Token | he |
Token ID | 339 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
ishy | +0.003 |
ory | +0.003 |
fiber | +0.003 |
obs | +0.003 |
ouses | +0.003 |
Neg logit contributions | |
Amanda | -0.003 |
Am | -0.003 |
Sky | -0.003 |
basement | -0.003 |
Ellen | -0.003 |
Token | ate |
Token ID | 15063 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ishy | +0.016 |
ory | +0.014 |
obs | +0.014 |
ashed | +0.014 |
fiber | +0.014 |
Neg logit contributions | |
Amanda | -0.011 |
Am | -0.011 |
Sky | -0.011 |
basement | -0.011 |
Anne | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Amanda | +0.007 |
Am | +0.006 |
Anne | +0.006 |
Sky | +0.006 |
Ellen | +0.006 |
Neg logit contributions | |
ishy | -0.016 |
ory | -0.014 |
obs | -0.014 |
fiber | -0.014 |
ashed | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ishy | +0.060 |
obs | +0.056 |
ory | +0.056 |
fiber | +0.055 |
inters | +0.055 |
Neg logit contributions | |
Amanda | -0.014 |
Am | -0.013 |
Anne | -0.013 |
Sky | -0.013 |
Ellen | -0.012 |
Token | ch |
Token ID | 442 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
ishy | +0.059 |
obs | +0.056 |
ashed | +0.055 |
ory | +0.054 |
itted | +0.054 |
Neg logit contributions | |
Amanda | -0.050 |
Sky | -0.049 |
Am | -0.048 |
George | -0.047 |
shop | -0.047 |
Token | ocol |
Token ID | 4668 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
ishy | +0.033 |
obs | +0.032 |
abs | +0.032 |
ashed | +0.030 |
fiber | +0.030 |
Neg logit contributions | |
Sky | -0.075 |
Amanda | -0.074 |
Am | -0.072 |
Sunshine | -0.068 |
nine | -0.068 |
Token | ates |
Token ID | 689 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ishy | +0.167 |
ory | +0.142 |
inters | +0.141 |
ashed | +0.140 |
obs | +0.137 |
Neg logit contributions | |
Am | -0.206 |
Sky | -0.200 |
Amanda | -0.197 |
Jean | -0.187 |
Anne | -0.187 |
Token | and |
Token ID | 290 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
ishy | +0.043 |
ory | +0.039 |
obs | +0.039 |
ashed | +0.038 |
fiber | +0.038 |
Neg logit contributions | |
Amanda | -0.023 |
Am | -0.022 |
Sky | -0.022 |
Anne | -0.022 |
Ellen | -0.022 |
Token | sweets |
Token ID | 42402 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ishy | +0.108 |
obs | +0.098 |
ory | +0.096 |
inters | +0.096 |
fiber | +0.094 |
Neg logit contributions | |
Amanda | -0.067 |
Sky | -0.065 |
Anne | -0.065 |
never | -0.064 |
Am | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
ishy | +0.057 |
obs | +0.052 |
ory | +0.052 |
ashed | +0.051 |
fiber | +0.051 |
Neg logit contributions | |
Amanda | -0.037 |
Am | -0.035 |
Sky | -0.035 |
Anne | -0.035 |
Ellen | -0.034 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ishy | +0.020 |
ory | +0.018 |
obs | +0.018 |
fiber | +0.017 |
ashed | +0.017 |
Neg logit contributions | |
Amanda | -0.016 |
Sky | -0.016 |
Am | -0.016 |
Anne | -0.016 |
Ellen | -0.015 |
Token | reward |
Token ID | 6721 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ishy | +0.022 |
ory | +0.020 |
obs | +0.020 |
fiber | +0.020 |
inters | +0.019 |
Neg logit contributions | |
Amanda | -0.014 |
Am | -0.014 |
Sky | -0.013 |
Anne | -0.013 |
Ellen | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ishy | +0.031 |
ory | +0.028 |
obs | +0.028 |
fiber | +0.028 |
ashed | +0.027 |
Neg logit contributions | |
Amanda | -0.019 |
Am | -0.018 |
Sky | -0.018 |
Anne | -0.018 |
Ellen | -0.018 |
Token | It |
Token ID | 632 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ishy | +0.005 |
ory | +0.005 |
obs | +0.004 |
uggets | +0.004 |
fiber | +0.004 |
Neg logit contributions | |
basement | -0.003 |
Amanda | -0.003 |
Am | -0.003 |
Sky | -0.003 |
never | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ishy | +0.005 |
ashed | +0.004 |
ory | +0.004 |
fiber | +0.004 |
preferences | +0.004 |
Neg logit contributions | |
basement | -0.003 |
Am | -0.003 |
Amanda | -0.003 |
Ellen | -0.003 |
Alice | -0.003 |
Token | ch |
Token ID | 442 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Amanda | +0.022 |
Am | +0.022 |
basement | +0.021 |
Sky | +0.021 |
Anne | +0.020 |
Neg logit contributions | |
ishy | -0.047 |
ory | -0.043 |
uggets | -0.043 |
fiber | -0.043 |
obs | -0.042 |
Token | ocol |
Token ID | 4668 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
ishy | +0.041 |
fiber | +0.040 |
obs | +0.039 |
ouses | +0.038 |
uggets | +0.038 |
Neg logit contributions | |
Amanda | -0.054 |
Sky | -0.054 |
Am | -0.053 |
� | -0.052 |
June | -0.052 |
Token | ates |
Token ID | 689 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ishy | +0.155 |
inters | +0.132 |
ory | +0.131 |
ashed | +0.130 |
obs | +0.129 |
Neg logit contributions | |
Am | -0.207 |
Sky | -0.201 |
Amanda | -0.200 |
Anne | -0.192 |
Jean | -0.190 |
Token | and |
Token ID | 290 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
ishy | +0.045 |
ory | +0.041 |
obs | +0.041 |
ashed | +0.040 |
inters | +0.040 |
Neg logit contributions | |
Amanda | -0.027 |
Am | -0.026 |
Ellen | -0.026 |
basement | -0.026 |
Sky | -0.026 |
Token | sweets |
Token ID | 42402 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ishy | +0.103 |
fiber | +0.095 |
ory | +0.093 |
obs | +0.093 |
ashed | +0.092 |
Neg logit contributions | |
Am | -0.059 |
Amanda | -0.058 |
basement | -0.057 |
Ellen | -0.055 |
Anne | -0.054 |
Token | ! |
Token ID | 0 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ishy | +0.074 |
obs | +0.068 |
ory | +0.068 |
fiber | +0.066 |
ashed | +0.066 |
Neg logit contributions | |
Amanda | -0.050 |
Am | -0.048 |
basement | -0.047 |
Sky | -0.047 |
Anne | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ishy | +0.007 |
ory | +0.006 |
obs | +0.006 |
uggets | +0.006 |
fiber | +0.006 |
Neg logit contributions | |
basement | -0.004 |
Amanda | -0.004 |
Am | -0.004 |
never | -0.004 |
Sky | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ishy | +0.037 |
obs | +0.033 |
ory | +0.033 |
fiber | +0.032 |
inters | +0.032 |
Neg logit contributions | |
Amanda | -0.022 |
Am | -0.021 |
Sky | -0.021 |
Anne | -0.021 |
Ellen | -0.020 |
Token | cup |
Token ID | 6508 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ishy | +0.031 |
ory | +0.028 |
obs | +0.028 |
fiber | +0.028 |
uggets | +0.027 |
Neg logit contributions | |
