055 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
Fel | +0.482 |
tails | +0.477 |
Bet | +0.463 |
June | +0.435 |
buzzing | +0.434 |
Neg logit contributions | |
officer | -0.416 |
ma | -0.351 |
salon | -0.343 |
sir | -0.339 |
ily | -0.335 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
officer | +0.159 |
ma | +0.129 |
sir | +0.125 |
Dad | +0.116 |
kids | +0.113 |
Neg logit contributions | |
Fel | -0.472 |
tails | -0.457 |
Bet | -0.445 |
June | -0.438 |
buzzing | -0.421 |
Token | skipped |
Token ID | 26684 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
officer | +0.781 |
ma | +0.660 |
sir | +0.654 |
salon | +0.637 |
kids | +0.612 |
Neg logit contributions | |
tails | -0.924 |
Fel | -0.908 |
Bet | -0.876 |
buzzing | -0.845 |
June | -0.830 |
Token | home |
Token ID | 1363 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Fel | +0.012 |
tails | +0.012 |
Bet | +0.012 |
June | +0.011 |
buzzing | +0.011 |
Neg logit contributions | |
officer | -0.008 |
ma | -0.007 |
salon | -0.007 |
ily | -0.007 |
kids | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
officer | +0.122 |
ma | +0.099 |
sir | +0.098 |
salon | +0.097 |
ily | +0.096 |
Neg logit contributions | |
tails | -0.164 |
Fel | -0.163 |
Bet | -0.156 |
buzzing | -0.154 |
Louise | -0.149 |
Token | full |
Token ID | 1336 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
officer | +0.011 |
ma | +0.009 |
salon | +0.009 |
sir | +0.009 |
kids | +0.009 |
Neg logit contributions | |
Fel | -0.018 |
tails | -0.018 |
Bet | -0.018 |
June | -0.017 |
buzzing | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Fel | +0.115 |
tails | +0.114 |
Bet | +0.113 |
buzzing | +0.111 |
Louise | +0.107 |
Neg logit contributions | |
officer | -0.084 |
salon | -0.066 |
sir | -0.065 |
ma | -0.065 |
ople | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Fel | +0.022 |
tails | +0.022 |
Bet | +0.021 |
June | +0.020 |
buzzing | +0.020 |
Neg logit contributions | |
officer | -0.010 |
ma | -0.008 |
salon | -0.008 |
sir | -0.007 |
ily | -0.007 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
officer | +0.032 |
ma | +0.025 |
sir | +0.024 |
salon | +0.024 |
ily | +0.023 |
Neg logit contributions | |
Fel | -0.065 |
tails | -0.064 |
Bet | -0.062 |
June | -0.060 |
buzzing | -0.059 |
Token | my |
Token ID | 1820 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
officer | +0.084 |
salon | +0.073 |
sir | +0.072 |
ma | +0.072 |
iza | +0.067 |
Neg logit contributions | |
tails | -0.097 |
Fel | -0.095 |
Bet | -0.095 |
June | -0.090 |
buzzing | -0.088 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Fel | +0.022 |
tails | +0.022 |
Bet | +0.021 |
June | +0.020 |
buzzing | +0.020 |
Neg logit contributions | |
officer | -0.015 |
ma | -0.013 |
salon | -0.012 |
sir | -0.012 |
ily | -0.012 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
officer | +0.022 |
ma | +0.018 |
salon | +0.017 |
sir | +0.017 |
kids | +0.017 |
Neg logit contributions | |
Fel | -0.039 |
tails | -0.039 |
Bet | -0.038 |
June | -0.036 |
buzzing | -0.036 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
kids | +0.100 |
ma | +0.098 |
Dad | +0.096 |
officer | +0.096 |
boy | +0.091 |
Neg logit contributions | |
Fel | -0.164 |
tails | -0.161 |
Bet | -0.161 |
June | -0.156 |
buzzing | -0.145 |
Token | days |
Token ID | 12545 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
officer | +0.742 |
ma | +0.662 |
sir | +0.622 |
salon | +0.588 |
kids | +0.567 |
Neg logit contributions | |
tails | -0.960 |
Fel | -0.925 |
Bet | -0.920 |
buzzing | -0.880 |
June | -0.862 |
Token | because |
Token ID | 780 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
officer | +0.212 |
ma | +0.191 |
sir | +0.185 |
iza | +0.180 |
salon | +0.176 |
Neg logit contributions | |
tails | -0.249 |
Fel | -0.247 |
Bet | -0.227 |
buzzing | -0.224 |
June | -0.216 |
Token | that |
Token ID | 326 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
Fel | +0.052 |
tails | +0.049 |
Felix | +0.048 |
Bet | +0.047 |
buzzing | +0.046 |
Neg logit contributions | |
officer | -0.042 |
ma | -0.037 |
sir | -0.035 |
iza | -0.035 |
salon | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
officer | +0.035 |
iza | +0.032 |
ople | +0.031 |
sir | +0.030 |
ily | +0.030 |
Neg logit contributions | |
Fel | -0.046 |
tails | -0.045 |
buzzing | -0.042 |
Bet | -0.041 |
Felix | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Fel | +0.107 |
tails | +0.106 |
Bet | +0.103 |
buzzing | +0.101 |
June | +0.096 |
Neg logit contributions | |
officer | -0.095 |
ople | -0.081 |
ma | -0.080 |
sir | -0.080 |
salon | -0.078 |
Token | always |
Token ID | 1464 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
officer | +0.114 |
kids | +0.100 |
ma | +0.096 |
Dad | +0.095 |
dad | +0.092 |
Neg logit contributions | |
Fel | -0.245 |
Bet | -0.235 |
tails | -0.231 |
June | -0.221 |
ches | -0.212 |
Token | so |
Token ID | 523 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
officer | +0.169 |
kids | +0.145 |
ma | +0.143 |
Dad | +0.137 |
iza | +0.134 |
Neg logit contributions | |
Fel | -0.264 |
Bet | -0.253 |
tails | -0.252 |
June | -0.236 |
ches | -0.228 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
officer | +0.015 |
salon | +0.013 |
ma | +0.012 |
sir | +0.012 |
ily | +0.012 |
Neg logit contributions | |
Fel | -0.019 |
tails | -0.018 |
Bet | -0.018 |
buzzing | -0.017 |
June | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
officer | +0.030 |
kids | +0.025 |
ma | +0.024 |
sir | +0.023 |
Dad | +0.023 |
Neg logit contributions | |
Fel | -0.057 |
tails | -0.056 |
Bet | -0.056 |
June | -0.053 |
Louise | -0.051 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Fel | +0.247 |
tails | +0.245 |
Bet | +0.244 |
June | +0.232 |
webs | +0.225 |
Neg logit contributions | |
officer | -0.115 |
Dad | -0.100 |
ma | -0.098 |
kids | -0.098 |
dad | -0.095 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
officer | +0.080 |
kids | +0.069 |
ma | +0.066 |
Dad | +0.063 |
boy | +0.063 |
Neg logit contributions | |
tails | -0.183 |
Fel | -0.183 |
Bet | -0.180 |
June | -0.176 |
buzzing | -0.169 |
Token | days |
Token ID | 12545 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
officer | +0.581 |
salon | +0.453 |
ily | +0.450 |
ma | +0.447 |
iza | +0.442 |
Neg logit contributions | |
Fel | -1.118 |
Bet | -1.067 |
tails | -1.062 |
June | -1.005 |
buzzing | -0.994 |
Token | because |
Token ID | 780 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
officer | +0.196 |
ma | +0.170 |
salon | +0.164 |
sir | +0.163 |
iza | +0.159 |
Neg logit contributions | |
tails | -0.274 |
Fel | -0.270 |
Bet | -0.254 |
buzzing | -0.249 |
June | -0.245 |
Token | of |
Token ID | 286 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Fel | +0.059 |
tails | +0.058 |
Bet | +0.057 |
June | +0.054 |
buzzing | +0.053 |
Neg logit contributions | |
officer | -0.042 |
ma | -0.034 |
salon | -0.034 |
sir | -0.033 |
ily | -0.032 |
Token | their |
Token ID | 511 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Fel | +0.034 |
tails | +0.034 |
Bet | +0.033 |
June | +0.031 |
Louise | +0.030 |
Neg logit contributions | |
officer | -0.018 |
kids | -0.015 |
ma | -0.015 |
Dad | -0.014 |
salon | -0.014 |
Token | lucky |
Token ID | 9670 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Fel | +0.043 |
tails | +0.043 |
Bet | +0.041 |
buzzing | +0.039 |
June | +0.039 |
Neg logit contributions | |
officer | -0.035 |
ma | -0.029 |
salon | -0.029 |
sir | -0.028 |
ily | -0.028 |
Token | over |
Token ID | 625 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
officer | +0.246 |
sir | +0.216 |
ma | +0.207 |
salon | +0.204 |
cash | +0.201 |
Neg logit contributions | |
tails | -0.249 |
buzzing | -0.247 |
Bet | -0.244 |
Fel | -0.242 |
June | -0.231 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Fel | +0.140 |
tails | +0.137 |
Bet | +0.137 |
buzzing | +0.129 |
June | +0.128 |
Neg logit contributions | |
officer | -0.105 |
ma | -0.087 |
sir | -0.085 |
salon | -0.082 |
ily | -0.079 |
Token | place |
Token ID | 1295 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
officer | +0.009 |
sir | +0.008 |
ma | +0.008 |
iza | +0.008 |
ateful | +0.008 |
Neg logit contributions | |
Fel | -0.013 |
tails | -0.013 |
buzzing | -0.013 |
Bet | -0.012 |
webs | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
tails | +0.049 |
Fel | +0.046 |
Bet | +0.046 |
buzzing | +0.046 |
Louise | +0.044 |
Neg logit contributions | |
officer | -0.036 |
ma | -0.030 |
sir | -0.028 |
salon | -0.027 |
iza | -0.027 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
officer | +0.041 |
sir | +0.035 |
ma | +0.035 |
accident | +0.035 |
salon | +0.035 |
Neg logit contributions | |
Fel | -0.037 |
Bet | -0.036 |
tails | -0.035 |
Louise | -0.033 |
June | -0.033 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
officer | +0.176 |
ma | +0.158 |
sir | +0.156 |
Dad | +0.154 |
kids | +0.144 |
Neg logit contributions | |
Fel | -0.449 |
tails | -0.427 |
Bet | -0.421 |
June | -0.417 |
ches | -0.405 |
Token | said |
Token ID | 531 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
officer | +0.789 |
ma | +0.697 |
sir | +0.691 |
salon | +0.654 |
cash | +0.638 |
Neg logit contributions | |
tails | -0.880 |
Fel | -0.839 |
Bet | -0.826 |
buzzing | -0.803 |
Louise | -0.778 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
officer | +0.045 |
ople | +0.040 |
salon | +0.038 |
ma | +0.038 |
ateful | +0.038 |
Neg logit contributions | |
Fel | -0.053 |
tails | -0.051 |
Bet | -0.049 |
buzzing | -0.048 |
Louise | -0.048 |
Token | � |
Token ID | 6184 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
officer | +0.025 |
salon | +0.023 |
ople | +0.023 |
ateful | +0.022 |
cubes | +0.022 |
Neg logit contributions | |
Fel | -0.024 |
Bet | -0.022 |
tails | -0.022 |
Louise | -0.021 |
buzzing | -0.021 |
Token | � |
Token ID | 95 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
officer | +0.033 |
cubes | +0.029 |
kids | +0.029 |
ma | +0.028 |
dad | +0.027 |
Neg logit contributions | |
Fel | -0.035 |
tails | -0.030 |
Bet | -0.029 |
buzzing | -0.028 |
Louise | -0.027 |
Token | € |
Token ID | 26391 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
officer | +0.217 |
cubes | +0.200 |
sir | +0.192 |
dad | +0.191 |
Dad | +0.187 |
Neg logit contributions | |
Fel | -0.229 |
Bet | -0.204 |
tails | -0.203 |
June | -0.202 |
Louise | -0.193 |
Token | was |
Token ID | 373 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
officer | +0.344 |
ma | +0.276 |
salon | +0.269 |
sir | +0.265 |
ily | +0.256 |
Neg logit contributions | |
Fel | -0.594 |
tails | -0.587 |
Bet | -0.574 |
June | -0.545 |
buzzing | -0.542 |
Token | always |
Token ID | 1464 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
Fel | +0.115 |
tails | +0.114 |
Bet | +0.111 |
June | +0.104 |
buzzing | +0.103 |
Neg logit contributions | |
officer | -0.089 |
ma | -0.075 |
salon | -0.074 |
sir | -0.072 |
ily | -0.071 |
Token | excited |
Token ID | 6568 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
officer | +0.203 |
ma | +0.169 |
salon | +0.166 |
sir | +0.164 |
ily | +0.160 |
Neg logit contributions | |
Fel | -0.250 |
tails | -0.247 |
Bet | -0.240 |
buzzing | -0.228 |
June | -0.226 |
Token | for |
Token ID | 329 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
officer | +0.030 |
ma | +0.025 |
salon | +0.025 |
sir | +0.024 |
iza | +0.024 |
Neg logit contributions | |
tails | -0.042 |
Fel | -0.042 |
Bet | -0.040 |
buzzing | -0.040 |
Louise | -0.039 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Fel | +0.155 |
tails | +0.153 |
Bet | +0.145 |
buzzing | +0.144 |
Louise | +0.143 |
Neg logit contributions | |
officer | -0.115 |
salon | -0.095 |
sir | -0.094 |
ma | -0.093 |
ily | -0.087 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
officer | +0.095 |
kids | +0.094 |
boy | +0.087 |
ma | +0.084 |
knee | +0.082 |
Neg logit contributions | |
Fel | -0.158 |
Bet | -0.156 |
June | -0.153 |
tails | -0.151 |
buzzing | -0.143 |
Token | days |
Token ID | 12545 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
officer | +0.616 |
ma | +0.492 |
salon | +0.482 |
sir | +0.473 |
ily | +0.459 |
Neg logit contributions | |
Fel | -1.070 |
tails | -1.055 |
Bet | -1.033 |
June | -0.982 |
buzzing | -0.975 |
Token | because |
Token ID | 780 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
officer | +0.204 |
ma | +0.183 |
ily | +0.176 |
iza | +0.175 |
salon | +0.174 |
Neg logit contributions | |
tails | -0.250 |
Fel | -0.246 |
Bet | -0.226 |
Louise | -0.220 |
buzzing | -0.220 |
Token | it |
Token ID | 340 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
Fel | +0.052 |
tails | +0.049 |
Felix | +0.047 |
Bet | +0.047 |
Louise | +0.047 |
Neg logit contributions | |
officer | -0.037 |
ma | -0.031 |
salon | -0.030 |
sir | -0.029 |
iza | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Fel | +0.077 |
tails | +0.077 |
Bet | +0.075 |
June | +0.070 |
buzzing | +0.069 |
Neg logit contributions | |
officer | -0.058 |
ma | -0.048 |
salon | -0.047 |
sir | -0.046 |
kids | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Fel | +0.126 |
tails | +0.124 |
Bet | +0.122 |
June | +0.115 |
buzzing | +0.115 |
Neg logit contributions | |
officer | -0.081 |
ma | -0.066 |
salon | -0.065 |
sir | -0.064 |
ily | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Fel | +0.021 |
tails | +0.021 |
Bet | +0.021 |
June | +0.020 |
Louise | +0.020 |
Neg logit contributions | |
officer | -0.009 |
ma | -0.007 |
salon | -0.007 |
sir | -0.007 |
ily | -0.007 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
officer | +0.031 |
ma | +0.024 |
sir | +0.023 |
salon | +0.023 |
ily | +0.022 |
Neg logit contributions | |
Fel | -0.062 |
tails | -0.061 |
Bet | -0.060 |
June | -0.057 |
buzzing | -0.057 |
Token | my |
Token ID | 1820 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
officer | +0.080 |
sir | +0.070 |
salon | +0.070 |
ma | +0.069 |
iza | +0.064 |
Neg logit contributions | |
tails | -0.098 |
Fel | -0.095 |
Bet | -0.095 |
June | -0.090 |
buzzing | -0.089 |
Token | loved |
Token ID | 6151 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Fel | +0.021 |
tails | +0.021 |
Bet | +0.020 |
June | +0.019 |
buzzing | +0.019 |