Amanda | -0.019 |
Am | -0.019 |
basement | -0.019 |
Sky | -0.018 |
Anne | -0.018 |
Token | cakes |
Token ID | 37263 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ishy | +0.010 |
obs | +0.009 |
ory | +0.009 |
ashed | +0.009 |
fiber | +0.009 |
Neg logit contributions | |
Amanda | -0.007 |
Am | -0.007 |
Anne | -0.007 |
Sky | -0.007 |
Ellen | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ishy | +0.012 |
obs | +0.011 |
ory | +0.011 |
ashed | +0.011 |
ouses | +0.010 |
Neg logit contributions | |
basement | -0.007 |
Amanda | -0.007 |
June | -0.007 |
Am | -0.007 |
Anne | -0.007 |
Token | ch |
Token ID | 442 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ishy | +0.073 |
ory | +0.066 |
fiber | +0.065 |
obs | +0.065 |
ashed | +0.064 |
Neg logit contributions | |
Amanda | -0.063 |
Am | -0.061 |
basement | -0.061 |
Sky | -0.061 |
Anne | -0.060 |
Token | ocol |
Token ID | 4668 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
ishy | +0.027 |
fiber | +0.025 |
obs | +0.024 |
preferences | +0.023 |
ouses | +0.023 |
Neg logit contributions | |
Amanda | -0.067 |
Am | -0.065 |
Sky | -0.064 |
Alice | -0.061 |
Pen | -0.061 |
Token | ates |
Token ID | 689 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ishy | +0.157 |
inters | +0.134 |
ory | +0.132 |
fiber | +0.130 |
obs | +0.129 |
Neg logit contributions | |
Am | -0.201 |
Amanda | -0.194 |
Sky | -0.193 |
Jean | -0.182 |
Anne | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
ishy | +0.042 |
obs | +0.038 |
ory | +0.037 |
fiber | +0.037 |
inters | +0.037 |
Neg logit contributions | |
Amanda | -0.024 |
Am | -0.023 |
Sky | -0.023 |
Anne | -0.023 |
Ellen | -0.022 |
Token | |
Token ID | 220 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
ishy | +0.010 |
obs | +0.009 |
ory | +0.009 |
fiber | +0.009 |
inters | +0.009 |
Neg logit contributions | |
Amanda | -0.006 |
Am | -0.006 |
Sky | -0.006 |
Anne | -0.006 |
Ellen | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ishy | +0.198 |
ory | +0.180 |
obs | +0.180 |
fiber | +0.179 |
ashed | +0.178 |
Neg logit contributions | |
Amanda | -0.063 |
Sky | -0.059 |
Am | -0.059 |
Anne | -0.058 |
Ellen | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
ishy | +0.021 |
ory | +0.019 |
obs | +0.019 |
fiber | +0.019 |
uggets | +0.019 |
Neg logit contributions | |
Amanda | -0.010 |
Sky | -0.010 |
basement | -0.010 |
Anne | -0.010 |
Am | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
ishy | +0.017 |
obs | +0.016 |
ashed | +0.016 |
inters | +0.016 |
ory | +0.016 |
Neg logit contributions | |
Amanda | -0.008 |
Am | -0.008 |
Sky | -0.008 |
Anne | -0.008 |
Ellen | -0.008 |
Token | large |
Token ID | 1588 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
Sky | +0.020 |
Amanda | +0.020 |
Am | +0.019 |
Anne | +0.019 |
Elizabeth | +0.019 |
Neg logit contributions | |
ishy | -0.028 |
ory | -0.025 |
obs | -0.025 |
inters | -0.024 |
fiber | -0.024 |
Token | selection |
Token ID | 6356 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Amanda | +0.014 |
Am | +0.014 |
Sky | +0.014 |
Anne | +0.014 |
Elizabeth | +0.013 |
Neg logit contributions | |
ishy | -0.022 |
ory | -0.019 |
obs | -0.019 |
fiber | -0.019 |
inters | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
ishy | +0.039 |
obs | +0.036 |
ory | +0.035 |
fiber | +0.035 |
inters | +0.035 |
Neg logit contributions | |
Amanda | -0.025 |
Am | -0.024 |
Sky | -0.024 |
Anne | -0.024 |
Ellen | -0.024 |
Token | ch |
Token ID | 442 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ishy | +0.024 |
obs | +0.022 |
ory | +0.022 |
ashed | +0.022 |
inters | +0.021 |
Neg logit contributions | |
Amanda | -0.024 |
Am | -0.023 |
Anne | -0.022 |
Ellen | -0.022 |
Sky | -0.022 |
Token | ocol |
Token ID | 4668 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
ishy | +0.028 |
fiber | +0.024 |
ashed | +0.024 |
ushed | +0.023 |
ory | +0.022 |
Neg logit contributions | |
Amanda | -0.083 |
Am | -0.082 |
� | -0.081 |
Sky | -0.080 |
shop | -0.078 |
Token | ates |
Token ID | 689 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ishy | +0.164 |
ashed | +0.138 |
inters | +0.138 |
ory | +0.137 |
fiber | +0.131 |
Neg logit contributions | |
Am | -0.200 |
Sky | -0.189 |
Amanda | -0.186 |
Jean | -0.179 |
Anne | -0.176 |
Token | . |
Token ID | 13 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
ishy | +0.064 |
obs | +0.058 |
ory | +0.057 |
fiber | +0.056 |
inters | +0.056 |
Neg logit contributions | |
Amanda | -0.044 |
Am | -0.042 |
Sky | -0.042 |
Anne | -0.042 |
Ellen | -0.041 |
Token | Ell |
Token ID | 7122 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Sky | +0.007 |
basement | +0.007 |
Am | +0.007 |
Amanda | +0.006 |
never | +0.006 |
Neg logit contributions | |
ishy | -0.010 |
ory | -0.009 |
obs | -0.009 |
ashed | -0.009 |
uggets | -0.009 |
Token | a |
Token ID | 64 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ishy | +0.015 |
obs | +0.014 |
ory | +0.014 |
fiber | +0.014 |
inters | +0.014 |
Neg logit contributions | |
Amanda | -0.008 |
Am | -0.007 |
Anne | -0.007 |
Sky | -0.007 |
Ellen | -0.007 |
Token | picked |
Token ID | 6497 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
basement | +0.021 |
Amanda | +0.021 |
Sky | +0.021 |
Ellen | +0.021 |
Am | +0.020 |
Neg logit contributions | |
ishy | -0.030 |
ory | -0.028 |
ashed | -0.028 |
obs | -0.028 |
ouses | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
Amanda | +0.011 |
Am | +0.010 |
Sky | +0.010 |
Anne | +0.010 |
basement | +0.010 |
Neg logit contributions | |
ishy | -0.029 |
ory | -0.026 |
obs | -0.026 |
ashed | -0.026 |
fiber | -0.026 |
Token | laughed |
Token ID | 13818 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ishy | +0.077 |
ory | +0.070 |
ashed | +0.070 |
obs | +0.069 |
fiber | +0.068 |
Neg logit contributions | |
Amanda | -0.067 |
Am | -0.067 |
Ellen | -0.066 |
basement | -0.065 |
Sky | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
ishy | +0.065 |
obs | +0.059 |
ory | +0.058 |
ashed | +0.057 |
fiber | +0.057 |
Neg logit contributions | |
Amanda | -0.046 |
Am | -0.045 |
Sky | -0.044 |
Anne | -0.044 |
Ellen | -0.044 |
Token | ate |
Token ID | 15063 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ishy | +0.101 |
obs | +0.092 |
ory | +0.091 |
fiber | +0.090 |
ashed | +0.090 |
Neg logit contributions | |
Amanda | -0.068 |
Am | -0.066 |
Sky | -0.065 |
Anne | -0.064 |
Ellen | -0.063 |
Token | ch |
Token ID | 442 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Amanda | +0.005 |
Am | +0.005 |
Sky | +0.005 |
Anne | +0.004 |
Ellen | +0.004 |
Neg logit contributions | |
ishy | -0.010 |
obs | -0.009 |
ory | -0.009 |
fiber | -0.009 |
inters | -0.009 |
Token | ocol |
Token ID | 4668 |
Feature activation | +7.07e+00 |
Pos logit contributions | |
ishy | +0.047 |
fiber | +0.045 |
ory | +0.043 |
obs | +0.043 |
inters | +0.042 |
Neg logit contributions | |
Sky | -0.108 |
Amanda | -0.105 |
Am | -0.099 |
Anne | -0.098 |
George | -0.098 |
Token | ates |
Token ID | 689 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ishy | +0.184 |
ory | +0.161 |
inters | +0.160 |
ashed | +0.156 |
fiber | +0.154 |
Neg logit contributions | |
Am | -0.177 |
Sky | -0.176 |
Amanda | -0.175 |
Anne | -0.166 |
Jean | -0.164 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ishy | +0.061 |
obs | +0.055 |
ory | +0.054 |
fiber | +0.054 |
inters | +0.054 |
Neg logit contributions | |
Amanda | -0.040 |
Am | -0.038 |
Sky | -0.038 |
Anne | -0.037 |
Ellen | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
ishy | +0.008 |
ory | +0.008 |
obs | +0.008 |
fiber | +0.008 |
inters | +0.008 |
Neg logit contributions | |
Amanda | -0.004 |
Sky | -0.004 |
Anne | -0.004 |
Am | -0.004 |
June | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
ishy | +0.018 |
ory | +0.016 |
obs | +0.016 |
ashed | +0.016 |
fiber | +0.015 |
Neg logit contributions | |
Amanda | -0.015 |
Am | -0.014 |
Sky | -0.014 |
Anne | -0.014 |
Ellen | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ishy | +0.034 |
obs | +0.031 |
ory | +0.031 |
fiber | +0.031 |
ashed | +0.031 |
Neg logit contributions | |
Amanda | -0.014 |
Am | -0.013 |
Sky | -0.013 |
Anne | -0.013 |
Ellen | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ishy | +0.010 |
ory | +0.009 |
obs | +0.009 |
fiber | +0.009 |
inters | +0.009 |
Neg logit contributions | |
Amanda | -0.004 |
Am | -0.004 |
Sky | -0.004 |
Ellen | -0.004 |
Anne | -0.004 |
Token | grass |
Token ID | 8701 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ishy | +0.038 |
obs | +0.035 |
ory | +0.035 |
inters | +0.034 |
ashed | +0.033 |
Neg logit contributions | |
Amanda | -0.024 |
Ellen | -0.023 |
Am | -0.023 |
June | -0.023 |
Anne | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
ishy | +0.009 |
ory | +0.008 |
ashed | +0.008 |
obs | +0.008 |
itted | +0.008 |
Neg logit contributions | |
Amanda | -0.005 |
Am | -0.005 |
Ellen | -0.005 |
Anne | -0.005 |
Sky | -0.005 |
Token | looked |
Token ID | 3114 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
ishy | +0.106 |
obs | +0.096 |
ory | +0.096 |
fiber | +0.094 |
inters | +0.094 |
Neg logit contributions | |
Amanda | -0.064 |
Am | -0.061 |
Sky | -0.061 |
Anne | -0.060 |
Ellen | -0.059 |
Token | up |
Token ID | 510 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ishy | +0.000 |
fiber | +0.000 |
obs | +0.000 |
inters | +0.000 |
ory | +0.000 |
Neg logit contributions | |
Amanda | -0.000 |
Anne | -0.000 |
Sky | -0.000 |
Am | -0.000 |
Ellen | -0.000 |
Token | |
Token ID | 220 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
ishy | +0.032 |
fiber | +0.030 |
obs | +0.029 |
ory | +0.029 |
inters | +0.029 |
Neg logit contributions | |
Amanda | -0.018 |
Am | -0.017 |
Sky | -0.017 |
Anne | -0.017 |
Ellen | -0.016 |
Token | at |
Token ID | 379 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ishy | +0.263 |
fiber | +0.240 |
ory | +0.237 |
ashed | +0.233 |
obs | +0.232 |
Neg logit contributions | |
Amanda | -0.094 |
Anne | -0.089 |
Am | -0.089 |
� | -0.088 |
Sky | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ishy | +0.051 |
obs | +0.047 |
ory | +0.047 |
fiber | +0.046 |
ashed | +0.046 |
Neg logit contributions | |
Amanda | -0.010 |
Am | -0.009 |
Anne | -0.009 |
Sky | -0.009 |
Ellen | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
ishy | +0.039 |
obs | +0.036 |
ory | +0.036 |
inters | +0.034 |
fiber | +0.034 |
Neg logit contributions | |
Amanda | -0.029 |
Am | -0.027 |
Sky | -0.027 |
Anne | -0.027 |
Ellen | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Am | +0.013 |
Amanda | +0.013 |
Sky | +0.012 |
never | +0.012 |
Ellen | +0.012 |
Neg logit contributions | |
ishy | -0.020 |
ory | -0.018 |
obs | -0.018 |
fiber | -0.017 |
inters | -0.017 |
Token | blue |
Token ID | 4171 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ishy | +0.027 |
obs | +0.024 |
ory | +0.024 |
inters | +0.024 |
fiber | +0.024 |
Neg logit contributions | |
Amanda | -0.021 |
Am | -0.020 |
Sky | -0.020 |
Anne | -0.020 |
Ellen | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
Amanda | +0.024 |
Am | +0.022 |
Sky | +0.022 |
Anne | +0.022 |
Ellen | +0.021 |
Neg logit contributions | |
ishy | -0.080 |
obs | -0.074 |
ory | -0.074 |
ashed | -0.073 |
fiber | -0.072 |
Token | apple |
Token ID | 17180 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
� | +0.019 |
shop | +0.019 |
basement | +0.018 |
Sky | +0.018 |
also | +0.018 |
Neg logit contributions | |
ishy | -0.029 |
ouses | -0.029 |
obs | -0.028 |
ory | -0.028 |
uggets | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Amanda | +0.021 |
Am | +0.020 |
Ellen | +0.019 |
Anne | +0.019 |
Sky | +0.019 |
Neg logit contributions | |
ishy | -0.031 |
obs | -0.029 |
ory | -0.029 |
inters | -0.028 |
fiber | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
ishy | +0.085 |
ory | +0.077 |
obs | +0.077 |
fiber | +0.076 |
ashed | +0.076 |
Neg logit contributions | |
Amanda | -0.050 |
Am | -0.048 |
Sky | -0.047 |
basement | -0.047 |
Ellen | -0.047 |
Token | tasted |
Token ID | 29187 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ishy | +0.021 |
ory | +0.019 |
obs | +0.019 |
ashed | +0.018 |
fiber | +0.018 |
Neg logit contributions | |
Amanda | -0.014 |
Am | -0.014 |
Ellen | -0.014 |
Sky | -0.013 |
Anne | -0.013 |
Token | swe |
Token ID | 3490 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
ishy | +0.050 |
obs | +0.047 |
ouses | +0.046 |
ory | +0.046 |
ashed | +0.046 |
Neg logit contributions | |
Amanda | -0.022 |