Neg logit contributions | |
officer | -0.015 |
ma | -0.012 |
salon | -0.012 |
sir | -0.012 |
iza | -0.011 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
officer | +0.026 |
ma | +0.021 |
salon | +0.020 |
sir | +0.020 |
ily | +0.020 |
Neg logit contributions | |
Fel | -0.046 |
tails | -0.046 |
Bet | -0.045 |
June | -0.042 |
buzzing | -0.042 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
ma | +0.093 |
officer | +0.093 |
kids | +0.092 |
Dad | +0.088 |
sir | +0.084 |
Neg logit contributions | |
tails | -0.162 |
Fel | -0.161 |
Bet | -0.159 |
June | -0.154 |
buzzing | -0.145 |
Token | days |
Token ID | 12545 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
officer | +0.713 |
ma | +0.624 |
sir | +0.591 |
salon | +0.566 |
kids | +0.541 |
Neg logit contributions | |
tails | -0.970 |
Fel | -0.941 |
Bet | -0.935 |
buzzing | -0.893 |
June | -0.878 |
Token | because |
Token ID | 780 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
officer | +0.203 |
ma | +0.182 |
sir | +0.176 |
iza | +0.169 |
salon | +0.167 |
Neg logit contributions | |
tails | -0.255 |
Fel | -0.253 |
Bet | -0.234 |
buzzing | -0.232 |
June | -0.224 |
Token | that |
Token ID | 326 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Fel | +0.053 |
tails | +0.049 |
Felix | +0.048 |
Bet | +0.047 |
buzzing | +0.047 |
Neg logit contributions | |
officer | -0.042 |
ma | -0.036 |
sir | -0.035 |
salon | -0.035 |
iza | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
officer | +0.040 |
iza | +0.035 |
ople | +0.034 |
sir | +0.034 |
salon | +0.033 |
Neg logit contributions | |
Fel | -0.054 |
tails | -0.053 |
buzzing | -0.050 |
Bet | -0.050 |
June | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Fel | +0.102 |
tails | +0.101 |
Bet | +0.099 |
buzzing | +0.097 |
June | +0.092 |
Neg logit contributions | |
officer | -0.089 |
ople | -0.075 |
ma | -0.075 |
sir | -0.075 |
salon | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
tails | +0.531 |
Fel | +0.528 |
Bet | +0.498 |
buzzing | +0.489 |
June | +0.470 |
Neg logit contributions | |
officer | -0.405 |
ma | -0.343 |
sir | -0.331 |
salon | -0.325 |
ily | -0.322 |
Token |
|
Token ID | 198 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
tails | +0.066 |
Fel | +0.060 |
buzzing | +0.058 |
Bet | +0.057 |
webs | +0.057 |
Neg logit contributions | |
officer | -0.034 |
ily | -0.031 |
ma | -0.027 |
iza | -0.026 |
kids | -0.026 |
Token | So |
Token ID | 2396 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
tails | +0.058 |
Fel | +0.051 |
buzzing | +0.051 |
webs | +0.051 |
Louise | +0.049 |
Neg logit contributions | |
officer | -0.040 |
ily | -0.036 |
ma | -0.034 |
iza | -0.033 |
salon | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Fel | +0.055 |
tails | +0.054 |
Bet | +0.053 |
June | +0.050 |
buzzing | +0.050 |
Neg logit contributions | |
officer | -0.039 |
ma | -0.032 |
salon | -0.031 |
sir | -0.031 |
kids | -0.030 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
officer | +0.014 |
ma | +0.012 |
salon | +0.011 |
kids | +0.011 |
sir | +0.011 |
Neg logit contributions | |
Fel | -0.021 |
tails | -0.021 |
Bet | -0.020 |
June | -0.019 |
buzzing | -0.019 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.185 |
ma | +0.154 |
sir | +0.144 |
kids | +0.143 |
salon | +0.139 |
Neg logit contributions | |
Fel | -0.428 |
tails | -0.420 |
Bet | -0.415 |
June | -0.401 |
Louise | -0.385 |
Token | resisted |
Token ID | 26643 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
officer | +0.687 |
ma | +0.584 |
sir | +0.563 |
salon | +0.558 |
ily | +0.535 |
Neg logit contributions | |
tails | -0.993 |
Fel | -0.957 |
Bet | -0.941 |
buzzing | -0.898 |
June | -0.887 |
Token | and |
Token ID | 290 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
officer | +0.099 |
ma | +0.080 |
salon | +0.079 |
sir | +0.078 |
ily | +0.076 |
Neg logit contributions | |
Fel | -0.145 |
tails | -0.144 |
Bet | -0.140 |
buzzing | -0.133 |
June | -0.133 |
Token | eventually |
Token ID | 4191 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
officer | +0.034 |
ma | +0.028 |
salon | +0.027 |
sir | +0.027 |
ily | +0.026 |
Neg logit contributions | |
Fel | -0.047 |
tails | -0.047 |
Bet | -0.046 |
buzzing | -0.043 |
June | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Fel | +0.246 |
tails | +0.246 |
Bet | +0.240 |
buzzing | +0.226 |
Louise | +0.226 |
Neg logit contributions | |
officer | -0.184 |
salon | -0.150 |
ma | -0.149 |
sir | -0.149 |
kids | -0.141 |
Token | wall |
Token ID | 3355 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
officer | +0.013 |
ma | +0.011 |
salon | +0.011 |
sir | +0.011 |
iza | +0.011 |
Neg logit contributions | |
Fel | -0.020 |
tails | -0.020 |
Bet | -0.019 |
buzzing | -0.018 |
June | -0.018 |
Token | aches |
Token ID | 3694 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
officer | +0.134 |
ma | +0.106 |
sir | +0.102 |
salon | +0.100 |
accident | +0.097 |
Neg logit contributions | |
tails | -0.206 |
Fel | -0.201 |
Bet | -0.194 |
buzzing | -0.190 |
June | -0.183 |
Token | on |
Token ID | 319 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
officer | +0.272 |
ma | +0.216 |
salon | +0.213 |
accident | +0.209 |
sir | +0.203 |
Neg logit contributions | |
tails | -0.322 |
Fel | -0.315 |
Bet | -0.309 |
buzzing | -0.297 |
Louise | -0.296 |
Token | Mondays |
Token ID | 49748 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Fel | +0.222 |
tails | +0.220 |
Bet | +0.215 |
June | +0.203 |
buzzing | +0.202 |
Neg logit contributions | |
officer | -0.142 |
ma | -0.116 |
salon | -0.113 |
sir | -0.111 |
ily | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
officer | +0.068 |
ma | +0.053 |
ily | +0.053 |
salon | +0.051 |
iza | +0.051 |
Neg logit contributions | |
tails | -0.101 |
Fel | -0.098 |
Bet | -0.095 |
buzzing | -0.091 |
Louise | -0.091 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
officer | +0.021 |
ma | +0.016 |
salon | +0.016 |
sir | +0.016 |
ily | +0.015 |
Neg logit contributions | |
Fel | -0.037 |
tails | -0.036 |
Bet | -0.035 |
June | -0.034 |
buzzing | -0.033 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.090 |
cubes | +0.089 |
kids | +0.088 |
boy | +0.081 |
knee | +0.080 |
Neg logit contributions | |
Bet | -0.168 |
Fel | -0.166 |
June | -0.166 |
tails | -0.165 |
Louise | -0.155 |
Token | days |
Token ID | 12545 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
officer | +0.703 |
ma | +0.588 |
sir | +0.560 |
salon | +0.549 |
kids | +0.543 |
Neg logit contributions | |
tails | -0.982 |
Fel | -0.964 |
Bet | -0.947 |
June | -0.893 |
buzzing | -0.890 |
Token | , |
Token ID | 11 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
officer | +0.217 |
ma | +0.176 |
sir | +0.171 |
salon | +0.170 |
iza | +0.168 |
Neg logit contributions | |
tails | -0.262 |
Fel | -0.261 |
Bet | -0.249 |
buzzing | -0.238 |
June | -0.236 |
Token | and |
Token ID | 290 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
officer | +0.019 |
ma | +0.016 |
salon | +0.015 |
sir | +0.015 |
kids | +0.014 |
Neg logit contributions | |
Fel | -0.036 |
tails | -0.036 |
Bet | -0.035 |
June | -0.033 |
buzzing | -0.033 |
Token | Fridays |
Token ID | 45011 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
officer | +0.028 |
ma | +0.023 |
sir | +0.022 |
salon | +0.022 |
kids | +0.022 |
Neg logit contributions | |
Fel | -0.056 |
tails | -0.054 |
Bet | -0.054 |
June | -0.051 |
buzzing | -0.050 |
Token | ." |
Token ID | 526 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Fel | +0.026 |
Bet | +0.026 |
tails | +0.025 |
June | +0.024 |
buzzing | +0.024 |
Neg logit contributions | |
officer | -0.013 |
ma | -0.011 |
salon | -0.010 |
sir | -0.010 |
kids | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
Fel | +0.194 |
Bet | +0.187 |
tails | +0.186 |
June | +0.177 |
buzzing | +0.171 |
Neg logit contributions | |
officer | -0.124 |
ma | -0.102 |
sir | -0.099 |
kids | -0.097 |
ily | -0.096 |
Token | special |
Token ID | 2041 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
officer | +0.015 |
ma | +0.013 |
salon | +0.012 |
sir | +0.012 |
kids | +0.012 |
Neg logit contributions | |
Fel | -0.021 |
tails | -0.021 |
Bet | -0.021 |
June | -0.020 |
Louise | -0.019 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
tails | +0.040 |
Fel | +0.040 |
Bet | +0.038 |
buzzing | +0.037 |
Louise | +0.036 |
Neg logit contributions | |
officer | -0.029 |
ma | -0.024 |
salon | -0.024 |
sir | -0.023 |
ily | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
tails | +0.145 |
Fel | +0.140 |
Bet | +0.135 |
buzzing | +0.132 |
Louise | +0.129 |
Neg logit contributions | |
officer | -0.094 |
ma | -0.081 |
salon | -0.078 |
iza | -0.077 |
sir | -0.075 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Fel | +0.161 |
tails | +0.160 |
Bet | +0.155 |
June | +0.148 |
buzzing | +0.147 |
Neg logit contributions | |
officer | -0.106 |
ma | -0.086 |
salon | -0.085 |
sir | -0.083 |
ily | -0.081 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.093 |
kids | +0.092 |
boy | +0.090 |
Dad | +0.085 |
ma | +0.082 |
Neg logit contributions | |
Fel | -0.166 |
Bet | -0.162 |
tails | -0.162 |
June | -0.160 |
ches | -0.156 |
Token | days |
Token ID | 12545 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
officer | +0.709 |
ma | +0.606 |
salon | +0.579 |
sir | +0.569 |
kids | +0.543 |
Neg logit contributions | |
tails | -0.970 |
Fel | -0.947 |
Bet | -0.930 |
June | -0.878 |
buzzing | -0.875 |
Token | ." |
Token ID | 526 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
officer | +0.193 |
ma | +0.166 |
salon | +0.161 |
iza | +0.159 |
cash | +0.153 |
Neg logit contributions | |
tails | -0.268 |
Fel | -0.253 |
Bet | -0.236 |
buzzing | -0.236 |
Louise | -0.234 |
Token |
|
Token ID | 198 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
officer | +0.155 |
ma | +0.130 |
salon | +0.127 |
sir | +0.126 |
ily | +0.123 |
Neg logit contributions | |
Fel | -0.186 |
tails | -0.184 |
Bet | -0.179 |
buzzing | -0.168 |
June | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
tails | +0.033 |
Fel | +0.032 |
Bet | +0.032 |
buzzing | +0.030 |
Louise | +0.030 |
Neg logit contributions | |
officer | -0.020 |
ily | -0.016 |
ma | -0.015 |
kids | -0.015 |
salon | -0.014 |
Token | L |
Token ID | 43 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
tails | +0.034 |
Fel | +0.034 |
Bet | +0.033 |
buzzing | +0.031 |
June | +0.031 |
Neg logit contributions | |
officer | -0.019 |
ma | -0.015 |
salon | -0.015 |
sir | -0.014 |
ily | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Fel | +0.299 |
tails | +0.295 |
Bet | +0.289 |
June | +0.273 |
buzzing | +0.270 |
Neg logit contributions | |
officer | -0.212 |
ma | -0.176 |
salon | -0.171 |
sir | -0.170 |
ily | -0.165 |
Token | so |
Token ID | 523 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
tails | +0.174 |
Fel | +0.171 |
buzzing | +0.160 |
Bet | +0.159 |
Louise | +0.157 |
Neg logit contributions | |
officer | -0.139 |
ma | -0.120 |
salon | -0.117 |
sir | -0.113 |
ople | -0.113 |
Token | special |
Token ID | 2041 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
officer | +0.015 |
ma | +0.012 |
salon | +0.012 |
sir | +0.012 |
ily | +0.011 |
Neg logit contributions | |
Fel | -0.018 |
tails | -0.017 |
Bet | -0.017 |
buzzing | -0.016 |
June | -0.016 |
Token | about |
Token ID | 546 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
tails | +0.048 |
Fel | +0.048 |
Bet | +0.046 |
buzzing | +0.046 |
Louise | +0.045 |
Neg logit contributions | |
officer | -0.023 |
ma | -0.018 |
salon | -0.018 |
iza | -0.017 |
ily | -0.016 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
officer | +0.142 |
kids | +0.120 |
Dad | +0.117 |
dad | +0.115 |
sir | +0.115 |
Neg logit contributions | |
Fel | -0.266 |
Bet | -0.262 |
tails | -0.253 |
June | -0.244 |
elope | -0.228 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.094 |
kids | +0.084 |
boy | +0.083 |
Dad | +0.080 |
knee | +0.079 |
Neg logit contributions | |
Fel | -0.170 |
Bet | -0.169 |
tails | -0.167 |
June | -0.165 |
buzzing | -0.158 |
Token | days |
Token ID | 12545 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
officer | +0.607 |
ma | +0.490 |
salon | +0.470 |
sir | +0.459 |
ily | +0.437 |
Neg logit contributions | |
tails | -1.066 |
Fel | -1.059 |
Bet | -1.036 |
June | -0.986 |
buzzing | -0.985 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
officer | +0.181 |
cash | +0.152 |
iza | +0.149 |
ateful | +0.144 |
knee | +0.143 |
Neg logit contributions | |
tails | -0.258 |
Fel | -0.249 |
buzzing | -0.238 |
Louise | -0.237 |
June | -0.235 |
Token |
|
Token ID | 198 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
officer | +0.186 |
ma | +0.151 |
sir | +0.146 |
salon | +0.146 |
kids | +0.144 |
Neg logit contributions | |
tails | -0.250 |
Fel | -0.248 |
Bet | -0.242 |
buzzing | -0.231 |
June | -0.224 |
Token |
|
Token ID | 198 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
tails | +0.031 |
Bet | +0.030 |
Fel | +0.030 |
buzzing | +0.029 |
Louise | +0.028 |
Neg logit contributions | |
officer | -0.019 |
ma | -0.015 |
ily | -0.015 |
kids | -0.015 |
sir | -0.014 |
Token | Max |
Token ID | 11518 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
tails | +0.025 |
Bet | +0.024 |
Fel | +0.024 |
buzzing | +0.023 |
Louise | +0.023 |
Neg logit contributions | |
officer | -0.025 |
ma | -0.020 |
salon | -0.020 |
sir | -0.019 |
kids | -0.019 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Fel | +0.366 |
tails | +0.362 |
Bet | +0.361 |
June | +0.344 |
Louise | +0.342 |
Neg logit contributions | |
officer | -0.172 |
ma | -0.126 |
sir | -0.126 |
salon | -0.124 |
iza | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
officer | +0.097 |
ma | +0.076 |
salon | +0.074 |
sir | +0.072 |
ily | +0.069 |
Neg logit contributions | |
Fel | -0.200 |
tails | -0.198 |
Bet | -0.194 |
June | -0.185 |
buzzing | -0.184 |
Token | She |
Token ID | 1375 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
officer | +0.041 |
sir | +0.035 |
iza | +0.034 |
salon | +0.034 |
ma | +0.034 |
Neg logit contributions | |
Fel | -0.040 |
Bet | -0.038 |
tails | -0.038 |
June | -0.036 |
Louise | -0.036 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Fel | +0.053 |