� | -0.022 |
never | -0.022 |
Sky | -0.021 |
also | -0.021 |
Token | eter |
Token ID | 2357 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
iness | +0.130 |
asers | +0.128 |
ishy | +0.123 |
lessness | +0.121 |
inters | +0.116 |
Neg logit contributions | |
Amanda | -0.177 |
� | -0.177 |
never | -0.172 |
Jean | -0.169 |
K | -0.169 |
Token | than |
Token ID | 621 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ishy | +0.188 |
ouses | +0.186 |
abs | +0.183 |
inters | +0.180 |
ippers | +0.179 |
Neg logit contributions | |
never | -0.112 |
, | -0.108 |
Alice | -0.108 |
George | -0.098 |
Lucy | -0.097 |
Token | he |
Token ID | 339 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ishy | +0.042 |
obs | +0.039 |
itted | +0.038 |
ashed | +0.038 |
ouses | +0.038 |
Neg logit contributions | |
Amanda | -0.025 |
never | -0.024 |
Sky | -0.024 |
George | -0.024 |
Anne | -0.024 |
Token | had |
Token ID | 550 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ishy | +0.095 |
obs | +0.090 |
inters | +0.086 |
uggets | +0.086 |
ouses | +0.086 |
Neg logit contributions | |
never | -0.054 |
also | -0.051 |
� | -0.050 |
Amanda | -0.049 |
Am | -0.049 |
Token | ever |
Token ID | 1683 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
ishy | +0.071 |
obs | +0.064 |
inters | +0.062 |
ory | +0.062 |
fiber | +0.061 |
Neg logit contributions | |
never | -0.049 |
Am | -0.047 |
Amanda | -0.046 |
also | -0.045 |
� | -0.045 |
Token | not |
Token ID | 407 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Amanda | +0.019 |
Am | +0.018 |
Anne | +0.018 |
Sky | +0.018 |
Ellen | +0.017 |
Neg logit contributions | |
ishy | -0.041 |
fiber | -0.039 |
ory | -0.038 |
preferences | -0.038 |
inters | -0.037 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ishy | +0.040 |
ory | +0.037 |
obs | +0.037 |
fiber | +0.036 |
inters | +0.036 |
Neg logit contributions | |
Amanda | -0.020 |
Am | -0.019 |
Anne | -0.019 |
Sky | -0.019 |
Ellen | -0.018 |
Token | too |
Token ID | 1165 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Amanda | +0.021 |
Am | +0.020 |
Anne | +0.020 |
Sky | +0.020 |
Ellen | +0.020 |
Neg logit contributions | |
ishy | -0.031 |
ory | -0.028 |
obs | -0.028 |
fiber | -0.027 |
inters | -0.027 |
Token | many |
Token ID | 867 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
ishy | +0.077 |
obs | +0.070 |
ory | +0.070 |
ashed | +0.069 |
fiber | +0.069 |
Neg logit contributions | |
Amanda | -0.039 |
Am | -0.037 |
Sky | -0.037 |
Anne | -0.037 |
Ellen | -0.036 |
Token | ch |
Token ID | 442 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ishy | +0.025 |
ashed | +0.023 |
obs | +0.022 |
ory | +0.022 |
itted | +0.022 |
Neg logit contributions | |
Amanda | -0.021 |
Sky | -0.020 |
Am | -0.020 |
Anne | -0.020 |
never | -0.019 |
Token | ocol |
Token ID | 4668 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
ishy | +0.025 |
ashed | +0.023 |
obs | +0.022 |
fiber | +0.021 |
ouses | +0.021 |
Neg logit contributions | |
Sky | -0.063 |
Amanda | -0.061 |
Am | -0.059 |
never | -0.058 |
also | -0.057 |
Token | ates |
Token ID | 689 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ishy | +0.168 |
inters | +0.141 |
ashed | +0.141 |
ory | +0.141 |
obs | +0.137 |
Neg logit contributions | |
Am | -0.188 |
Sky | -0.185 |
Amanda | -0.176 |
never | -0.171 |
Jean | -0.170 |
Token | and |
Token ID | 290 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ishy | +0.051 |
obs | +0.046 |
ory | +0.046 |
ashed | +0.046 |
fiber | +0.046 |
Neg logit contributions | |
Amanda | -0.025 |
Am | -0.024 |
Sky | -0.024 |
Anne | -0.024 |
never | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ishy | +0.070 |
obs | +0.064 |
ory | +0.063 |
ashed | +0.062 |
inters | +0.061 |
Neg logit contributions | |
never | -0.031 |
Amanda | -0.031 |
Sky | -0.030 |
also | -0.030 |
Anne | -0.029 |
Token | friend |
Token ID | 1545 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ishy | +0.069 |
ashed | +0.063 |
obs | +0.063 |
ory | +0.061 |
abs | +0.060 |
Neg logit contributions | |
Sky | -0.052 |
Amanda | -0.051 |
never | -0.050 |
shop | -0.049 |
Am | -0.049 |
Token | learned |
Token ID | 4499 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Amanda | +0.020 |
Am | +0.019 |
Sky | +0.019 |
Anne | +0.019 |
Ellen | +0.019 |
Neg logit contributions | |
ishy | -0.035 |
obs | -0.032 |
ory | -0.032 |
fiber | -0.032 |
inters | -0.031 |
Token | really |
Token ID | 1107 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Amanda | +0.027 |
Am | +0.027 |
Sky | +0.026 |
basement | +0.026 |
Anne | +0.026 |
Neg logit contributions | |
ishy | -0.029 |
ory | -0.026 |
obs | -0.026 |
ashed | -0.025 |
inters | -0.025 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
obs | +0.093 |
uggets | +0.091 |
uns | +0.089 |
ocol | +0.089 |
ishy | +0.088 |
Neg logit contributions | |
never | -0.053 |
also | -0.052 |
� | -0.043 |
Amanda | -0.041 |
Sky | -0.038 |
Token | his |
Token ID | 465 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
ishy | +0.077 |
ory | +0.069 |
ashed | +0.068 |
obs | +0.068 |
ouses | +0.067 |
Neg logit contributions | |
Amanda | -0.026 |
Sky | -0.026 |
never | -0.025 |
Anne | -0.025 |
George | -0.024 |
Token | camera |
Token ID | 4676 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ishy | +0.127 |
inters | +0.117 |
uns | +0.115 |
ashed | +0.114 |
ocol | +0.114 |
Neg logit contributions | |
shop | -0.048 |
Amanda | -0.044 |
helicopter | -0.044 |
Ellen | -0.044 |
June | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ishy | +0.049 |
ory | +0.045 |
ashed | +0.044 |
fiber | +0.044 |
obs | +0.044 |
Neg logit contributions | |
Amanda | -0.025 |
Sky | -0.024 |
also | -0.024 |
never | -0.024 |
Anne | -0.024 |
Token | |
Token ID | 220 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
ishy | +0.047 |
obs | +0.043 |
uc | +0.043 |
ory | +0.042 |
ashed | +0.042 |
Neg logit contributions | |
George | -0.012 |
Anne | -0.012 |
Amanda | -0.012 |
Sky | -0.012 |
June | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ishy | +0.277 |
ory | +0.254 |
obs | +0.252 |
fiber | +0.251 |
ashed | +0.251 |
Neg logit contributions | |
Amanda | -0.081 |
Sky | -0.076 |
Anne | -0.075 |
Am | -0.075 |