tails | +0.053 |
Bet | +0.051 |
June | +0.049 |
buzzing | +0.049 |
Neg logit contributions | |
officer | -0.035 |
ma | -0.028 |
salon | -0.028 |
sir | -0.027 |
ily | -0.026 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
officer | +0.014 |
salon | +0.011 |
kids | +0.011 |
ma | +0.011 |
Dad | +0.011 |
Neg logit contributions | |
Fel | -0.029 |
tails | -0.028 |
Bet | -0.028 |
June | -0.027 |
Louise | -0.026 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.081 |
kids | +0.077 |
ma | +0.076 |
Dad | +0.074 |
sir | +0.070 |
Neg logit contributions | |
Bet | -0.168 |
tails | -0.168 |
Fel | -0.164 |
June | -0.162 |
buzzing | -0.154 |
Token | days |
Token ID | 12545 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
officer | +0.689 |
ma | +0.587 |
sir | +0.557 |
salon | +0.537 |
kids | +0.523 |
Neg logit contributions | |
tails | -0.989 |
Fel | -0.971 |
Bet | -0.965 |
buzzing | -0.913 |
June | -0.908 |
Token | because |
Token ID | 780 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
officer | +0.193 |
ma | +0.165 |
sir | +0.160 |
salon | +0.153 |
iza | +0.152 |
Neg logit contributions | |
tails | -0.261 |
Fel | -0.261 |
Bet | -0.249 |
buzzing | -0.240 |
June | -0.237 |
Token | that |
Token ID | 326 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Fel | +0.060 |
tails | +0.058 |
Bet | +0.056 |
June | +0.054 |
buzzing | +0.054 |
Neg logit contributions | |
officer | -0.053 |
ma | -0.045 |
sir | -0.044 |
salon | -0.042 |
iza | -0.042 |
Token | 's |
Token ID | 338 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
officer | +0.029 |
sir | +0.025 |
ma | +0.024 |
iza | +0.024 |
salon | +0.024 |
Neg logit contributions | |
Fel | -0.036 |
tails | -0.036 |
Bet | -0.035 |
buzzing | -0.033 |
June | -0.033 |
Token | when |
Token ID | 618 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
tails | +0.159 |
Fel | +0.158 |
Bet | +0.153 |
buzzing | +0.150 |
June | +0.144 |
Neg logit contributions | |
officer | -0.150 |
ople | -0.126 |
ma | -0.122 |
sir | -0.121 |
iza | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
tails | +0.032 |
Fel | +0.032 |
Bet | +0.030 |
buzzing | +0.029 |
Louise | +0.029 |
Neg logit contributions | |
officer | -0.025 |
ma | -0.021 |
salon | -0.020 |
ily | -0.020 |
sir | -0.020 |
Token | One |
Token ID | 3198 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
tails | +0.028 |
Fel | +0.028 |
Bet | +0.027 |
buzzing | +0.026 |
June | +0.025 |
Neg logit contributions | |
officer | -0.025 |
ma | -0.021 |
salon | -0.021 |
sir | -0.020 |
ily | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
officer | +0.013 |
ma | +0.011 |
salon | +0.011 |
sir | +0.011 |
ople | +0.010 |
Neg logit contributions | |
Fel | -0.016 |
tails | -0.016 |
Bet | -0.015 |
buzzing | -0.015 |
Louise | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Fel | +0.048 |
tails | +0.046 |
Bet | +0.045 |
Louise | +0.043 |
buzzing | +0.043 |
Neg logit contributions | |
officer | -0.033 |
ma | -0.027 |
salon | -0.027 |
sir | -0.026 |
accident | -0.025 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
officer | +0.015 |
ma | +0.012 |
salon | +0.012 |
sir | +0.012 |
ily | +0.011 |
Neg logit contributions | |
Fel | -0.022 |
tails | -0.022 |
Bet | -0.021 |
June | -0.020 |
Louise | -0.020 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.218 |
ma | +0.192 |
kids | +0.184 |
sir | +0.183 |
Dad | +0.178 |
Neg logit contributions | |
Fel | -0.394 |
tails | -0.383 |
Bet | -0.383 |
June | -0.370 |
ches | -0.349 |
Token | came |
Token ID | 1625 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
officer | +0.653 |
ma | +0.546 |
sir | +0.528 |
salon | +0.509 |
cash | +0.491 |
Neg logit contributions | |
tails | -1.018 |
Fel | -0.983 |
Bet | -0.979 |
buzzing | -0.929 |
Louise | -0.918 |
Token | home |
Token ID | 1363 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
officer | +0.014 |
ily | +0.012 |
ma | +0.011 |
kids | +0.011 |
Dad | +0.011 |
Neg logit contributions | |
Fel | -0.023 |
tails | -0.022 |
Bet | -0.022 |
buzzing | -0.020 |
June | -0.020 |
Token | from |
Token ID | 422 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
officer | +0.110 |
ma | +0.090 |
salon | +0.089 |
sir | +0.088 |
ily | +0.087 |
Neg logit contributions | |
Fel | -0.152 |
tails | -0.151 |
Bet | -0.149 |
buzzing | -0.144 |
Louise | -0.139 |
Token | school |
Token ID | 1524 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
officer | +0.048 |
ma | +0.039 |
sir | +0.037 |
salon | +0.037 |
ily | +0.035 |
Neg logit contributions | |
Fel | -0.088 |
tails | -0.087 |
Bet | -0.084 |
buzzing | -0.081 |
Louise | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
officer | +0.248 |
ma | +0.225 |
ateful | +0.218 |
sir | +0.217 |
rost | +0.217 |
Neg logit contributions | |
tails | -0.306 |
Fel | -0.300 |
buzzing | -0.287 |
Bet | -0.280 |
Louise | -0.279 |
Token | â |
Token ID | 22940 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
officer | +0.112 |
salon | +0.095 |
ma | +0.095 |
accident | +0.092 |
sir | +0.091 |
Neg logit contributions | |
Fel | -0.126 |
tails | -0.122 |
Bet | -0.120 |
June | -0.113 |
Louise | -0.112 |
Token | € |
Token ID | 26391 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
officer | +0.114 |
cubes | +0.114 |
dad | +0.109 |
salon | +0.107 |
kids | +0.105 |
Neg logit contributions | |
Fel | -0.120 |
tails | -0.116 |
Bet | -0.111 |
ches | -0.109 |
June | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
officer | +0.215 |
ma | +0.187 |
salon | +0.183 |
sir | +0.181 |
kids | +0.179 |
Neg logit contributions | |
Fel | -0.227 |
tails | -0.223 |
Bet | -0.220 |
buzzing | -0.208 |
June | -0.208 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
tails | +0.025 |
Fel | +0.024 |
Bet | +0.023 |
buzzing | +0.022 |
June | +0.022 |
Neg logit contributions | |
officer | -0.018 |
ma | -0.015 |
ily | -0.015 |
salon | -0.015 |
sir | -0.015 |
Token | Ag |
Token ID | 10262 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
tails | +0.023 |
Fel | +0.023 |
Bet | +0.022 |
buzzing | +0.021 |
June | +0.021 |
Neg logit contributions | |
officer | -0.020 |
ma | -0.017 |
salon | -0.016 |
ily | -0.016 |
sir | -0.016 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.219 |
cubes | +0.213 |
sir | +0.203 |
ma | +0.201 |
Dad | +0.198 |
Neg logit contributions | |
Fel | -0.499 |
tails | -0.468 |
June | -0.462 |
Bet | -0.455 |
ches | -0.451 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
officer | +0.769 |
ma | +0.653 |
sir | +0.644 |
salon | +0.639 |
cubes | +0.627 |
Neg logit contributions | |
tails | -0.872 |
Fel | -0.847 |
Bet | -0.810 |
buzzing | -0.793 |
Louise | -0.793 |
Token | and |
Token ID | 290 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
officer | +0.265 |
salon | +0.236 |
ople | +0.218 |
iza | +0.215 |
cubes | +0.212 |
Neg logit contributions | |
Fel | -0.316 |
tails | -0.307 |
buzzing | -0.299 |
Louise | -0.297 |
Bet | -0.297 |
Token | said |
Token ID | 531 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
officer | +0.026 |
ma | +0.020 |
salon | +0.020 |
sir | +0.020 |
ily | +0.019 |
Neg logit contributions | |
Fel | -0.051 |
tails | -0.051 |
Bet | -0.049 |
June | -0.047 |
buzzing | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
officer | +0.042 |
salon | +0.034 |
ople | +0.034 |
accident | +0.034 |
ma | +0.033 |
Neg logit contributions | |
Fel | -0.056 |
tails | -0.055 |
Bet | -0.052 |
Louise | -0.050 |
buzzing | -0.050 |
Token | � |
Token ID | 6184 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
officer | +0.023 |
salon | +0.020 |
ople | +0.019 |
ma | +0.019 |
accident | +0.019 |
Neg logit contributions | |
Fel | -0.024 |
tails | -0.022 |
Bet | -0.022 |
buzzing | -0.021 |
Louise | -0.021 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
Fel | +0.395 |
tails | +0.390 |
Bet | +0.380 |
June | +0.360 |
buzzing | +0.358 |
Neg logit contributions | |
officer | -0.280 |
ma | -0.232 |
salon | -0.227 |
sir | -0.224 |
ily | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
Fel | +0.837 |
tails | +0.813 |
Bet | +0.811 |
June | +0.774 |
Louise | +0.755 |
Neg logit contributions | |
officer | -0.310 |
ma | -0.225 |
ily | -0.221 |
kids | -0.211 |
salon | -0.207 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +7.22e+00 |
Pos logit contributions | |
officer | +0.034 |
ma | +0.033 |
ily | +0.033 |
Dad | +0.032 |
kids | +0.031 |
Neg logit contributions | |
tails | -0.057 |
Fel | -0.057 |
Bet | -0.051 |
buzzing | -0.050 |
ches | -0.049 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Fel | +0.666 |
tails | +0.664 |
Bet | +0.643 |
buzzing | +0.611 |
June | +0.610 |
Neg logit contributions | |
officer | -0.473 |
ma | -0.389 |
sir | -0.384 |
salon | -0.383 |
kids | -0.357 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
officer | +0.017 |
ma | +0.013 |
salon | +0.013 |
kids | +0.013 |
sir | +0.012 |
Neg logit contributions | |
Fel | -0.032 |
tails | -0.031 |
Bet | -0.031 |
June | -0.029 |
Louise | -0.029 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.074 |
kids | +0.061 |
ma | +0.061 |
sir | +0.056 |
Dad | +0.056 |
Neg logit contributions | |
tails | -0.175 |
Bet | -0.174 |
Fel | -0.174 |
June | -0.166 |
buzzing | -0.162 |
Token | days |
Token ID | 12545 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
officer | +0.643 |
ma | +0.528 |
sir | +0.505 |
salon | +0.503 |
kids | +0.477 |
Neg logit contributions | |
tails | -1.027 |
Fel | -1.024 |
Bet | -1.000 |
buzzing | -0.948 |
June | -0.947 |
Token | because |
Token ID | 780 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
officer | +0.187 |
ma | +0.157 |
sir | +0.153 |
salon | +0.149 |
iza | +0.144 |
Neg logit contributions | |
tails | -0.272 |
Fel | -0.272 |
Bet | -0.261 |
buzzing | -0.251 |
June | -0.247 |
Token | on |
Token ID | 319 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Fel | +0.059 |
tails | +0.058 |
Bet | +0.056 |
June | +0.054 |
buzzing | +0.054 |
Neg logit contributions | |
officer | -0.046 |
ma | -0.038 |
sir | -0.037 |
salon | -0.037 |
iza | -0.036 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Fel | +0.202 |
tails | +0.198 |
Bet | +0.189 |
buzzing | +0.187 |
Louise | +0.182 |
Neg logit contributions | |
officer | -0.178 |
sir | -0.144 |
ma | -0.140 |
ily | -0.138 |
ople | -0.135 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.089 |
boy | +0.079 |
kids | +0.078 |
sir | +0.077 |
Dad | +0.076 |
Neg logit contributions | |
Bet | -0.159 |
Fel | -0.157 |
tails | -0.155 |
June | -0.155 |
buzzing | -0.144 |
Token | ™ |
Token ID | 8151 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
officer | +0.228 |
ma | +0.199 |
salon | +0.196 |
sir | +0.194 |
kids | +0.191 |
Neg logit contributions | |
Fel | -0.217 |
tails | -0.214 |
Bet | -0.209 |
June | -0.197 |
buzzing | -0.197 |
Token | m |
Token ID | 76 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Fel | +0.210 |
tails | +0.207 |
Bet | +0.203 |
June | +0.190 |
buzzing | +0.187 |
Neg logit contributions | |
officer | -0.156 |
ma | -0.130 |
salon | -0.127 |
sir | -0.123 |
iza | -0.121 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
officer | +0.184 |
ma | +0.152 |
salon | +0.150 |
sir | +0.148 |
ily | +0.141 |
Neg logit contributions | |
Fel | -0.218 |
tails | -0.216 |
Bet | -0.207 |
buzzing | -0.197 |
Louise | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
officer | +0.126 |
salon | +0.105 |
ma | +0.101 |
ople | +0.099 |
iza | +0.098 |
Neg logit contributions | |
Fel | -0.167 |
tails | -0.162 |
Bet | -0.156 |
Louise | -0.149 |
buzzing | -0.148 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
officer | +0.020 |
ople | +0.016 |
ateful | +0.016 |
salon | +0.016 |
cubes | +0.016 |
Neg logit contributions | |
Fel | -0.028 |
Bet | -0.027 |
buzzing | -0.026 |
Louise | -0.026 |
Felix | -0.026 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.195 |
ma | +0.162 |
cubes | +0.161 |
kids | +0.157 |
Dad | +0.157 |
Neg logit contributions | |
Fel | -0.431 |
tails | -0.412 |
Bet | -0.400 |
June | -0.389 |
ches | -0.381 |
Token | . |
Token ID | 13 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
officer | +0.734 |
ma | +0.618 |
salon | +0.612 |
cash | +0.586 |
sir | +0.581 |
Neg logit contributions | |
tails | -0.919 |
Fel | -0.877 |
Bet | -0.857 |
buzzing | -0.840 |
Louise | -0.827 |
Token | I |
Token ID | 314 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
officer | +0.030 |
salon | +0.025 |
accident | +0.025 |
ma | +0.025 |
sir | +0.024 |
Neg logit contributions | |
Fel | -0.036 |
Bet | -0.035 |
tails | -0.035 |
June | -0.033 |
Louise | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
officer | +0.128 |
ma | +0.112 |
salon | +0.109 |
sir | +0.107 |
cubes | +0.105 |
Neg logit contributions | |
Fel | -0.139 |
tails | -0.132 |
Bet | -0.132 |
buzzing | -0.122 |
Louise | -0.120 |
Token | too |
Token ID | 1165 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Fel | +0.126 |
tails | +0.125 |
Bet | +0.122 |
buzzing | +0.122 |
Louise | +0.117 |
Neg logit contributions | |
officer | -0.099 |
ma | -0.081 |
sir | -0.081 |
salon | -0.078 |
line | -0.077 |
Token | busy |
Token ID | 8179 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
officer | +0.021 |
salon | +0.017 |
ma | +0.016 |
ily | +0.016 |
sir | +0.016 |
Neg logit contributions | |
Fel | -0.029 |
tails | -0.028 |
Bet | -0.028 |
buzzing | -0.027 |
Louise | -0.026 |
Token | baby |
Token ID | 5156 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
officer | +0.065 |
line | +0.060 |
ily | +0.059 |
ople | +0.059 |
iza | +0.058 |
Neg logit contributions | |
tails | -0.056 |
Fel | -0.055 |
buzzing | -0.054 |
Bet | -0.051 |
Louise | -0.050 |
Token | 's |
Token ID | 338 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
tails | +0.111 |
Fel | +0.108 |
Bet | +0.105 |
buzzing | +0.102 |
June | +0.100 |
Neg logit contributions | |
officer | -0.096 |
ma | -0.083 |
sir | -0.081 |
salon | -0.081 |
line | -0.078 |
Token | name |
Token ID | 1438 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
tails | +0.191 |
Fel | +0.187 |
Bet | +0.180 |
buzzing | +0.175 |
Louise | +0.171 |
Neg logit contributions | |
officer | -0.119 |
ma | -0.097 |
salon | -0.094 |
ily | -0.093 |
iza | -0.092 |
Token | was |