Ellen | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
ishy | +0.038 |
ory | +0.036 |
obs | +0.036 |
inters | +0.035 |
uggets | +0.034 |
Neg logit contributions | |
Amanda | -0.022 |
basement | -0.021 |
Am | -0.021 |
Sky | -0.021 |
Ellen | -0.021 |
Token | Every |
Token ID | 6109 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Amanda | +0.000 |
Am | +0.000 |
Anne | +0.000 |
Sky | +0.000 |
Ellen | +0.000 |
Neg logit contributions | |
ishy | -0.002 |
obs | -0.002 |
ory | -0.002 |
fiber | -0.002 |
inters | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Amanda | +0.011 |
Am | +0.011 |
Sky | +0.010 |
Anne | +0.010 |
Ellen | +0.010 |
Neg logit contributions | |
ishy | -0.008 |
ory | -0.007 |
obs | -0.007 |
ashed | -0.007 |
inters | -0.007 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
George | +0.003 |
� | +0.002 |
Anne | +0.002 |
Amanda | +0.002 |
never | +0.001 |
Neg logit contributions | |
ishy | -0.051 |
inters | -0.048 |
obs | -0.048 |
fiber | -0.047 |
uggets | -0.047 |
Token | 't |
Token ID | 470 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
basement | +0.015 |
Sky | +0.015 |
Amanda | +0.015 |
Anne | +0.015 |
loft | +0.014 |
Neg logit contributions | |
ishy | -0.028 |
ory | -0.028 |
fiber | -0.027 |
obs | -0.025 |
inters | -0.025 |
Token | have |
Token ID | 423 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
ishy | +0.010 |
ory | +0.010 |
fiber | +0.009 |
inters | +0.009 |
obs | +0.009 |
Neg logit contributions | |
Amanda | -0.007 |
Sky | -0.007 |
Anne | -0.006 |
basement | -0.006 |
Am | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Amanda | +0.001 |
Sky | +0.001 |
Am | +0.001 |
Anne | +0.001 |
basement | +0.001 |
Neg logit contributions | |
ishy | -0.001 |
ory | -0.001 |
fiber | -0.001 |
obs | -0.001 |
inters | -0.001 |
Token | these |
Token ID | 777 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ishy | +0.021 |
obs | +0.019 |
ory | +0.019 |
fiber | +0.019 |
inters | +0.019 |
Neg logit contributions | |
Amanda | -0.008 |
Am | -0.008 |
Sky | -0.008 |
Anne | -0.008 |
Ellen | -0.007 |
Token | ch |
Token ID | 442 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ishy | +0.046 |
ashed | +0.042 |
ory | +0.042 |
obs | +0.041 |
itted | +0.041 |
Neg logit contributions | |
Amanda | -0.039 |
Am | -0.037 |
Anne | -0.037 |
� | -0.037 |
Sky | -0.036 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
ishy | +0.029 |
ashed | +0.025 |
ory | +0.024 |
fiber | +0.024 |
obs | +0.024 |
Neg logit contributions | |
Amanda | -0.073 |
Am | -0.072 |
Sky | -0.069 |
never | -0.068 |
Anne | -0.068 |
Token | ates |
Token ID | 689 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ishy | +0.170 |
ory | +0.144 |
inters | +0.142 |
ashed | +0.141 |
obs | +0.138 |
Neg logit contributions | |
Am | -0.187 |
Sky | -0.176 |
Amanda | -0.174 |
Jean | -0.167 |
never | -0.165 |
Token | ! |
Token ID | 0 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ishy | +0.038 |
obs | +0.035 |
ory | +0.034 |
fiber | +0.034 |
inters | +0.034 |
Neg logit contributions | |
Amanda | -0.019 |
Am | -0.018 |
Sky | -0.018 |
Anne | -0.018 |
Ellen | -0.018 |
Token | Now |
Token ID | 2735 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Amanda | +0.040 |
basement | +0.039 |
Sky | +0.039 |
Am | +0.038 |
Anne | +0.037 |
Neg logit contributions | |
ishy | -0.050 |
obs | -0.046 |
ory | -0.045 |
fiber | -0.045 |
inters | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
Am | +0.029 |
basement | +0.028 |
Amanda | +0.027 |
Sky | +0.027 |
Anne | +0.027 |
Neg logit contributions | |
ishy | -0.046 |
fiber | -0.045 |
ory | -0.045 |
preferences | -0.042 |
ouses | -0.041 |
Token | go |
Token ID | 467 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
Am | +0.070 |
Amanda | +0.069 |
basement | +0.067 |
Sky | +0.067 |
Ellen | +0.065 |
Neg logit contributions | |
ishy | -0.114 |
fiber | -0.108 |
ory | -0.107 |
inters | -0.104 |
preferences | -0.103 |
Token | matching |
Token ID | 12336 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ishy | +0.048 |
ashed | +0.046 |
ory | +0.046 |
uggets | +0.044 |
inters | +0.043 |
Neg logit contributions | |
Amanda | -0.035 |
Anne | -0.034 |
Am | -0.034 |
basement | -0.033 |
Ellen | -0.033 |
Token | p |
Token ID | 279 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
ishy | +0.033 |
ory | +0.029 |
ashed | +0.029 |
obs | +0.028 |
inters | +0.028 |
Neg logit contributions | |
Amanda | -0.033 |
Am | -0.032 |
Anne | -0.032 |
Sky | -0.032 |
basement | -0.031 |
Token | aj |
Token ID | 1228 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
fiber | +0.055 |
ishy | +0.054 |
ashed | +0.049 |
iness | +0.048 |
uggets | +0.047 |
Neg logit contributions | |
Amanda | -0.075 |
Am | -0.072 |
Jean | -0.070 |
basement | -0.070 |
Anne | -0.070 |
Token | amas |
Token ID | 17485 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ishy | +0.102 |
ory | +0.088 |
ashed | +0.087 |
inters | +0.086 |
fiber | +0.086 |
Neg logit contributions | |
Amanda | -0.123 |
Anne | -0.120 |
Am | -0.119 |
Sky | -0.118 |
Ellen | -0.117 |
Token | with |
Token ID | 351 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ishy | +0.044 |
obs | +0.041 |
ory | +0.039 |
ashed | +0.038 |
inters | +0.038 |
Neg logit contributions | |
Amanda | -0.039 |
Sky | -0.038 |
Am | -0.038 |
basement | -0.037 |
Ellen | -0.037 |
Token | com |
Token ID | 401 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
ishy | +0.036 |
ory | +0.033 |
ashed | +0.033 |
inters | +0.032 |
obs | +0.032 |
Neg logit contributions | |
Amanda | -0.021 |
Am | -0.020 |
Sky | -0.020 |
Anne | -0.020 |
George | -0.019 |
Token | ets |
Token ID | 1039 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
emo | +0.122 |
iness | +0.112 |
uggets | +0.112 |
sensation | +0.105 |
kin | +0.104 |
Neg logit contributions | |
� | -0.174 |
, | -0.159 |
Am | -0.157 |
's | -0.153 |
close | -0.152 |
Token | on |
Token ID | 319 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ishy | +0.074 |
obs | +0.068 |
ory | +0.067 |
fiber | +0.066 |
inters | +0.066 |
Neg logit contributions | |
Amanda | -0.054 |
Am | -0.052 |
Sky | -0.052 |
Anne | -0.051 |
Ellen | -0.051 |
Token | them |
Token ID | 606 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ishy | +0.035 |
obs | +0.033 |
ory | +0.032 |
fiber | +0.031 |
uggets | +0.031 |
Neg logit contributions | |
Amanda | -0.019 |
Sky | -0.019 |
Am | -0.019 |
Ellen | -0.019 |
basement | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ishy | +0.085 |
obs | +0.077 |
ory | +0.077 |
fiber | +0.075 |
inters | +0.075 |
Neg logit contributions | |
Amanda | -0.062 |
Am | -0.059 |
Sky | -0.059 |
Anne | -0.058 |
Ellen | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
ishy | +0.003 |
obs | +0.003 |
ory | +0.003 |
fiber | +0.003 |
inters | +0.003 |
Neg logit contributions | |
Amanda | -0.002 |
Am | -0.002 |
Sky | -0.002 |
basement | -0.002 |
Anne | -0.002 |
Token | paint |
Token ID | 7521 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ishy | +0.046 |
obs | +0.041 |
ory | +0.041 |
ashed | +0.041 |
inters | +0.041 |
Neg logit contributions | |
Amanda | -0.026 |
Am | -0.025 |
Sky | -0.024 |
Anne | -0.024 |
Ellen | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ishy | +0.049 |
obs | +0.045 |
ory | +0.044 |
fiber | +0.044 |
inters | +0.043 |
Neg logit contributions | |
Amanda | -0.021 |
Am | -0.021 |
basement | -0.020 |
Anne | -0.020 |
Sky | -0.020 |
Token | same |
Token ID | 976 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Amanda | +0.004 |
Am | +0.004 |
Sky | +0.004 |
Anne | +0.004 |
basement | +0.004 |
Neg logit contributions | |
ishy | -0.008 |
ory | -0.007 |
obs | -0.007 |
fiber | -0.007 |
inters | -0.007 |
Token | flower |
Token ID | 15061 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ishy | +0.030 |
obs | +0.027 |
ory | +0.026 |
fiber | +0.026 |
ashed | +0.026 |
Neg logit contributions | |
Amanda | -0.023 |
Am | -0.022 |
Sky | -0.022 |
Anne | -0.022 |
Ellen | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ishy | +0.020 |
obs | +0.018 |
ory | +0.018 |
ouses | +0.017 |
ashes | +0.017 |
Neg logit contributions | |
Am | -0.012 |
Alice | -0.011 |
Amanda | -0.011 |
Ellen | -0.011 |
K | -0.011 |
Token | |
Token ID | 220 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
ishy | +0.068 |
ory | +0.062 |
obs | +0.062 |
fiber | +0.062 |
inters | +0.061 |
Neg logit contributions | |
Amanda | -0.023 |
Anne | -0.021 |
Sky | -0.021 |
Am | -0.020 |
Ellen | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ishy | +0.269 |
ory | +0.248 |
obs | +0.247 |
fiber | +0.245 |
ashed | +0.243 |
Neg logit contributions | |
Amanda | -0.085 |
Am | -0.078 |
Anne | -0.078 |
Sky | -0.078 |
Ellen | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ishy | +0.056 |
ory | +0.052 |
obs | +0.052 |
inters | +0.051 |
ashed | +0.051 |
Neg logit contributions | |
Amanda | -0.028 |
Am | -0.027 |
Sky | -0.026 |
basement | -0.026 |
Anne | -0.026 |
Token | L |
Token ID | 43 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
ishy | +0.009 |
ashed | +0.008 |
obs | +0.008 |
ory | +0.008 |
inters | +0.008 |
Neg logit contributions | |
Amanda | -0.007 |
Sky | -0.007 |
Am | -0.006 |
Anne | -0.006 |
George | -0.006 |
Token | ily |
Token ID | 813 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ishy | +0.024 |
obs | +0.023 |
fiber | +0.023 |
inters | +0.022 |
ory | +0.022 |
Neg logit contributions | |
also | -0.015 |
basement | -0.015 |
Anne | -0.015 |
Amanda | -0.015 |
Am | -0.014 |
Token | got |
Token ID | 1392 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
Amanda | +0.005 |
Sky | +0.005 |
basement | +0.005 |
Am | +0.005 |
Ellen | +0.005 |
Neg logit contributions | |
ishy | -0.008 |
ashed | -0.008 |
obs | -0.008 |
ory | -0.008 |
inters | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
ishy | +0.054 |
obs | +0.049 |
ory | +0.049 |
fiber | +0.048 |
inters | +0.048 |
Neg logit contributions | |
Amanda | -0.032 |
Am | -0.031 |
Sky | -0.031 |
Anne | -0.031 |
basement | -0.030 |
Token | try |
Token ID | 1949 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ishy | +0.026 |
obs | +0.024 |
ory | +0.024 |
fiber | +0.023 |
inters | +0.023 |
Neg logit contributions | |
Amanda | -0.014 |
Am | -0.013 |
Sky | -0.013 |
Anne | -0.013 |
Ellen | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
ishy | +0.060 |
obs | +0.057 |
ory | +0.056 |
inters | +0.054 |
fiber | +0.054 |
Neg logit contributions | |
Amanda | -0.034 |
Am | -0.033 |
basement | -0.032 |
Sky | -0.032 |
Anne | -0.032 |
Token | out |
Token ID | 503 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
ishy | +0.066 |
obs | +0.060 |
ory | +0.060 |
inters | +0.059 |
ashed | +0.059 |
Neg logit contributions | |
Am | -0.031 |
Amanda | -0.031 |
Anne | -0.029 |
basement | -0.029 |
Sky | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ishy | +0.021 |
obs | +0.020 |
ory | +0.020 |
inters | +0.019 |
uggets | +0.019 |
Neg logit contributions | |
basement | -0.016 |
Amanda | -0.016 |
Am | -0.016 |
Ellen | -0.015 |
Sky | -0.015 |
Token | |
Token ID | 220 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
ishy | +0.056 |
ory | +0.052 |
obs | +0.051 |
fiber | +0.051 |
ashed | +0.050 |
Neg logit contributions | |
Amanda | -0.021 |
Anne | -0.020 |
Sky | -0.020 |
George | -0.020 |
Ellen | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ishy | +0.279 |
ory | +0.256 |
fiber | +0.255 |
obs | +0.254 |
ashed | +0.252 |
Neg logit contributions | |
Amanda | -0.075 |
Sky | -0.069 |
Anne | -0.069 |
Am | -0.068 |
also | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ishy | +0.058 |
ory | +0.054 |
obs | +0.054 |
inters | +0.052 |
ashed | +0.052 |
Neg logit contributions | |
Amanda | -0.028 |
Am | -0.026 |
Sky | -0.026 |
basement | -0.026 |
Anne | -0.026 |
Token | Tim |
Token ID | 14967 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ishy | +0.012 |
obs | +0.011 |
ory | +0.011 |
inters | +0.011 |
ashed | +0.011 |
Neg logit contributions | |
Amanda | -0.007 |
Sky | -0.007 |
Am | -0.007 |
Anne | -0.006 |
Ellen | -0.006 |
Token | my |
Token ID | 1820 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Amanda | +0.009 |
Am | +0.008 |
Sky | +0.008 |
Anne | +0.008 |
Ellen | +0.008 |
Neg logit contributions | |
ishy | -0.013 |
ory | -0.011 |
obs | -0.011 |
ashed | -0.011 |
fiber | -0.011 |
Token | pulled |
Token ID | 5954 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Amanda | +0.013 |
Am | +0.012 |