Token ID | 373 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Fel | +0.207 |
tails | +0.205 |
Bet | +0.197 |
buzzing | +0.186 |
June | +0.186 |
Neg logit contributions | |
officer | -0.198 |
ma | -0.171 |
salon | -0.169 |
sir | -0.168 |
iza | -0.161 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Fel | +0.140 |
tails | +0.139 |
Bet | +0.134 |
June | +0.129 |
buzzing | +0.127 |
Neg logit contributions | |
officer | -0.074 |
ma | -0.060 |
Dad | -0.059 |
sir | -0.058 |
kids | -0.057 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.197 |
ma | +0.168 |
kids | +0.156 |
sir | +0.154 |
Dad | +0.150 |
Neg logit contributions | |
Fel | -0.416 |
tails | -0.410 |
Bet | -0.401 |
June | -0.387 |
buzzing | -0.376 |
Token | . |
Token ID | 13 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
officer | +0.563 |
ma | +0.434 |
salon | +0.428 |
sir | +0.421 |
ily | +0.410 |
Neg logit contributions | |
Fel | -1.115 |
tails | -1.087 |
Bet | -1.075 |
June | -1.025 |
buzzing | -1.009 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
officer | +0.044 |
salon | +0.040 |
ma | +0.039 |
sir | +0.038 |
iza | +0.038 |
Neg logit contributions | |
Fel | -0.041 |
Bet | -0.040 |
tails | -0.039 |
June | -0.036 |
buzzing | -0.035 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.159 |
ma | +0.127 |
sir | +0.121 |
Dad | +0.109 |
kids | +0.109 |
Neg logit contributions | |
Fel | -0.462 |
tails | -0.450 |
Bet | -0.436 |
June | -0.427 |
buzzing | -0.418 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
officer | +0.766 |
ma | +0.672 |
sir | +0.666 |
salon | +0.634 |
cash | +0.626 |
Neg logit contributions | |
tails | -0.916 |
Fel | -0.860 |
Bet | -0.853 |
buzzing | -0.840 |
June | -0.800 |
Token | to |
Token ID | 284 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
officer | +0.015 |
ma | +0.011 |
kids | +0.011 |
salon | +0.011 |
Dad | +0.011 |
Neg logit contributions | |
Fel | -0.032 |
tails | -0.031 |
Bet | -0.031 |
June | -0.029 |
Louise | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Fel | +0.207 |
tails | +0.205 |
Bet | +0.197 |
buzzing | +0.186 |
June | +0.186 |
Neg logit contributions | |
officer | -0.198 |
ma | -0.171 |
salon | -0.169 |
sir | -0.168 |
iza | -0.161 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Fel | +0.140 |
tails | +0.139 |
Bet | +0.134 |
June | +0.129 |
buzzing | +0.127 |
Neg logit contributions | |
officer | -0.074 |
ma | -0.060 |
Dad | -0.059 |
sir | -0.058 |
kids | -0.057 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.197 |
ma | +0.168 |
kids | +0.156 |
sir | +0.154 |
Dad | +0.150 |
Neg logit contributions | |
Fel | -0.416 |
tails | -0.410 |
Bet | -0.401 |
June | -0.387 |
buzzing | -0.376 |
Token | . |
Token ID | 13 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
officer | +0.563 |
ma | +0.434 |
salon | +0.428 |
sir | +0.421 |
ily | +0.410 |
Neg logit contributions | |
Fel | -1.115 |
tails | -1.087 |
Bet | -1.075 |
June | -1.025 |
buzzing | -1.009 |
Token | Ag |
Token ID | 2449 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
officer | +0.044 |
salon | +0.040 |
ma | +0.039 |
sir | +0.038 |
iza | +0.038 |
Neg logit contributions | |
Fel | -0.041 |
Bet | -0.040 |
tails | -0.039 |
June | -0.036 |
buzzing | -0.035 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.159 |
ma | +0.127 |
sir | +0.121 |
Dad | +0.109 |
kids | +0.109 |
Neg logit contributions | |
Fel | -0.462 |
tails | -0.450 |
Bet | -0.436 |
June | -0.427 |
buzzing | -0.418 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
officer | +0.766 |
ma | +0.672 |
sir | +0.666 |
salon | +0.634 |
cash | +0.626 |
Neg logit contributions | |
tails | -0.916 |
Fel | -0.860 |
Bet | -0.853 |
buzzing | -0.840 |
June | -0.800 |
Token | to |
Token ID | 284 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
officer | +0.015 |
ma | +0.011 |
kids | +0.011 |
salon | +0.011 |
Dad | +0.011 |
Neg logit contributions | |
Fel | -0.032 |
tails | -0.031 |
Bet | -0.031 |
June | -0.029 |
Louise | -0.029 |
Token | wink |
Token ID | 41955 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
officer | +0.040 |
salon | +0.033 |
ma | +0.033 |
sir | +0.032 |
ily | +0.032 |
Neg logit contributions | |
tails | -0.048 |
Fel | -0.048 |
Bet | -0.046 |
buzzing | -0.044 |
Louise | -0.043 |
Token | at |
Token ID | 379 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
officer | +0.013 |
salon | +0.011 |
ma | +0.010 |
sir | +0.010 |
iza | +0.010 |
Neg logit contributions | |
tails | -0.019 |
Fel | -0.019 |
buzzing | -0.018 |
Louise | -0.018 |
Bet | -0.017 |
Token | all |
Token ID | 477 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
officer | +0.067 |
ma | +0.053 |
salon | +0.051 |
sir | +0.051 |
kids | +0.050 |
Neg logit contributions | |
Fel | -0.120 |
tails | -0.118 |
Bet | -0.116 |
June | -0.110 |
buzzing | -0.109 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.074 |
kids | +0.061 |
ma | +0.061 |
sir | +0.056 |
Dad | +0.056 |
Neg logit contributions | |
tails | -0.175 |
Bet | -0.174 |
Fel | -0.174 |
June | -0.166 |
buzzing | -0.162 |
Token | days |
Token ID | 12545 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
officer | +0.643 |
ma | +0.528 |
sir | +0.505 |
salon | +0.503 |
kids | +0.477 |
Neg logit contributions | |
tails | -1.027 |
Fel | -1.024 |
Bet | -1.000 |
buzzing | -0.948 |
June | -0.947 |
Token | because |
Token ID | 780 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
officer | +0.187 |
ma | +0.157 |
sir | +0.153 |
salon | +0.149 |
iza | +0.144 |
Neg logit contributions | |
tails | -0.272 |
Fel | -0.272 |
Bet | -0.261 |
buzzing | -0.251 |
June | -0.247 |
Token | on |
Token ID | 319 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Fel | +0.059 |
tails | +0.058 |
Bet | +0.056 |
June | +0.054 |
buzzing | +0.054 |
Neg logit contributions | |
officer | -0.046 |
ma | -0.038 |
sir | -0.037 |
salon | -0.037 |
iza | -0.036 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Fel | +0.202 |
tails | +0.198 |
Bet | +0.189 |
buzzing | +0.187 |
Louise | +0.182 |
Neg logit contributions | |
officer | -0.178 |
sir | -0.144 |
ma | -0.140 |
ily | -0.138 |
ople | -0.135 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
officer | +0.089 |
boy | +0.079 |
kids | +0.078 |
sir | +0.077 |
Dad | +0.076 |
Neg logit contributions | |
Bet | -0.159 |
Fel | -0.157 |
tails | -0.155 |
June | -0.155 |
buzzing | -0.144 |
Token | days |
Token ID | 12545 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
officer | +0.655 |
ma | +0.537 |
sir | +0.517 |
salon | +0.511 |
kids | +0.485 |
Neg logit contributions | |
tails | -1.016 |
Fel | -1.016 |
Bet | -0.989 |
June | -0.937 |
buzzing | -0.931 |
Token | she |
Token ID | 673 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
officer | +0.207 |
sir | +0.175 |
ma | +0.172 |
salon | +0.164 |
iza | +0.158 |
Neg logit contributions | |
tails | -0.251 |
Fel | -0.247 |
Bet | -0.237 |
buzzing | -0.232 |
June | -0.225 |
Token | did |
Token ID | 750 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
Fel | +0.143 |
tails | +0.140 |
Bet | +0.131 |
buzzing | +0.130 |
Louise | +0.128 |
Neg logit contributions | |
officer | -0.112 |
sir | -0.098 |
ma | -0.096 |
salon | -0.089 |
cash | -0.086 |
Token | something |
Token ID | 1223 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
officer | +0.240 |
sir | +0.195 |
ma | +0.186 |
salon | +0.176 |
ily | +0.173 |
Neg logit contributions | |
Fel | -0.330 |
tails | -0.329 |
buzzing | -0.312 |
Bet | -0.310 |
June | -0.295 |
Token | special |
Token ID | 2041 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
officer | +0.029 |
ma | +0.024 |
salon | +0.024 |
sir | +0.023 |
ily | +0.023 |
Neg logit contributions | |
Fel | -0.043 |
tails | -0.042 |
Bet | -0.042 |
June | -0.040 |
Louise | -0.038 |
Token | way |
Token ID | 835 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
officer | +0.335 |
sir | +0.294 |
ily | +0.287 |
ma | +0.284 |
iza | +0.281 |
Neg logit contributions | |
tails | -0.463 |
Fel | -0.460 |
Bet | -0.435 |
buzzing | -0.427 |
June | -0.415 |
Token | . |
Token ID | 13 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
tails | +0.253 |
Fel | +0.247 |
Bet | +0.241 |
buzzing | +0.232 |
June | +0.229 |
Neg logit contributions | |
officer | -0.171 |
ma | -0.140 |
sir | -0.135 |
salon | -0.133 |
ily | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
officer | +0.027 |
ma | +0.023 |
salon | +0.023 |
sir | +0.022 |
ily | +0.022 |
Neg logit contributions | |
Fel | -0.031 |
tails | -0.031 |
Bet | -0.030 |
June | -0.028 |
buzzing | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
tails | +0.030 |
Fel | +0.028 |
Bet | +0.028 |
buzzing | +0.027 |
Louise | +0.027 |
Neg logit contributions | |
officer | -0.017 |
ily | -0.015 |
ma | -0.014 |
kids | -0.014 |
iza | -0.014 |
Token | Ag |
Token ID | 10262 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
tails | +0.026 |
Fel | +0.025 |
Bet | +0.024 |
Louise | +0.023 |
buzzing | +0.023 |
Neg logit contributions | |
officer | -0.021 |
ma | -0.017 |
ily | -0.017 |
salon | -0.017 |
iza | -0.017 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
officer | +0.217 |
sir | +0.198 |
cubes | +0.193 |
ma | +0.190 |
Dad | +0.187 |
Neg logit contributions | |
Fel | -0.506 |
tails | -0.474 |
June | -0.466 |
Bet | -0.463 |
ches | -0.455 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
officer | +0.833 |
sir | +0.722 |
ma | +0.709 |
salon | +0.685 |
cash | +0.661 |
Neg logit contributions | |
tails | -0.829 |
Fel | -0.803 |
Bet | -0.763 |
buzzing | -0.750 |
Louise | -0.724 |
Token | to |
Token ID | 284 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
officer | +0.013 |
ma | +0.011 |
sir | +0.011 |
ily | +0.010 |
salon | +0.010 |
Neg logit contributions | |
Fel | -0.016 |
tails | -0.016 |
Bet | -0.015 |
buzzing | -0.015 |
June | -0.015 |
Token | help |
Token ID | 1037 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
officer | +0.035 |
sir | +0.030 |
ma | +0.029 |
salon | +0.029 |
ople | +0.029 |
Neg logit contributions | |
Fel | -0.041 |
tails | -0.040 |
Bet | -0.037 |
Louise | -0.037 |
buzzing | -0.037 |
Token | out |
Token ID | 503 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Fel | +0.068 |
tails | +0.067 |
Bet | +0.065 |
June | +0.062 |
buzzing | +0.061 |
Neg logit contributions | |
officer | -0.044 |
ma | -0.036 |
salon | -0.035 |
sir | -0.034 |
ily | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Fel | +0.266 |
tails | +0.264 |
Bet | +0.254 |
buzzing | +0.244 |
June | +0.242 |
Neg logit contributions | |
officer | -0.175 |
ma | -0.144 |
sir | -0.141 |
salon | -0.141 |
iza | -0.135 |
Token | something |
Token ID | 1223 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
officer | +0.240 |
sir | +0.195 |
ma | +0.186 |
salon | +0.176 |
ily | +0.173 |
Neg logit contributions | |
Fel | -0.330 |
tails | -0.329 |
buzzing | -0.312 |
Bet | -0.310 |
June | -0.295 |
Token | special |
Token ID | 2041 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
officer | +0.029 |
ma | +0.024 |
salon | +0.024 |
sir | +0.023 |
ily | +0.023 |
Neg logit contributions | |
Fel | -0.043 |
tails | -0.042 |
Bet | -0.042 |
June | -0.040 |
Louise | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Fel | +0.063 |
tails | +0.063 |
Bet | +0.060 |
buzzing | +0.059 |
Louise | +0.058 |
Neg logit contributions | |
officer | -0.042 |
ma | -0.036 |
sir | -0.034 |
salon | -0.034 |
iza | -0.032 |
Token | On |
Token ID | 1550 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
officer | +0.026 |
Dad | +0.024 |
ma | +0.024 |
kids | +0.023 |
ily | +0.022 |
Neg logit contributions | |
tails | -0.059 |
Fel | -0.058 |
buzzing | -0.055 |
Bet | -0.055 |
webs | -0.052 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Fel | +0.071 |
tails | +0.070 |
Bet | +0.068 |
June | +0.065 |
buzzing | +0.065 |
Neg logit contributions | |
officer | -0.050 |
ma | -0.041 |
sir | -0.040 |
salon | -0.039 |
ily | -0.038 |
Token | nes |
Token ID | 2516 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
officer | +0.086 |
sir | +0.073 |
kids | +0.072 |
knee | +0.071 |
Dad | +0.068 |
Neg logit contributions | |
Fel | -0.163 |
Bet | -0.163 |
June | -0.161 |
tails | -0.160 |
Lou | -0.149 |
Token | days |
Token ID | 12545 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
officer | +0.610 |
ma | +0.489 |
salon | +0.477 |
sir | +0.469 |
ily | +0.455 |
Neg logit contributions | |
Fel | -1.054 |
tails | -1.041 |
Bet | -1.018 |
June | -0.967 |
buzzing | -0.961 |
Token | she |
Token ID | 673 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
officer | +0.213 |
sir | +0.178 |
ma | +0.171 |
American | +0.164 |
ateful | +0.163 |
Neg logit contributions | |
Fel | -0.238 |
tails | -0.232 |
Bet | -0.227 |
Louise | -0.216 |
buzzing | -0.216 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Fel | +0.129 |
tails | +0.129 |
Bet | +0.117 |
buzzing | +0.116 |
Louise | +0.116 |
Neg logit contributions | |
officer | -0.129 |
sir | -0.115 |
ma | -0.111 |
line | -0.102 |
cubes | -0.101 |
Token | to |
Token ID | 284 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
officer | +0.112 |
ma | +0.090 |
salon | +0.087 |
sir | +0.087 |
ily | +0.084 |
Neg logit contributions | |
Fel | -0.188 |
tails | -0.186 |
Bet | -0.182 |
June | -0.173 |
buzzing | -0.172 |
Token | count |
Token ID | 954 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
officer | +0.045 |
sir | +0.039 |
ople | +0.037 |
isher | +0.037 |
ma | +0.037 |
Neg logit contributions | |
tails | -0.040 |
Fel | -0.039 |
buzzing | -0.038 |
Bet | -0.035 |
Louise | -0.035 |
Token | needed |
Token ID | 2622 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
officer | +0.073 |
ma | +0.059 |
salon | +0.057 |
sir | +0.056 |
ily | +0.055 |
Neg logit contributions | |
Fel | -0.123 |
tails | -0.122 |
Bet | -0.119 |
June | -0.113 |
buzzing | -0.112 |
Token | help |
Token ID | 1037 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Fel | +0.070 |
tails | +0.069 |
Bet | +0.068 |
June | +0.064 |
buzzing | +0.062 |
Neg logit contributions | |
officer | -0.041 |
ma | -0.034 |
sir | -0.033 |
kids | -0.033 |
ily | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Fel | +0.058 |
tails | +0.055 |
Bet | +0.055 |
June | +0.053 |
buzzing | +0.051 |
Neg logit contributions | |
officer | -0.023 |
ma | -0.017 |
kids | -0.017 |
sir | -0.016 |
ily | -0.016 |
Token | So |
Token ID | 1406 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Dad | +0.030 |
officer | +0.029 |
ily | +0.029 |
ma | +0.028 |
sir | +0.028 |
Neg logit contributions | |
Fel | -0.034 |
tails | -0.034 |
buzzing | -0.033 |
leaping | -0.032 |
Bet | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
dad | +0.017 |
officer | +0.017 |
sir | +0.016 |
Dad | +0.016 |
ma | +0.016 |
Neg logit contributions | |
Fel | -0.097 |
tails | -0.093 |
June | -0.093 |
pill | -0.093 |
Bet | -0.091 |
Token | Remy |
Token ID | 32912 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
he | +0.017 |
dad | +0.017 |
Dad | +0.017 |
kids | +0.017 |
boy | +0.017 |
Neg logit contributions | |
tails | -0.017 |
June | -0.016 |
Fel | -0.016 |
webs | -0.015 |
Bet | -0.015 |
Token | closed |
Token ID | 4838 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
tails | +1.069 |
Fel | +1.058 |
Bet | +1.046 |
buzzing | +1.009 |
Louise | +1.005 |
Neg logit contributions | |
officer | -0.668 |
salon | -0.568 |
ma | -0.541 |
sir | -0.521 |
cubes | -0.515 |
Token | his |
Token ID | 465 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
officer | +0.193 |
ma | +0.158 |
salon | +0.157 |
sir | +0.153 |
iza | +0.146 |
Neg logit contributions | |
Fel | -0.280 |
tails | -0.275 |
Bet | -0.269 |
Louise | -0.262 |
buzzing | -0.256 |
Token | eyes |
Token ID | 2951 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
officer | +0.069 |
ma | +0.056 |
sir | +0.054 |
salon | +0.053 |
kids | +0.052 |
Neg logit contributions | |
Fel | -0.136 |
tails | -0.133 |
Bet | -0.132 |
June | -0.126 |
buzzing | -0.123 |
Token | and |
Token ID | 290 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
officer | +0.011 |
salon | +0.009 |
ma | +0.009 |
iza | +0.009 |
ople | +0.009 |
Neg logit contributions | |
tails | -0.012 |
Fel | -0.012 |
Bet | -0.012 |
buzzing | -0.012 |
Louise | -0.011 |
Token | prayed |
Token ID | 32168 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
officer | +0.030 |
salon | +0.025 |
ma | +0.024 |
sir | +0.024 |
ily | +0.023 |
Neg logit contributions | |
tails | -0.045 |
Fel | -0.044 |
Bet | -0.043 |
buzzing | -0.043 |
Louise | -0.042 |
Token | Tim |
Token ID | 5045 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
officer | +0.006 |
ma | +0.004 |
salon | +0.004 |
sir | +0.004 |
iza | +0.004 |
Neg logit contributions | |
Fel | -0.010 |
tails | -0.010 |
Bet | -0.009 |
June | -0.009 |
buzzing | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
officer | +0.051 |
ma | +0.041 |
salon | +0.040 |
sir | +0.039 |
ily | +0.038 |
Neg logit contributions | |
Fel | -0.086 |
tails | -0.085 |
Bet | -0.083 |
June | -0.079 |
buzzing | -0.079 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
officer | +0.022 |
salon | +0.019 |
iza | +0.019 |
ople | +0.018 |
line | +0.018 |
Neg logit contributions | |
Fel | -0.026 |
tails | -0.025 |
buzzing | -0.025 |
Bet | -0.024 |
Louise | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
officer | +0.103 |
ma | +0.082 |
salon | +0.079 |
sir | +0.079 |
ily | +0.076 |
Neg logit contributions | |
Fel | -0.192 |
tails | -0.190 |
Bet | -0.186 |
June | -0.177 |
buzzing | -0.175 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
officer | +0.029 |
salon | +0.024 |
ma | +0.024 |
sir | +0.023 |
iza | +0.023 |
Neg logit contributions | |
tails | -0.042 |
Fel | -0.042 |
Bet | -0.042 |
buzzing | -0.039 |
June | -0.039 |
Token | snake |
Token ID | 17522 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
officer | +0.015 |
kids | +0.015 |
boy | +0.015 |
ily | +0.014 |
accident | +0.014 |
Neg logit contributions | |
Fel | -0.014 |
tails | -0.014 |
Bet | -0.013 |
June | -0.012 |
Louise | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Fel | +0.706 |
tails | +0.702 |
Bet | +0.686 |
buzzing | +0.653 |
Louise | +0.649 |
Neg logit contributions | |
officer | -0.448 |
ma | -0.371 |
salon | -0.364 |
iza | -0.355 |
sir | -0.346 |
Token | they |
Token ID | 484 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
officer | +0.014 |
iza | +0.012 |
salon | +0.012 |
ma | +0.012 |
sir | +0.011 |
Neg logit contributions | |
tails | -0.020 |
Bet | -0.019 |
Fel | -0.018 |
buzzing | -0.018 |
Louise | -0.018 |
Token | kept |
Token ID | 4030 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
tails | +0.077 |
Fel | +0.076 |
Bet | +0.074 |
June | +0.070 |
buzzing | +0.069 |
Neg logit contributions | |
officer | -0.057 |
ma | -0.050 |
salon | -0.049 |
sir | -0.048 |
iza | -0.046 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
officer | +0.117 |
dad | +0.112 |
Dad | +0.112 |
kids | +0.111 |
accident | +0.108 |
Neg logit contributions | |
Fel | -0.228 |
Bet | -0.219 |
June | -0.206 |
tails | -0.202 |
Louise | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
Fel | +0.210 |
tails | +0.205 |
Bet | +0.199 |
buzzing | +0.191 |
June | +0.188 |
Neg logit contributions | |
officer | -0.182 |
ma | -0.154 |
salon | -0.152 |
sir | -0.150 |
iza | -0.146 |
Token | oo |
Token ID | 2238 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
Fel | +0.113 |
tails | +0.109 |
Bet | +0.108 |
June | +0.101 |
Louise | +0.098 |
Neg logit contributions | |
officer | -0.127 |
salon | -0.109 |
ma | -0.109 |
sir | -0.108 |
iza | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
Fel | +0.256 |
tails | +0.253 |
Bet | +0.248 |
June | +0.236 |
buzzing | +0.234 |
Neg logit contributions | |
officer | -0.140 |
ma | -0.112 |
salon | -0.109 |
sir | -0.107 |
ily | -0.103 |
Token | It |
Token ID | 632 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Fel | +0.006 |
tails | +0.006 |
Bet | +0.005 |
buzzing | +0.005 |
June | +0.005 |
Neg logit contributions | |
officer | -0.005 |
salon | -0.004 |
ma | -0.004 |
sir | -0.004 |
iza | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
officer | +0.021 |
boy | +0.018 |
did | +0.016 |
kids | +0.015 |
accident | +0.015 |
Neg logit contributions | |
tails | -0.057 |
Fel | -0.057 |
Bet | -0.056 |
June | -0.054 |
Louise | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Fel | +0.187 |
tails | +0.183 |
Bet | +0.175 |
June | +0.170 |
Louise | +0.163 |
Neg logit contributions | |
officer | -0.094 |
kids | -0.079 |
Dad | -0.079 |
accident | -0.076 |
ma | -0.076 |
Token | cow |
Token ID | 9875 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
Fel | +0.002 |
tails | +0.002 |
Bet | +0.002 |
buzzing | +0.002 |
June | +0.002 |
Neg logit contributions | |
officer | -0.001 |
ma | -0.001 |
salon | -0.001 |
ily | -0.001 |
sir | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Fel | +0.845 |
Bet | +0.803 |
June | +0.778 |
tails | +0.768 |
Louise | +0.741 |
Neg logit contributions | |
officer | -0.354 |
kids | -0.271 |
sir | -0.259 |
salon | -0.257 |
ma | -0.252 |
Token | It |
Token ID | 632 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Fel | +0.011 |
Bet | +0.011 |
tails | +0.011 |
Louise | +0.010 |
buzzing | +0.010 |
Neg logit contributions | |
officer | -0.010 |
salon | -0.008 |
ma | -0.008 |
accident | -0.008 |
sir | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
officer | +0.028 |
boy | +0.021 |
kids | +0.020 |
accident | +0.020 |
ily | +0.019 |
Neg logit contributions | |
Fel | -0.060 |
tails | -0.060 |
Bet | -0.058 |
June | -0.056 |
Louise | -0.056 |
Token | angry |
Token ID | 7954 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
Fel | +0.178 |
tails | +0.170 |
Bet | +0.166 |
June | +0.161 |
Louise | +0.153 |
Neg logit contributions | |
officer | -0.099 |
kids | -0.084 |
Dad | -0.083 |
ma | -0.083 |
dad | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
officer | +0.000 |
ma | +0.000 |
salon | +0.000 |
sir | +0.000 |
iza | +0.000 |
Neg logit contributions | |
Fel | -0.001 |
tails | -0.001 |
Bet | -0.001 |
buzzing | -0.001 |
June | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +3.07e-04 |
Pos logit contributions | |
officer | +0.229 |
ma | +0.203 |
sir | +0.202 |
salon | +0.195 |
ateful | +0.195 |
Neg logit contributions | |
tails | -0.323 |
Fel | -0.319 |
Bet | -0.305 |
buzzing | -0.290 |
June | -0.289 |
Token | to |
Token ID | 284 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Fel | +0.000 |
Bet | +0.000 |
tails | +0.000 |
buzzing | +0.000 |
leaping | +0.000 |
Neg logit contributions | |
officer | -0.000 |
sir | -0.000 |
ateful | -0.000 |
salon | -0.000 |
isher | -0.000 |
Token | go |
Token ID | 467 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
officer | +0.042 |
salon | +0.036 |
cubes | +0.035 |
ily | +0.035 |
outed | +0.035 |
Neg logit contributions | |
tails | -0.048 |
Fel | -0.047 |
Bet | -0.046 |
Louise | -0.044 |
buzzing | -0.044 |
Token | home |
Token ID | 1363 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Fel | +0.040 |
tails | +0.040 |
Bet | +0.038 |
buzzing | +0.037 |
June | +0.036 |
Neg logit contributions | |
officer | -0.029 |
ma | -0.024 |
salon | -0.023 |
sir | -0.023 |
ily | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
officer | +0.131 |
ily | +0.111 |
salon | +0.109 |
ma | +0.107 |
iza | +0.105 |
Neg logit contributions | |
tails | -0.140 |
Fel | -0.138 |
buzzing | -0.129 |
Bet | -0.128 |
Louise | -0.125 |
Token | Andy |
Token ID | 12382 |
Feature activation | +7.97e+00 |
Pos logit contributions | |
officer | +0.017 |
Dad | +0.014 |
dad | +0.013 |
kids | +0.013 |
boy | +0.013 |
Neg logit contributions | |
Fel | -0.033 |
tails | -0.031 |
Bet | -0.031 |
ches | -0.030 |
June | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
tails | +0.719 |
Fel | +0.708 |
Bet | +0.678 |
buzzing | +0.656 |
Louise | +0.651 |
Neg logit contributions | |
officer | -0.519 |
ma | -0.441 |
salon | -0.431 |
sir | -0.430 |
ily | -0.421 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
tails | +0.115 |
Fel | +0.113 |
buzzing | +0.112 |
Bet | +0.109 |
Louise | +0.103 |
Neg logit contributions | |
officer | -0.110 |
sir | -0.092 |
ma | -0.090 |
ily | -0.088 |
salon | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
officer | +0.136 |
salon | +0.114 |
iza | +0.113 |
ma | +0.113 |
ily | +0.112 |
Neg logit contributions | |
Fel | -0.171 |
tails | -0.167 |
buzzing | -0.162 |
Bet | -0.158 |
Louise | -0.156 |
Token | He |
Token ID | 679 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
officer | +0.024 |
ma | +0.019 |
sir | +0.019 |
salon | +0.018 |
kids | +0.018 |
Neg logit contributions | |
Fel | -0.045 |
tails | -0.045 |
Bet | -0.043 |
buzzing | -0.041 |
June | -0.041 |
Token | missed |
Token ID | 6825 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
officer | +0.092 |
ma | +0.078 |
salon | +0.078 |
sir | +0.076 |
ily | +0.074 |
Neg logit contributions | |
Fel | -0.136 |
tails | -0.136 |
Bet | -0.130 |
buzzing | -0.125 |
June | -0.124 |
Token | too |
Token ID | 1165 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Fel | +0.274 |
Bet | +0.269 |
tails | +0.268 |
Louise | +0.250 |
buzzing | +0.249 |
Neg logit contributions | |
officer | -0.164 |
ma | -0.130 |
iza | -0.125 |
ateful | -0.121 |
salon | -0.119 |
Token | , |
Token ID | 11 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
officer | +0.017 |
salon | +0.013 |
ople | +0.012 |
iza | +0.012 |
ma | +0.012 |
Neg logit contributions | |
Fel | -0.028 |
Bet | -0.028 |
tails | -0.028 |
buzzing | -0.027 |
Louise | -0.026 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +9.37e+00 |
Pos logit contributions | |
officer | +0.004 |
ma | +0.003 |
sir | +0.003 |
kids | +0.003 |
salon | +0.003 |
Neg logit contributions | |
Fel | -0.007 |
tails | -0.007 |
Bet | -0.007 |
June | -0.007 |
buzzing | -0.007 |
Token | ens |
Token ID | 641 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Fel | +0.829 |
tails | +0.819 |
Bet | +0.796 |
June | +0.752 |
buzzing | +0.748 |
Neg logit contributions | |
officer | -0.655 |
ma | -0.548 |
salon | -0.534 |
sir | -0.531 |
ily | -0.520 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Fel | +0.329 |
tails | +0.325 |
Bet | +0.320 |
June | +0.305 |
buzzing | +0.304 |
Neg logit contributions | |
officer | -0.129 |
ma | -0.095 |
salon | -0.093 |
sir | -0.088 |
ily | -0.084 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +9.39e+00 |
Pos logit contributions | |
officer | +0.237 |
Dad | +0.236 |
Tommy | +0.232 |
kids | +0.222 |
dad | +0.220 |
Neg logit contributions | |
tails | -0.162 |
Fel | -0.160 |
webs | -0.151 |
buzzing | -0.149 |
June | -0.145 |
Token | ens |
Token ID | 641 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Fel | +0.879 |
tails | +0.871 |
Bet | +0.835 |
buzzing | +0.803 |
June | +0.800 |
Neg logit contributions | |
officer | -0.613 |
ma | -0.502 |
ily | -0.494 |
sir | -0.493 |
kids | -0.478 |
Token | l |
Token ID | 300 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Fel | +0.264 |
tails | +0.260 |
Bet | +0.254 |
June | +0.240 |
buzzing | +0.238 |
Neg logit contributions | |
officer | -0.196 |
ma | -0.163 |
salon | -0.159 |
sir | -0.157 |
ily | -0.153 |
Token | icked |
Token ID | 9484 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Fel | +0.283 |
tails | +0.280 |
Bet | +0.272 |
June | +0.256 |
buzzing | +0.254 |
Neg logit contributions | |
officer | -0.246 |
ma | -0.208 |
salon | -0.203 |
sir | -0.201 |
ily | -0.200 |
Token | his |
Token ID | 465 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
tails | +0.170 |
Fel | +0.161 |
elope | +0.154 |
buzzing | +0.153 |
June | +0.152 |
Neg logit contributions | |
ily | -0.053 |
Dad | -0.049 |
officer | -0.046 |
kids | -0.045 |
Tommy | -0.044 |
Token | lips |
Token ID | 11914 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
officer | +0.066 |
ma | +0.054 |
kids | +0.054 |
sir | +0.051 |
knee | +0.051 |
Neg logit contributions | |
Fel | -0.125 |
Bet | -0.121 |
tails | -0.118 |
June | -0.114 |
Louise | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
officer | +0.121 |
ma | +0.103 |
kids | +0.098 |
sir | +0.098 |
salon | +0.094 |
Neg logit contributions | |
Fel | -0.228 |
Bet | -0.224 |
tails | -0.224 |
June | -0.214 |
buzzing | -0.207 |
Token | look |
Token ID | 804 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
Fel | +0.012 |
tails | +0.011 |