Sky | +0.012 |
basement | +0.012 |
Ellen | +0.012 |
Neg logit contributions | |
ishy | -0.016 |
ashed | -0.015 |
ory | -0.014 |
obs | -0.014 |
inters | -0.014 |
Token | ates |
Token ID | 689 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ishy | +0.142 |
ory | +0.122 |
inters | +0.120 |
ashed | +0.119 |
fiber | +0.116 |
Neg logit contributions | |
Am | -0.184 |
Sky | -0.177 |
Amanda | -0.175 |
Anne | -0.168 |
Jean | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
ishy | +0.043 |
obs | +0.040 |
ory | +0.039 |
inters | +0.038 |
fiber | +0.038 |
Neg logit contributions | |
Amanda | -0.030 |
Am | -0.029 |
Sky | -0.028 |
Anne | -0.028 |
Ellen | -0.028 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ishy | +0.011 |
obs | +0.009 |
ory | +0.009 |
fiber | +0.009 |
inters | +0.009 |
Neg logit contributions | |
Amanda | -0.009 |
Am | -0.008 |
Sky | -0.008 |
Anne | -0.008 |
Ellen | -0.008 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ishy | +0.006 |
ashed | +0.005 |
obs | +0.005 |
ory | +0.005 |
ouses | +0.005 |
Neg logit contributions | |
Amanda | -0.005 |
Ellen | -0.005 |
Am | -0.005 |
basement | -0.005 |
Sky | -0.005 |
Token | ch |
Token ID | 442 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ishy | +0.040 |
obs | +0.036 |
ory | +0.036 |
fiber | +0.036 |
inters | +0.035 |
Neg logit contributions | |
Amanda | -0.021 |
Am | -0.020 |
Sky | -0.020 |
Anne | -0.019 |
Ellen | -0.019 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
ishy | +0.035 |
ashed | +0.032 |
obs | +0.029 |
ory | +0.029 |
fiber | +0.029 |
Neg logit contributions | |
Sky | -0.086 |
Amanda | -0.085 |
Am | -0.082 |
Anne | -0.080 |
June | -0.079 |
Token | ates |
Token ID | 689 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ishy | +0.162 |
ory | +0.138 |
inters | +0.137 |
ashed | +0.136 |
obs | +0.131 |
Neg logit contributions | |
Am | -0.193 |
Sky | -0.188 |
Amanda | -0.184 |
Anne | -0.176 |
Jean | -0.176 |
Token | . |
Token ID | 13 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
ishy | +0.044 |
obs | +0.040 |
ory | +0.040 |
fiber | +0.039 |
ashed | +0.038 |
Neg logit contributions | |
Amanda | -0.030 |
Am | -0.029 |
Sky | -0.028 |
Anne | -0.028 |
Ellen | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ishy | +0.023 |
obs | +0.021 |
ory | +0.021 |
ashed | +0.021 |
fiber | +0.021 |
Neg logit contributions | |
Amanda | -0.009 |
Sky | -0.008 |
Anne | -0.008 |
Am | -0.008 |
Ellen | -0.008 |
Token | thanked |
Token ID | 26280 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ishy | +0.040 |
ashed | +0.036 |
ory | +0.036 |
obs | +0.035 |
fiber | +0.035 |
Neg logit contributions | |
Amanda | -0.034 |
Ellen | -0.033 |
basement | -0.033 |
Am | -0.033 |
Sky | -0.032 |
Token | Ben |
Token ID | 3932 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
Amanda | +0.007 |
Sky | +0.007 |
Am | +0.007 |
Anne | +0.006 |
Ellen | +0.006 |
Neg logit contributions | |
ishy | -0.011 |
obs | -0.010 |
ashed | -0.010 |
ory | -0.010 |
inters | -0.010 |
Token | colorful |
Token ID | 20239 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Amanda | +0.016 |
Sky | +0.016 |
Am | +0.015 |
Anne | +0.015 |
basement | +0.015 |
Neg logit contributions | |
ishy | -0.017 |
ory | -0.015 |
obs | -0.015 |
fiber | -0.015 |
ouses | -0.014 |
Token | cand |
Token ID | 2658 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
ishy | +0.031 |
obs | +0.028 |
ory | +0.028 |
fiber | +0.027 |
inters | +0.027 |
Neg logit contributions | |
Amanda | -0.029 |
Am | -0.028 |
Sky | -0.028 |
Anne | -0.028 |
Ellen | -0.027 |
Token | ies |
Token ID | 444 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
ishy | +0.040 |
inters | +0.032 |
ashed | +0.032 |
fiber | +0.031 |
inter | +0.031 |
Neg logit contributions | |
Amanda | -0.097 |
Am | -0.096 |
also | -0.095 |
never | -0.093 |
Sky | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
ishy | +0.022 |
obs | +0.021 |
ory | +0.021 |
ashed | +0.020 |
fiber | +0.020 |
Neg logit contributions | |
Amanda | -0.012 |
Am | -0.011 |
Sky | -0.011 |
Anne | -0.011 |
basement | -0.011 |
Token | ch |
Token ID | 442 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ishy | +0.115 |
obs | +0.104 |
ory | +0.103 |
inters | +0.102 |
ashed | +0.101 |
Neg logit contributions | |
Amanda | -0.074 |
Am | -0.070 |
Anne | -0.070 |
Sky | -0.070 |
Ellen | -0.068 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
ishy | +0.049 |
fiber | +0.046 |
obs | +0.043 |
inter | +0.043 |
inters | +0.042 |
Neg logit contributions | |
Amanda | -0.083 |
Sky | -0.078 |
Am | -0.078 |
Sunshine | -0.074 |
Jean | -0.074 |
Token | ates |
Token ID | 689 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ishy | +0.154 |
inters | +0.130 |
ory | +0.129 |
obs | +0.125 |
fiber | +0.125 |
Neg logit contributions | |
Am | -0.198 |
Amanda | -0.192 |
Sky | -0.191 |
Jean | -0.182 |
Anne | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
ishy | +0.049 |
fiber | +0.044 |
obs | +0.044 |
inters | +0.044 |
ory | +0.043 |
Neg logit contributions | |
Amanda | -0.027 |
Am | -0.025 |
Sky | -0.025 |
Anne | -0.025 |
also | -0.024 |
Token | She |
Token ID | 1375 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ishy | +0.017 |
obs | +0.016 |
ory | +0.016 |
ashed | +0.016 |
inters | +0.016 |
Neg logit contributions | |
Amanda | -0.008 |
Am | -0.008 |
Sky | -0.007 |
Anne | -0.007 |
basement | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ishy | +0.029 |
ory | +0.027 |
ashed | +0.027 |
fiber | +0.026 |
obs | +0.026 |
Neg logit contributions | |
Amanda | -0.021 |
basement | -0.021 |
Sky | -0.021 |
Ellen | -0.021 |
Am | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
ory | +0.040 |
ashed | +0.040 |
ishy | +0.040 |
uggets | +0.038 |
uc | +0.038 |
Neg logit contributions | |
basement | -0.027 |
Am | -0.023 |
loft | -0.023 |
cinema | -0.023 |
Anne | -0.022 |
Token | cakes |
Token ID | 30849 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Ellen | +0.029 |
Amanda | +0.029 |
June | +0.028 |
Anne | +0.028 |
Elizabeth | +0.028 |
Neg logit contributions | |
ishy | -0.039 |
fiber | -0.036 |
obs | -0.035 |
uggets | -0.035 |
inters | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
Amanda | +0.009 |
Am | +0.009 |