Louise | +0.011 |
Luna | +0.011 |
buzzing | +0.011 |
Neg logit contributions | |
officer | -0.008 |
ople | -0.006 |
line | -0.006 |
salon | -0.006 |
ma | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
officer | +0.225 |
ma | +0.176 |
salon | +0.172 |
sir | +0.168 |
ily | +0.162 |
Neg logit contributions | |
Fel | -0.440 |
tails | -0.435 |
Bet | -0.426 |
June | -0.405 |
buzzing | -0.404 |
Token | this |
Token ID | 428 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
officer | +0.080 |
ma | +0.066 |
salon | +0.064 |
sir | +0.063 |
iza | +0.061 |
Neg logit contributions | |
Fel | -0.107 |
tails | -0.106 |
Bet | -0.102 |
buzzing | -0.098 |
Louise | -0.097 |
Token | wig |
Token ID | 45678 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
officer | +0.158 |
ma | +0.132 |
sir | +0.128 |
salon | +0.127 |
ily | +0.125 |
Neg logit contributions | |
Fel | -0.187 |
tails | -0.186 |
Bet | -0.176 |
buzzing | -0.171 |
Louise | -0.167 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
officer | +0.121 |
ma | +0.103 |
salon | +0.101 |
sir | +0.100 |
ily | +0.098 |
Neg logit contributions | |
Fel | -0.123 |
tails | -0.123 |
Bet | -0.117 |
buzzing | -0.111 |
June | -0.110 |
Token | Anna |
Token ID | 11735 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Fel | +0.251 |
Louise | +0.245 |
tails | +0.236 |
Luna | +0.236 |
Izzy | +0.231 |
Neg logit contributions | |
officer | -0.215 |
salon | -0.188 |
isher | -0.175 |
American | -0.172 |
line | -0.171 |
Token | says |
Token ID | 1139 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
Fel | +0.025 |
tails | +0.025 |
Bet | +0.024 |
Louise | +0.023 |
buzzing | +0.023 |
Neg logit contributions | |
officer | -0.022 |
ma | -0.019 |
salon | -0.019 |
sir | -0.018 |
iza | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
tails | +0.220 |
Fel | +0.212 |
buzzing | +0.207 |
Louise | +0.201 |
Bet | +0.199 |
Neg logit contributions | |
officer | -0.159 |
salon | -0.134 |
ma | -0.132 |
iza | -0.126 |
ople | -0.124 |
Token | " |
Token ID | 366 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
tails | +0.003 |
Fel | +0.003 |
Bet | +0.003 |
June | +0.003 |
buzzing | +0.003 |
Neg logit contributions | |
officer | -0.002 |
ma | -0.002 |
ily | -0.002 |
Dad | -0.001 |
sir | -0.001 |
Token | It |
Token ID | 1026 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Fel | +0.013 |
tails | +0.013 |
Bet | +0.013 |
June | +0.012 |
buzzing | +0.012 |
Neg logit contributions | |
officer | -0.012 |
ma | -0.010 |
salon | -0.010 |
sir | -0.010 |
kids | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
officer | +0.037 |
ma | +0.031 |
sir | +0.030 |
kids | +0.029 |
Dad | +0.029 |
Neg logit contributions | |
tails | -0.051 |
Fel | -0.051 |
Bet | -0.049 |
buzzing | -0.047 |
June | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
tails | +0.023 |
Fel | +0.022 |
Bet | +0.021 |
buzzing | +0.021 |
webs | +0.021 |
Neg logit contributions | |
officer | -0.010 |
ily | -0.008 |
Dad | -0.008 |
kids | -0.008 |
dad | -0.007 |
Token | One |
Token ID | 3198 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
tails | +0.020 |
Fel | +0.019 |
Bet | +0.018 |
Louise | +0.018 |
webs | +0.018 |
Neg logit contributions | |
officer | -0.014 |
ma | -0.011 |
ily | -0.011 |
kids | -0.011 |
sir | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
officer | +0.014 |
ma | +0.012 |
sir | +0.011 |
kids | +0.011 |
salon | +0.011 |
Neg logit contributions | |
Fel | -0.024 |
tails | -0.024 |
Bet | -0.024 |
June | -0.022 |
buzzing | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
tails | +0.033 |
Fel | +0.032 |
Bet | +0.031 |
June | +0.030 |
buzzing | +0.030 |
Neg logit contributions | |
officer | -0.017 |
kids | -0.013 |
ma | -0.013 |
ily | -0.013 |
sir | -0.013 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
officer | +0.018 |
ma | +0.016 |
salon | +0.016 |
iza | +0.016 |
ily | +0.015 |
Neg logit contributions | |
Fel | -0.034 |
tails | -0.033 |
June | -0.032 |
Louise | -0.032 |
Bet | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
tails | +0.196 |
Fel | +0.191 |
Bet | +0.182 |
buzzing | +0.181 |
Louise | +0.179 |
Neg logit contributions | |
officer | -0.141 |
salon | -0.131 |
sir | -0.130 |
ma | -0.129 |
cash | -0.126 |
Token | David |
Token ID | 3271 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
officer | +0.019 |
salon | +0.016 |
ma | +0.016 |
iza | +0.015 |
sir | +0.015 |
Neg logit contributions | |
Fel | -0.027 |
tails | -0.027 |
Bet | -0.026 |
buzzing | -0.025 |
Louise | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
officer | +0.099 |
salon | +0.081 |
ma | +0.081 |
sir | +0.079 |
ily | +0.076 |
Neg logit contributions | |
Fel | -0.152 |
tails | -0.151 |
Bet | -0.147 |
buzzing | -0.141 |
Louise | -0.140 |
Token | said |
Token ID | 531 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
officer | +0.016 |
salon | +0.015 |
ma | +0.013 |
sir | +0.013 |
line | +0.013 |
Neg logit contributions | |
Bet | -0.028 |
tails | -0.028 |
Fel | -0.027 |
buzzing | -0.026 |
Louise | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
officer | +0.042 |
salon | +0.034 |
ma | +0.034 |
iza | +0.033 |
sir | +0.032 |
Neg logit contributions | |
Fel | -0.059 |
tails | -0.059 |
Bet | -0.057 |
buzzing | -0.054 |
Louise | -0.054 |
Token | wave |
Token ID | 6769 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
Fel | +0.272 |
tails | +0.268 |
Bet | +0.262 |
June | +0.248 |
buzzing | +0.245 |
Neg logit contributions | |
officer | -0.194 |
ma | -0.161 |
salon | -0.157 |
sir | -0.155 |
ily | -0.151 |
Token | he |
Token ID | 339 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Fel | +0.090 |
tails | +0.089 |
Bet | +0.086 |
buzzing | +0.085 |
June | +0.082 |
Neg logit contributions | |
officer | -0.062 |
ma | -0.052 |
salon | -0.050 |
sir | -0.050 |
iza | -0.047 |
Token | had |
Token ID | 550 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
officer | +0.068 |
ma | +0.057 |
salon | +0.057 |
sir | +0.056 |
ily | +0.052 |
Neg logit contributions | |
Fel | -0.096 |
tails | -0.096 |
Bet | -0.092 |
buzzing | -0.089 |
June | -0.088 |
Token | ever |
Token ID | 1683 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
Fel | +0.016 |
tails | +0.016 |
Bet | +0.015 |
buzzing | +0.015 |
June | +0.014 |
Neg logit contributions | |
officer | -0.014 |
ma | -0.012 |
sir | -0.012 |
salon | -0.012 |
cash | -0.011 |
Token | seen |
Token ID | 1775 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
tails | +0.063 |
Bet | +0.061 |
Fel | +0.061 |
buzzing | +0.060 |
June | +0.056 |
Neg logit contributions | |
officer | -0.049 |
sir | -0.043 |
salon | -0.042 |
ma | -0.042 |
cash | -0.038 |
Token | ! |
Token ID | 0 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
Fel | +0.069 |
tails | +0.068 |
Bet | +0.066 |
buzzing | +0.064 |
June | +0.063 |
Neg logit contributions | |
officer | -0.047 |
ma | -0.039 |
salon | -0.038 |
sir | -0.037 |
iza | -0.036 |
Token | But |
Token ID | 887 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Fel | +0.522 |
tails | +0.506 |
Bet | +0.505 |
June | +0.476 |
Louise | +0.471 |
Neg logit contributions | |
officer | -0.406 |
salon | -0.341 |
ma | -0.338 |
sir | -0.325 |
accident | -0.324 |
Token | he |
Token ID | 339 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
Fel | +0.028 |
tails | +0.028 |
Bet | +0.027 |
Louise | +0.026 |
buzzing | +0.026 |
Neg logit contributions | |
officer | -0.022 |
salon | -0.018 |
ma | -0.018 |
ily | -0.017 |
iza | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
officer | +0.057 |
ma | +0.047 |
salon | +0.046 |
sir | +0.045 |
ily | +0.044 |
Neg logit contributions | |
Fel | -0.078 |
tails | -0.077 |
Bet | -0.075 |
buzzing | -0.071 |
June | -0.071 |
Token | still |
Token ID | 991 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Fel | +0.159 |
tails | +0.157 |
Bet | +0.154 |
buzzing | +0.150 |
June | +0.146 |
Neg logit contributions | |
officer | -0.117 |
ma | -0.094 |
salon | -0.094 |
sir | -0.093 |
ily | -0.087 |
Token | brave |
Token ID | 14802 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
officer | +0.087 |
ma | +0.071 |
salon | +0.070 |
sir | +0.069 |
ily | +0.067 |
Neg logit contributions | |
Fel | -0.122 |
tails | -0.121 |
Bet | -0.118 |
June | -0.111 |
buzzing | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
officer | +0.141 |
iza | +0.124 |
salon | +0.121 |
ma | +0.118 |
cash | +0.114 |
Neg logit contributions | |
tails | -0.161 |
buzzing | -0.159 |
Fel | -0.155 |
webs | -0.151 |
Bet | -0.148 |
Token | It |
Token ID | 632 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Fel | +0.011 |
tails | +0.010 |
Bet | +0.010 |
June | +0.010 |
buzzing | +0.010 |
Neg logit contributions | |
officer | -0.009 |
ma | -0.007 |
salon | -0.007 |
sir | -0.007 |
kids | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
officer | +0.027 |
ma | +0.021 |
salon | +0.020 |
sir | +0.020 |
ily | +0.019 |
Neg logit contributions | |
Fel | -0.055 |
tails | -0.054 |
Bet | -0.053 |
June | -0.051 |
buzzing | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
Fel | +0.189 |
tails | +0.186 |
Bet | +0.182 |
June | +0.173 |
Louise | +0.169 |
Neg logit contributions | |
officer | -0.107 |
ma | -0.087 |
salon | -0.083 |
sir | -0.082 |
ily | -0.081 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
officer | +0.003 |
ma | +0.003 |
salon | +0.003 |
sir | +0.003 |
kids | +0.003 |
Neg logit contributions | |
Fel | -0.005 |
tails | -0.005 |
Bet | -0.005 |
June | -0.005 |
Louise | -0.005 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
officer | +0.081 |
ma | +0.067 |
salon | +0.065 |
sir | +0.064 |
ily | +0.062 |
Neg logit contributions | |
Fel | -0.119 |
tails | -0.117 |
Bet | -0.115 |
June | -0.109 |
buzzing | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Fel | +0.357 |
Bet | +0.346 |
tails | +0.342 |
June | +0.332 |
Louise | +0.324 |
Neg logit contributions | |
officer | -0.138 |
salon | -0.095 |
sir | -0.092 |
ily | -0.091 |
kids | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
Fel | +0.012 |
tails | +0.012 |
Bet | +0.012 |
June | +0.011 |
Louise | +0.011 |
Neg logit contributions | |
officer | -0.010 |
ma | -0.009 |
salon | -0.009 |
sir | -0.008 |
kids | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
tails | +0.080 |
Fel | +0.078 |
Bet | +0.075 |
June | +0.071 |
buzzing | +0.070 |
Neg logit contributions | |
officer | -0.048 |
ily | -0.041 |
ma | -0.040 |
kids | -0.038 |
Dad | -0.038 |
Token | Anna |
Token ID | 31160 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
Fel | +0.076 |
tails | +0.075 |
Bet | +0.073 |
June | +0.069 |
buzzing | +0.069 |
Neg logit contributions | |
officer | -0.050 |
ma | -0.041 |
salon | -0.040 |
sir | -0.040 |
ily | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
officer | +0.043 |
ma | +0.036 |
salon | +0.036 |
sir | +0.036 |
line | +0.034 |
Neg logit contributions | |
Fel | -0.062 |
tails | -0.061 |
Bet | -0.059 |
buzzing | -0.057 |
Louise | -0.056 |
Token | them |
Token ID | 606 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
officer | +0.121 |
ma | +0.102 |
salon | +0.100 |
sir | +0.099 |
ily | +0.094 |
Neg logit contributions | |
Fel | -0.145 |
tails | -0.143 |
Bet | -0.138 |
buzzing | -0.131 |
June | -0.131 |
Token | together |
Token ID | 1978 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
officer | +0.058 |
ma | +0.049 |
salon | +0.049 |
sir | +0.048 |
iza | +0.047 |
Neg logit contributions | |
Fel | -0.053 |
tails | -0.053 |
Bet | -0.050 |
buzzing | -0.048 |
June | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Fel | +0.096 |
tails | +0.094 |
Bet | +0.093 |
June | +0.088 |
buzzing | +0.087 |
Neg logit contributions | |
officer | -0.046 |
ma | -0.036 |
salon | -0.035 |
sir | -0.034 |
ily | -0.033 |
Token | fill |
Token ID | 6070 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
officer | +0.038 |
sir | +0.031 |
salon | +0.030 |
ma | +0.030 |
ople | +0.029 |
Neg logit contributions | |
tails | -0.046 |
Fel | -0.045 |
Bet | -0.044 |
buzzing | -0.043 |
Louise | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
officer | +0.002 |
ma | +0.001 |
kids | +0.001 |
salon | +0.001 |
ily | +0.001 |
Neg logit contributions | |
Fel | -0.003 |
tails | -0.003 |
Bet | -0.003 |
June | -0.003 |
Louise | -0.002 |
Token | gap |
Token ID | 7625 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Fel | +0.007 |
webs | +0.007 |
tails | +0.007 |
buzzing | +0.007 |
web | +0.007 |
Neg logit contributions | |
officer | -0.007 |
sir | -0.005 |
iza | -0.005 |
ma | -0.005 |
ily | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Fel | +0.229 |
tails | +0.229 |
Bet | +0.222 |
buzzing | +0.213 |
June | +0.210 |
Neg logit contributions | |
officer | -0.161 |
ma | -0.131 |
salon | -0.128 |
sir | -0.126 |
ily | -0.120 |
Token | Finally |
Token ID | 9461 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Dad | +0.031 |
ily | +0.030 |
ma | +0.030 |
officer | +0.028 |
kids | +0.028 |
Neg logit contributions | |
tails | -0.048 |
Fel | -0.044 |
Bet | -0.043 |
buzzing | -0.041 |
June | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Fel | +0.265 |
tails | +0.259 |
Bet | +0.254 |
buzzing | +0.240 |
June | +0.240 |
Neg logit contributions | |
officer | -0.179 |
ma | -0.143 |
salon | -0.143 |
sir | -0.140 |
ily | -0.134 |
Token | the |
Token ID | 262 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
officer | +0.012 |
Dad | +0.012 |
ma | +0.011 |
iza | +0.011 |
dad | +0.011 |
Neg logit contributions | |
tails | -0.024 |
Fel | -0.024 |
Bet | -0.023 |
June | -0.022 |
buzzing | -0.021 |
Token | ceiling |
Token ID | 13387 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
Fel | +0.008 |
tails | +0.008 |
webs | +0.008 |
buzzing | +0.008 |
Louise | +0.008 |
Neg logit contributions | |
officer | -0.007 |
iza | -0.006 |
sir | -0.006 |
line | -0.005 |
ma | -0.005 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Fel | +0.065 |
tails | +0.064 |
Bet | +0.063 |
June | +0.059 |
buzzing | +0.059 |
Neg logit contributions | |
officer | -0.039 |
ma | -0.032 |
salon | -0.031 |
sir | -0.031 |
ily | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
officer | +0.105 |
ma | +0.083 |
salon | +0.081 |
sir | +0.079 |
ily | +0.077 |
Neg logit contributions | |
Fel | -0.191 |
tails | -0.189 |
Bet | -0.185 |
June | -0.176 |
buzzing | -0.175 |
Token | be |
Token ID | 307 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
officer | +0.031 |
salon | +0.024 |
ma | +0.024 |
sir | +0.024 |
iza | +0.024 |
Neg logit contributions | |
tails | -0.050 |
Fel | -0.048 |
Bet | -0.048 |
buzzing | -0.045 |
June | -0.045 |
Token | more |
Token ID | 517 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
officer | +0.116 |
ma | +0.094 |
salon | +0.092 |
sir | +0.090 |
ily | +0.088 |
Neg logit contributions | |
Fel | -0.183 |
tails | -0.181 |
Bet | -0.176 |
June | -0.167 |
buzzing | -0.166 |
Token | careful |
Token ID | 8161 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Fel | +0.154 |
tails | +0.152 |
Bet | +0.148 |
June | +0.141 |
buzzing | +0.140 |
Neg logit contributions | |
officer | -0.096 |
ma | -0.078 |
salon | -0.076 |
sir | -0.075 |
ily | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
officer | +0.028 |
ma | +0.023 |
salon | +0.022 |
sir | +0.022 |
iza | +0.022 |
Neg logit contributions | |
tails | -0.039 |
Fel | -0.038 |
Bet | -0.037 |
buzzing | -0.036 |
June | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
officer | +0.024 |
ma | +0.019 |
salon | +0.019 |
sir | +0.019 |
iza | +0.018 |
Neg logit contributions | |
tails | -0.038 |
Fel | -0.037 |
Bet | -0.037 |
buzzing | -0.035 |
June | -0.035 |
Token | always |
Token ID | 1464 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
officer | +0.030 |
ma | +0.024 |
salon | +0.024 |
sir | +0.023 |
ily | +0.023 |
Neg logit contributions | |
tails | -0.051 |
Fel | -0.051 |
Bet | -0.050 |
buzzing | -0.047 |
June | -0.047 |
Token | look |
Token ID | 804 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
officer | +0.170 |
salon | +0.140 |
ily | +0.139 |
ma | +0.137 |
iza | +0.136 |
Neg logit contributions | |
tails | -0.262 |
Fel | -0.250 |
Bet | -0.246 |
buzzing | -0.237 |
June | -0.233 |
Token | out |
Token ID | 503 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
officer | +0.262 |
ma | +0.215 |
salon | +0.210 |
sir | +0.207 |
ily | +0.202 |
Neg logit contributions | |
Fel | -0.380 |
tails | -0.376 |
Bet | -0.367 |
June | -0.347 |
buzzing | -0.344 |
Token | for |
Token ID | 329 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Fel | +0.258 |
tails | +0.254 |
Bet | +0.248 |
June | +0.235 |
buzzing | +0.234 |
Neg logit contributions | |
officer | -0.176 |
ma | -0.144 |
salon | -0.142 |
sir | -0.139 |
ily | -0.135 |
Token | little |
Token ID | 1310 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Fel | +0.085 |
tails | +0.084 |
Bet | +0.084 |
June | +0.080 |
buzzing | +0.079 |
Neg logit contributions | |
officer | -0.031 |
ma | -0.024 |
salon | -0.023 |
kids | -0.022 |
sir | -0.022 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
officer | +0.108 |
ma | +0.083 |
salon | +0.081 |
sir | +0.079 |
ily | +0.076 |
Neg logit contributions | |
Fel | -0.230 |
tails | -0.227 |
Bet | -0.223 |
June | -0.212 |
buzzing | -0.211 |
Token | watched |
Token ID | 7342 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
Fel | +0.019 |
tails | +0.018 |
Bet | +0.018 |
June | +0.017 |
buzzing | +0.017 |
Neg logit contributions | |
officer | -0.012 |
ma | -0.009 |
salon | -0.009 |
sir | -0.009 |
ily | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Fel | +0.083 |
tails | +0.082 |
Bet | +0.080 |
June | +0.076 |
buzzing | +0.075 |
Neg logit contributions | |
officer | -0.058 |
ma | -0.048 |
salon | -0.047 |
sir | -0.046 |
ily | -0.045 |
Token | amaz |
Token ID | 40642 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
officer | +0.134 |
ma | +0.110 |
salon | +0.106 |
kids | +0.105 |
sir | +0.104 |
Neg logit contributions | |
Fel | -0.204 |
tails | -0.203 |
Bet | -0.199 |
June | -0.188 |
buzzing | -0.183 |
Token | ement |
Token ID | 972 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Fel | +0.079 |
tails | +0.075 |
Louise | +0.073 |
webs | +0.073 |
June | +0.072 |
Neg logit contributions | |
officer | -0.093 |
sir | -0.078 |
ma | -0.075 |
line | -0.073 |
buy | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
officer | +0.196 |
ma | +0.156 |
salon | +0.152 |
sir | +0.150 |
iza | +0.146 |
Neg logit contributions | |
tails | -0.307 |
Fel | -0.303 |
Bet | -0.290 |
buzzing | -0.286 |
Louise | -0.279 |
Token | She |
Token ID | 1375 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
officer | +0.042 |
ma | +0.035 |
salon | +0.034 |
sir | +0.033 |
ily | +0.033 |
Neg logit contributions | |
Fel | -0.056 |
tails | -0.055 |
Bet | -0.054 |
June | -0.051 |
buzzing | -0.050 |
Token | climbed |
Token ID | 19952 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Fel | +0.052 |
tails | +0.052 |
Bet | +0.051 |
June | +0.048 |
buzzing | +0.047 |
Neg logit contributions | |
officer | -0.026 |
ma | -0.021 |
salon | -0.020 |
sir | -0.019 |
ily | -0.019 |
Token | up |
Token ID | 510 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
officer | +0.102 |
right | +0.100 |
ily | +0.087 |
boy | +0.083 |
kids | +0.082 |
Neg logit contributions | |
tails | -0.236 |
Fel | -0.234 |
Bet | -0.234 |
June | -0.220 |
oing | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Fel | +0.209 |
tails | +0.208 |
Bet | +0.203 |
June | +0.194 |
buzzing | +0.187 |
Neg logit contributions | |
officer | -0.098 |
salon | -0.077 |
ma | -0.076 |
accident | -0.073 |
ily | -0.072 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Fel | +0.169 |
tails | +0.166 |
Bet | +0.163 |
June | +0.154 |
buzzing | +0.152 |
Neg logit contributions | |
officer | -0.109 |
ma | -0.089 |
salon | -0.086 |
kids | -0.086 |
sir | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Fel | +0.227 |
tails | +0.226 |
Bet | +0.215 |
buzzing | +0.214 |
Louise | +0.208 |
Neg logit contributions | |
officer | -0.138 |
ma | -0.111 |
salon | -0.108 |
sir | -0.106 |
iza | -0.103 |
Token | new |
Token ID | 649 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
officer | +0.016 |
ma | +0.013 |
salon | +0.013 |
sir | +0.013 |
iza | +0.013 |
Neg logit contributions | |
tails | -0.022 |
Fel | -0.022 |
Bet | -0.021 |
buzzing | -0.020 |
June | -0.020 |
Token | drawings |
Token ID | 23388 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
Fel | +0.167 |
tails | +0.164 |
Bet | +0.162 |
June | +0.153 |
buzzing | +0.151 |
Neg logit contributions | |
officer | -0.109 |
ma | -0.088 |
salon | -0.086 |
kids | -0.086 |
sir | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
tails | +0.001 |
Fel | +0.001 |
Bet | +0.001 |
buzzing | +0.001 |
June | +0.001 |
Neg logit contributions | |
officer | -0.001 |
ma | -0.001 |
salon | -0.001 |
sir | -0.001 |
iza | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
officer | +0.015 |
salon | +0.013 |
ma | +0.013 |
sir | +0.012 |
accident | +0.012 |
Neg logit contributions | |
Fel | -0.016 |
tails | -0.016 |
Bet | -0.015 |
June | -0.014 |
Louise | -0.014 |
Token | hold |
Token ID | 1745 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
tails | +0.081 |
Fel | +0.079 |
Bet | +0.074 |
buzzing | +0.072 |
Louise | +0.071 |
Neg logit contributions | |
officer | -0.061 |
ma | -0.052 |
sir | -0.052 |
ople | -0.051 |
salon | -0.051 |
Token | hands |
Token ID | 2832 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Fel | +0.098 |
tails | +0.096 |
Bet | +0.094 |
June | +0.089 |
buzzing | +0.088 |
Neg logit contributions | |
officer | -0.073 |
ma | -0.061 |
salon | -0.059 |
sir | -0.059 |
ily | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Fel | +0.188 |
tails | +0.187 |
Bet | +0.182 |
June | +0.173 |
buzzing | +0.173 |
Neg logit contributions | |
officer | -0.106 |
ma | -0.085 |
salon | -0.083 |
sir | -0.081 |
ily | -0.079 |
Token | follow |
Token ID | 1061 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
officer | +0.015 |
ma | +0.013 |
salon | +0.012 |
sir | +0.012 |
ily | +0.012 |
Neg logit contributions | |
tails | -0.020 |
Fel | -0.020 |
Bet | -0.019 |
buzzing | -0.018 |
June | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
officer | +0.064 |
ma | +0.051 |
salon | +0.050 |
sir | +0.049 |
kids | +0.048 |
Neg logit contributions | |
Fel | -0.106 |
tails | -0.104 |
Bet | -0.102 |
June | -0.097 |
buzzing | -0.096 |
Token | catch |
Token ID | 4929 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
officer | +0.040 |
ma | +0.033 |
salon | +0.032 |
sir | +0.032 |
kids | +0.031 |
Neg logit contributions | |
Fel | -0.051 |
tails | -0.050 |
Bet | -0.049 |
June | -0.046 |
buzzing | -0.046 |
Token | flies |
Token ID | 17607 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
Fel | +0.454 |
tails | +0.447 |
Bet | +0.437 |
June | +0.419 |
Louise | +0.409 |
Neg logit contributions | |
officer | -0.244 |
kids | -0.198 |
ma | -0.187 |
sir | -0.184 |
ily | -0.183 |
Token | and |
Token ID | 290 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
Fel | +0.405 |
tails | +0.398 |
Bet | +0.389 |
June | +0.372 |
Louise | +0.366 |
Neg logit contributions | |
officer | -0.211 |
ma | -0.165 |
sir | -0.160 |
salon | -0.158 |
kids | -0.155 |
Token | name |
Token ID | 1438 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
officer | +0.032 |
ma | +0.026 |
salon | +0.026 |
sir | +0.025 |
kids | +0.025 |
Neg logit contributions | |
Fel | -0.044 |
tails | -0.042 |
Bet | -0.041 |
June | -0.039 |
Louise | -0.038 |
Token | them |
Token ID | 606 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Fel | +0.247 |
tails | +0.244 |
Bet | +0.239 |
June | +0.226 |
buzzing | +0.224 |
Neg logit contributions | |
officer | -0.153 |
ma | -0.124 |
salon | -0.120 |
sir | -0.119 |
ily | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
officer | +0.035 |
ma | +0.027 |
sir | +0.026 |
kids | +0.026 |
salon | +0.024 |
Neg logit contributions | |
Fel | -0.082 |
tails | -0.080 |
Bet | -0.080 |
June | -0.076 |
buzzing | -0.075 |
Token | But |
Token ID | 887 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
officer | +0.026 |
ma | +0.022 |
sir | +0.022 |
salon | +0.021 |
kids | +0.021 |
Neg logit contributions | |
Fel | -0.034 |
tails | -0.033 |
Bet | -0.032 |
June | -0.030 |
buzzing | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
Fel | +0.008 |
tails | +0.008 |
Bet | +0.008 |
buzzing | +0.008 |
Louise | +0.008 |
Neg logit contributions | |
officer | -0.006 |
salon | -0.005 |
iza | -0.005 |
ma | -0.005 |
ily | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Fel | +0.091 |
Bet | +0.088 |
tails | +0.087 |
June | +0.083 |
buzzing | +0.078 |
Neg logit contributions | |
officer | -0.058 |
kids | -0.050 |
ma | -0.047 |
sir | -0.047 |
accident | -0.046 |
Token | not |
Token ID | 407 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Fel | +0.228 |
tails | +0.221 |
Bet | +0.215 |
June | +0.206 |
Louise | +0.202 |
Neg logit contributions | |
officer | -0.100 |
ma | -0.080 |
accident | -0.078 |
ily | -0.077 |
kids | -0.076 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
officer | +0.062 |
ma | +0.051 |
sir | +0.048 |
salon | +0.048 |
kids | +0.047 |
Neg logit contributions | |
Fel | -0.108 |
tails | -0.106 |
Bet | -0.104 |
June | -0.098 |
Louise | -0.097 |
Token | |
Token ID | 220 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
officer | +0.037 |
salon | +0.031 |
ma | +0.031 |
sir | +0.030 |
accident | +0.029 |
Neg logit contributions | |
Fel | -0.043 |
tails | -0.041 |
Bet | -0.041 |
June | -0.039 |
Louise | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
officer | +0.043 |
ma | +0.037 |
sir | +0.036 |
ily | +0.035 |
salon | +0.035 |
Neg logit contributions | |
Fel | -0.057 |
tails | -0.057 |
Bet | -0.055 |
buzzing | -0.053 |
June | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
tails | +0.027 |
Fel | +0.026 |
Bet | +0.025 |
buzzing | +0.024 |
June | +0.024 |
Neg logit contributions | |
officer | -0.020 |
ma | -0.016 |
ily | -0.016 |
sir | -0.016 |
salon | -0.016 |
Token | Setup |
Token ID | 40786 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
tails | +0.024 |
Fel | +0.023 |
Bet | +0.022 |
buzzing | +0.021 |
June | +0.021 |
Neg logit contributions | |
officer | -0.021 |
ma | -0.018 |
salon | -0.017 |
sir | -0.017 |
ily | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
Fel | +0.197 |
tails | +0.196 |
Bet | +0.187 |
buzzing | +0.180 |
Louise | +0.178 |
Neg logit contributions | |
officer | -0.145 |
salon | -0.122 |
ma | -0.121 |
sir | -0.114 |
iza | -0.114 |
Token | Pay |
Token ID | 7119 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
officer | +0.043 |
salon | +0.036 |
ma | +0.035 |
sir | +0.035 |
ily | +0.035 |
Neg logit contributions | |
tails | -0.060 |
Fel | -0.060 |
Bet | -0.058 |
Louise | -0.056 |
June | -0.055 |
Token | off |
Token ID | 2364 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
officer | +0.073 |
salon | +0.065 |
ma | +0.063 |
accident | +0.059 |
sir | +0.059 |
Neg logit contributions | |
tails | -0.085 |
Fel | -0.081 |
Bet | -0.075 |
Louise | -0.074 |
ches | -0.074 |
Token | : |
Token ID | 25 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
officer | +0.341 |
salon | +0.287 |
ma | +0.284 |
sir | +0.272 |
ily | +0.270 |
Neg logit contributions | |
tails | -0.477 |
Fel | -0.474 |
Bet | -0.453 |
buzzing | -0.437 |
Louise | -0.432 |
Token | The |
Token ID | 383 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
officer | +0.009 |
ma | +0.008 |
salon | +0.007 |
sir | +0.007 |
ily | +0.007 |
Neg logit contributions | |
Fel | -0.013 |
tails | -0.012 |
Bet | -0.012 |
buzzing | -0.012 |
June | -0.011 |
Token | setup |
Token ID | 9058 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
officer | +0.060 |
salon | +0.050 |
ma | +0.050 |
ily | +0.049 |
iza | +0.049 |
Neg logit contributions | |
tails | -0.078 |
Fel | -0.077 |
Bet | -0.075 |
buzzing | -0.074 |
June | -0.071 |
Token | was |
Token ID | 373 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
officer | +0.205 |
ma | +0.171 |
salon | +0.170 |
sir | +0.167 |
iza | +0.161 |
Neg logit contributions | |
Fel | -0.269 |
tails | -0.268 |
Bet | -0.256 |
buzzing | -0.250 |
June | -0.245 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
tails | +0.345 |
Fel | +0.340 |
Bet | +0.329 |
buzzing | +0.325 |
June | +0.309 |
Neg logit contributions | |
officer | -0.224 |
salon | -0.185 |
ma | -0.184 |
sir | -0.175 |
ily | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
officer | +0.128 |
salon | +0.107 |
ma | +0.106 |
iza | +0.103 |
sir | +0.101 |
Neg logit contributions | |
Fel | -0.181 |
tails | -0.180 |
buzzing | -0.175 |
Bet | -0.173 |
Louise | -0.164 |
Token | They |
Token ID | 1119 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Fel | +0.007 |
tails | +0.007 |
Bet | +0.007 |
June | +0.006 |
buzzing | +0.006 |
Neg logit contributions | |
officer | -0.006 |
salon | -0.005 |
ma | -0.005 |
sir | -0.005 |
iza | -0.005 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
tails | +0.095 |
Fel | +0.094 |
Bet | +0.090 |
buzzing | +0.088 |
June | +0.085 |
Neg logit contributions | |
officer | -0.061 |
salon | -0.056 |
ma | -0.055 |
sir | -0.055 |
iza | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
officer | +0.109 |
ma | +0.089 |
salon | +0.088 |
iza | +0.086 |
sir | +0.086 |
Neg logit contributions | |
tails | -0.146 |
Fel | -0.145 |
Bet | -0.142 |
buzzing | -0.137 |
June | -0.133 |
Token | penny |
Token ID | 26369 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
buzzing | +0.001 |
tails | +0.001 |
leaping | +0.001 |
flying | +0.001 |
snowball | +0.001 |
Neg logit contributions | |
nes | -0.001 |
ily | -0.001 |
iza | -0.001 |
ople | -0.001 |
gan | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
officer | +0.334 |
ma | +0.264 |
salon | +0.257 |
sir | +0.252 |
ily | +0.244 |
Neg logit contributions | |
Fel | -0.633 |
tails | -0.626 |
Bet | -0.613 |
June | -0.583 |
buzzing | -0.579 |
Token | It |
Token ID | 632 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
Fel | +0.009 |
tails | +0.009 |
Bet | +0.009 |
June | +0.008 |
buzzing | +0.008 |
Neg logit contributions | |
officer | -0.008 |
ma | -0.006 |
salon | -0.006 |
sir | -0.006 |
ily | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
officer | +0.031 |
ma | +0.024 |
ily | +0.023 |
salon | +0.023 |
accident | +0.023 |
Neg logit contributions | |
Fel | -0.051 |
tails | -0.050 |
Bet | -0.049 |
June | -0.046 |
Louise | -0.046 |
Token | shiny |
Token ID | 22441 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Fel | +0.179 |
tails | +0.178 |
Bet | +0.174 |
buzzing | +0.165 |
June | +0.165 |
Neg logit contributions | |
officer | -0.109 |
ma | -0.088 |
salon | -0.086 |
sir | -0.084 |
ily | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
officer | +0.071 |
iza | +0.067 |
salon | +0.064 |
ma | +0.064 |
sir | +0.061 |
Neg logit contributions | |
buzzing | -0.054 |
webs | -0.052 |
tails | -0.050 |
Fel | -0.047 |
ches | -0.047 |
Token | follow |
Token ID | 1061 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
officer | +0.025 |
salon | +0.021 |
cubes | +0.020 |
ople | +0.020 |
ma | +0.019 |
Neg logit contributions | |
tails | -0.035 |
Bet | -0.033 |
Fel | -0.032 |
buzzing | -0.031 |
Louise | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
officer | +0.055 |
ma | +0.044 |
salon | +0.043 |
sir | +0.043 |
kids | +0.043 |
Neg logit contributions | |
Fel | -0.096 |
tails | -0.095 |
Bet | -0.094 |
June | -0.088 |
buzzing | -0.087 |
Token | rules |
Token ID | 3173 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
Fel | +0.028 |
tails | +0.027 |
buzzing | +0.026 |
Bet | +0.026 |
June | +0.026 |
Neg logit contributions | |
officer | -0.015 |
iza | -0.013 |
ople | -0.012 |
ily | -0.012 |
ma | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
officer | +0.355 |
ma | +0.303 |
cash | +0.291 |
salon | +0.290 |
iza | +0.284 |
Neg logit contributions | |
Fel | -0.463 |
tails | -0.460 |
Bet | -0.434 |
Louise | -0.432 |
buzzing | -0.431 |
Token | The |
Token ID | 383 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
Fel | +0.005 |
Bet | +0.005 |
tails | +0.005 |
Louise | +0.004 |
June | +0.004 |
Neg logit contributions | |
officer | -0.005 |
salon | -0.004 |
ma | -0.004 |
cubes | -0.004 |
accident | -0.004 |
Token | attic |
Token ID | 46113 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
officer | +0.023 |
iza | +0.021 |
ople | +0.020 |
sir | +0.020 |
line | +0.020 |
Neg logit contributions | |
Fel | -0.034 |
tails | -0.033 |
buzzing | -0.032 |
webs | -0.032 |
Bet | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
officer | +0.426 |
ma | +0.379 |
iza | +0.378 |
sir | +0.366 |
ily | +0.364 |
Neg logit contributions | |
tails | -0.326 |
Fel | -0.300 |
buzzing | -0.292 |
webs | -0.285 |
Bet | -0.283 |
Token | not |
Token ID | 407 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
tails | +0.138 |
Fel | +0.137 |
Bet | +0.134 |
buzzing | +0.129 |
June | +0.126 |
Neg logit contributions | |
officer | -0.096 |
salon | -0.078 |
ma | -0.077 |
sir | -0.075 |
iza | -0.074 |
Token | a |
Token ID | 257 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
officer | +0.073 |
salon | +0.066 |
iza | +0.064 |
ople | +0.063 |
cash | +0.062 |
Neg logit contributions | |
tails | -0.078 |
buzzing | -0.074 |
Bet | -0.072 |
Fel | -0.070 |
Louise | -0.069 |
Token | place |
Token ID | 1295 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
officer | +0.002 |
ma | +0.001 |
salon | +0.001 |
sir | +0.001 |
kids | +0.001 |
Neg logit contributions | |
Fel | -0.002 |
tails | -0.002 |
Bet | -0.002 |
June | -0.002 |
buzzing | -0.002 |
Token | for |
Token ID | 329 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
tails | +0.048 |
buzzing | +0.046 |
Fel | +0.045 |
Bet | +0.044 |
webs | +0.044 |
Neg logit contributions | |
officer | -0.042 |
cash | -0.035 |
ma | -0.035 |
salon | -0.035 |
iza | -0.035 |
Token | One |
Token ID | 1881 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
officer | +0.006 |
ma | +0.005 |
sir | +0.005 |
salon | +0.005 |
ily | +0.005 |
Neg logit contributions | |
tails | -0.008 |
Fel | -0.008 |
Bet | -0.008 |
buzzing | -0.007 |
June | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
officer | +0.067 |
salon | +0.056 |
ma | +0.055 |
sir | +0.053 |
ily | +0.052 |
Neg logit contributions | |
Fel | -0.078 |
tails | -0.077 |
Bet | -0.076 |
buzzing | -0.074 |
Louise | -0.072 |
Token | he |
Token ID | 339 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
tails | +0.063 |
Fel | +0.062 |
Bet | +0.061 |
June | +0.059 |
buzzing | +0.058 |
Neg logit contributions | |
officer | -0.031 |
ma | -0.025 |
sir | -0.024 |
kids | -0.024 |
ily | -0.023 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
officer | +0.070 |
salon | +0.061 |
ma | +0.060 |
sir | +0.057 |
ily | +0.055 |
Neg logit contributions | |
Fel | -0.098 |
tails | -0.097 |
Bet | -0.095 |
buzzing | -0.091 |
Louise | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Fel | +0.096 |
tails | +0.094 |
Bet | +0.092 |
buzzing | +0.088 |
Louise | +0.087 |
Neg logit contributions | |
officer | -0.068 |
ma | -0.057 |
salon | -0.057 |
sir | -0.054 |
iza | -0.052 |
Token | wreck |
Token ID | 15228 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
officer | +0.013 |
ma | +0.011 |
sir | +0.011 |
salon | +0.010 |
kids | +0.010 |
Neg logit contributions | |
Fel | -0.019 |
tails | -0.018 |
Bet | -0.018 |
June | -0.017 |
Louise | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
officer | +0.450 |
ma | +0.392 |
salon | +0.373 |
sir | +0.371 |
iza | +0.359 |
Neg logit contributions | |
tails | -0.599 |
Fel | -0.599 |
buzzing | -0.598 |
Bet | -0.574 |
leaping | -0.546 |
Token | was |
Token ID | 373 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
officer | +0.039 |
salon | +0.034 |
ma | +0.033 |
sir | +0.032 |
iza | +0.031 |
Neg logit contributions | |
Fel | -0.044 |
tails | -0.043 |
Bet | -0.042 |
buzzing | -0.041 |
Louise | -0.040 |
Token | underwater |
Token ID | 21258 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
buzzing | +0.108 |
tails | +0.107 |
Fel | +0.106 |
Bet | +0.102 |
leaping | +0.098 |
Neg logit contributions | |
officer | -0.116 |
salon | -0.102 |
ma | -0.102 |
ople | -0.101 |
ily | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Fel | +0.116 |
tails | +0.116 |
Bet | +0.112 |
buzzing | +0.110 |
June | +0.104 |
Neg logit contributions | |
officer | -0.088 |
ma | -0.073 |
salon | -0.073 |
sir | -0.069 |
ily | -0.069 |
Token | He |
Token ID | 679 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
officer | +0.019 |
salon | +0.015 |
ma | +0.015 |
sir | +0.015 |
ily | +0.014 |
Neg logit contributions | |
Fel | -0.032 |
tails | -0.031 |
Bet | -0.031 |
June | -0.029 |
Louise | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
officer | +0.249 |
ma | +0.206 |
salon | +0.202 |
sir | +0.199 |
iza | +0.198 |
Neg logit contributions | |
tails | -0.318 |
Fel | -0.316 |
Bet | -0.306 |
Louise | -0.292 |
buzzing | -0.291 |
Token | she |
Token ID | 673 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
officer | +0.027 |
ma | +0.023 |
sir | +0.023 |
salon | +0.022 |
ople | +0.022 |
Neg logit contributions | |
Fel | -0.030 |
tails | -0.029 |
Bet | -0.028 |
buzzing | -0.026 |
Louise | -0.026 |
Token | saw |
Token ID | 2497 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
Fel | +0.168 |
tails | +0.166 |
Bet | +0.163 |
June | +0.156 |
buzzing | +0.154 |
Neg logit contributions | |
officer | -0.077 |
ma | -0.058 |
salon | -0.056 |
kids | -0.055 |
sir | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Fel | +0.096 |
tails | +0.094 |
Bet | +0.092 |
June | +0.087 |
buzzing | +0.086 |
Neg logit contributions | |
officer | -0.049 |
ma | -0.038 |
kids | -0.037 |
ily | -0.037 |
salon | -0.037 |
Token | kindly |
Token ID | 26820 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
officer | +0.021 |
ma | +0.017 |
salon | +0.017 |
sir | +0.017 |
kids | +0.016 |
Neg logit contributions | |
Fel | -0.034 |
tails | -0.034 |
Bet | -0.033 |
June | -0.031 |
Louise | -0.031 |
Token | old |
Token ID | 1468 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
officer | +0.047 |
ily | +0.038 |
salon | +0.037 |
ma | +0.037 |
ople | +0.037 |
Neg logit contributions | |
tails | -0.091 |
Fel | -0.090 |
Bet | -0.088 |
buzzing | -0.087 |
Louise | -0.084 |
Token | man |
Token ID | 582 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
officer | +0.262 |
ily | +0.222 |
iza | +0.217 |
ma | +0.213 |
ople | +0.211 |
Neg logit contributions | |
tails | -0.520 |
Fel | -0.505 |
Bet | -0.497 |
buzzing | -0.493 |
Louise | -0.475 |
Token | . |
Token ID | 13 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
officer | +0.233 |
ma | +0.195 |
salon | +0.191 |
sir | +0.189 |
ily | +0.184 |
Neg logit contributions | |
Fel | -0.296 |
tails | -0.292 |
Bet | -0.285 |
June | -0.269 |
buzzing | -0.267 |
Token | He |
Token ID | 679 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
officer | +0.039 |
salon | +0.034 |
accident | +0.033 |
ople | +0.033 |
ateful | +0.032 |
Neg logit contributions | |
Fel | -0.053 |
tails | -0.051 |
Bet | -0.050 |
Louise | -0.047 |
buzzing | -0.046 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
officer | +0.092 |
ma | +0.070 |
sir | +0.066 |
kids | +0.065 |
salon | +0.065 |
Neg logit contributions | |
Fel | -0.170 |
tails | -0.167 |
Bet | -0.164 |
June | -0.155 |
buzzing | -0.154 |
Token | to |
Token ID | 284 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
officer | +0.145 |
ma | +0.123 |
salon | +0.120 |
sir | +0.117 |
iza | +0.115 |
Neg logit contributions | |
tails | -0.218 |
Fel | -0.218 |
Bet | -0.213 |
June | -0.202 |
Louise | -0.201 |
Token | great |
Token ID | 1049 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
officer | +0.015 |
ma | +0.013 |
salon | +0.013 |
kids | +0.013 |
boy | +0.013 |
Neg logit contributions | |
tails | -0.015 |
Fel | -0.014 |
Bet | -0.014 |
June | -0.013 |
Louise | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Fel | +0.369 |
tails | +0.364 |
Bet | +0.356 |
June | +0.338 |
buzzing | +0.336 |
Neg logit contributions | |
officer | -0.214 |
ma | -0.173 |
salon | -0.168 |
sir | -0.165 |
ily | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
officer | +0.018 |
ma | +0.015 |
kids | +0.014 |
salon | +0.014 |
sir | +0.014 |
Neg logit contributions | |
Fel | -0.030 |
tails | -0.030 |
Bet | -0.029 |
June | -0.028 |
Louise | -0.027 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
officer | +0.007 |
salon | +0.006 |
ma | +0.006 |
sir | +0.006 |
iza | +0.006 |
Neg logit contributions | |
Fel | -0.007 |
Bet | -0.007 |
tails | -0.007 |
June | -0.006 |
Louise | -0.006 |
Token | L |
Token ID | 43 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
tails | +0.068 |
Fel | +0.067 |
Bet | +0.065 |
June | +0.061 |
buzzing | +0.061 |
Neg logit contributions | |
officer | -0.054 |
ma | -0.045 |
ily | -0.045 |
kids | -0.044 |
salon | -0.044 |
Token | ily |
Token ID | 813 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
officer | +0.206 |
ma | +0.171 |
sir | +0.171 |
nam | +0.167 |
salon | +0.165 |
Neg logit contributions | |
Fel | -0.232 |
tails | -0.227 |
Bet | -0.223 |
ches | -0.220 |
Louise | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
officer | +0.395 |
sir | +0.332 |
ma | +0.327 |
salon | +0.322 |
iza | +0.298 |
Neg logit contributions | |
tails | -0.531 |
Fel | -0.530 |
Bet | -0.513 |
buzzing | -0.488 |
Louise | -0.487 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
officer | +0.032 |
salon | +0.029 |
line | +0.027 |
ma | +0.027 |
sir | +0.027 |
Neg logit contributions | |
tails | -0.038 |
Bet | -0.037 |
Fel | -0.036 |
Louise | -0.035 |
June | -0.035 |
Token | were |
Token ID | 547 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
officer | +0.103 |
salon | +0.093 |
sir | +0.091 |
ma | +0.088 |
line | +0.085 |
Neg logit contributions | |
tails | -0.135 |
Fel | -0.130 |
Bet | -0.129 |
buzzing | -0.118 |
June | -0.117 |
Token | twins |
Token ID | 20345 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
officer | +0.159 |
ma | +0.134 |
salon | +0.131 |
sir | +0.130 |
ily | +0.126 |
Neg logit contributions | |
Fel | -0.185 |
tails | -0.183 |
Bet | -0.178 |
June | -0.167 |
buzzing | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
officer | +0.133 |
ma | +0.116 |
ily | +0.115 |
sir | +0.111 |
ateful | +0.109 |
Neg logit contributions | |
tails | -0.175 |
Fel | -0.164 |
buzzing | -0.163 |
Bet | -0.158 |
elope | -0.152 |