Anne | +0.008 |
Ellen | +0.008 |
Sky | +0.008 |
Neg logit contributions | |
ishy | -0.019 |
obs | -0.018 |
ory | -0.018 |
ashed | -0.017 |
uggets | -0.017 |
Token | cookies |
Token ID | 14746 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
ishy | +0.078 |
obs | +0.069 |
ory | +0.068 |
fiber | +0.068 |
inters | +0.067 |
Neg logit contributions | |
Amanda | -0.086 |
Am | -0.083 |
Sky | -0.082 |
Anne | -0.082 |
Ellen | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
ishy | +0.020 |
obs | +0.018 |
ory | +0.018 |
ashed | +0.018 |
inters | +0.017 |
Neg logit contributions | |
Amanda | -0.011 |
Am | -0.011 |
Sky | -0.011 |
Anne | -0.011 |
Ellen | -0.011 |
Token | ch |
Token ID | 442 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ishy | +0.083 |
obs | +0.073 |
ory | +0.073 |
fiber | +0.071 |
inters | +0.071 |
Neg logit contributions | |
Amanda | -0.085 |
Am | -0.083 |
Sky | -0.082 |
Anne | -0.082 |
Ellen | -0.081 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.89e+00 |
Pos logit contributions | |
ishy | +0.048 |
fiber | +0.047 |
ouses | +0.046 |
obs | +0.046 |
ory | +0.045 |
Neg logit contributions | |
Sky | -0.078 |
Amanda | -0.076 |
Am | -0.074 |
Jean | -0.070 |
never | -0.070 |
Token | ates |
Token ID | 689 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ishy | +0.147 |
ory | +0.128 |
inters | +0.123 |
obs | +0.121 |
fiber | +0.120 |
Neg logit contributions | |
Am | -0.198 |
Sky | -0.196 |
Amanda | -0.196 |
Jean | -0.186 |
Anne | -0.185 |
Token | and |
Token ID | 290 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
ishy | +0.063 |
obs | +0.057 |
ory | +0.057 |
fiber | +0.056 |
inters | +0.056 |
Neg logit contributions | |
Amanda | -0.037 |
Am | -0.036 |
Sky | -0.036 |
Anne | -0.035 |
Ellen | -0.034 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ishy | +0.104 |
obs | +0.093 |
ory | +0.092 |
inters | +0.090 |
ashed | +0.090 |
Neg logit contributions | |
Amanda | -0.095 |
Am | -0.092 |
Sky | -0.092 |
Anne | -0.092 |
Ellen | -0.090 |
Token | cream |
Token ID | 8566 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ishy | +0.057 |
fiber | +0.054 |
itted | +0.052 |
ory | +0.051 |
inters | +0.051 |
Neg logit contributions | |
Sky | -0.046 |
Amanda | -0.045 |
shop | -0.044 |
never | -0.044 |
also | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
ishy | +0.033 |
obs | +0.029 |
ory | +0.029 |
fiber | +0.029 |
inters | +0.029 |
Neg logit contributions | |
Amanda | -0.021 |
Am | -0.020 |
Sky | -0.020 |
Anne | -0.020 |
Ellen | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
ishy | +0.022 |
ory | +0.020 |
obs | +0.019 |
ouses | +0.019 |
ashed | +0.019 |
Neg logit contributions | |
Amanda | -0.021 |
Am | -0.021 |
basement | -0.021 |
Ellen | -0.020 |
Sky | -0.020 |
Token | filled |
Token ID | 5901 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Amanda | +0.010 |
Am | +0.010 |
Sky | +0.010 |
Anne | +0.009 |
basement | +0.009 |
Neg logit contributions | |
ishy | -0.019 |
ory | -0.018 |
obs | -0.018 |
uggets | -0.017 |
ashed | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Amanda | +0.033 |
Am | +0.031 |
Sky | +0.030 |
basement | +0.030 |
Anne | +0.029 |
Neg logit contributions | |
ishy | -0.066 |
ory | -0.062 |
uggets | -0.062 |
obs | -0.061 |
ouses | -0.060 |
Token | delicious |
Token ID | 12625 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ishy | +0.008 |
obs | +0.007 |
inters | +0.007 |
ashed | +0.007 |
ory | +0.007 |
Neg logit contributions | |
Amanda | -0.006 |
Am | -0.006 |
Anne | -0.006 |
Sky | -0.006 |
George | -0.006 |
Token | ch |
Token ID | 442 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ishy | +0.038 |
ashed | +0.034 |
inters | +0.034 |
ory | +0.033 |
obs | +0.033 |
Neg logit contributions | |
Amanda | -0.037 |
Sky | -0.035 |
Am | -0.034 |
Anne | -0.034 |
George | -0.034 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
ishy | +0.033 |
fiber | +0.030 |
ory | +0.029 |
uggets | +0.029 |
ashed | +0.029 |
Neg logit contributions | |
Amanda | -0.070 |
Am | -0.069 |
Sky | -0.068 |
June | -0.066 |
Anne | -0.065 |
Token | ates |
Token ID | 689 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ishy | +0.156 |
ory | +0.133 |
inters | +0.132 |
ashed | +0.130 |
fiber | +0.127 |
Neg logit contributions | |
Am | -0.195 |
Sky | -0.190 |
Amanda | -0.187 |
Jean | -0.179 |
Anne | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
ishy | +0.038 |
obs | +0.034 |
ory | +0.034 |
fiber | +0.034 |
inters | +0.034 |
Neg logit contributions | |
Amanda | -0.024 |
Am | -0.023 |
Sky | -0.023 |
Anne | -0.023 |
Ellen | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Amanda | +0.011 |
Am | +0.011 |
basement | +0.011 |
Sky | +0.011 |
Anne | +0.011 |
Neg logit contributions | |
ishy | -0.018 |
ory | -0.017 |
obs | -0.017 |
ashed | -0.016 |
inters | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
basement | +0.023 |
Ellen | +0.021 |
Amanda | +0.021 |
Sky | +0.021 |
Am | +0.020 |
Neg logit contributions | |
ishy | -0.025 |
ory | -0.024 |
ashed | -0.024 |
ushed | -0.022 |
obs | -0.022 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
basement | +0.035 |
Sky | +0.033 |
Amanda | +0.033 |
Ellen | +0.032 |
loft | +0.032 |
Neg logit contributions | |
ishy | -0.056 |
uggets | -0.052 |
itted | -0.052 |
ashed | -0.052 |
ory | -0.051 |
Token | oll |
Token ID | 692 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
ishy | +0.033 |
fiber | +0.028 |
obs | +0.028 |
inters | +0.028 |
ory | +0.027 |
Neg logit contributions | |
Sky | -0.054 |
Am | -0.054 |
Amanda | -0.054 |
� | -0.053 |
Anne | -0.052 |
Token | ip |
Token ID | 541 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ishy | +0.059 |
ashes | +0.056 |
obs | +0.056 |
itted | +0.055 |
inters | +0.054 |
Neg logit contributions | |
never | -0.072 |
also | -0.070 |
Sky | -0.070 |
Amanda | -0.069 |
George | -0.068 |
Token | ops |
Token ID | 2840 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ishy | +0.037 |
obs | +0.029 |
uggets | +0.029 |
inters | +0.028 |
ory | +0.028 |
Neg logit contributions | |
Amanda | -0.087 |
never | -0.086 |
Sky | -0.086 |
� | -0.086 |
Am | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Amanda | +0.003 |
Am | +0.003 |
Ellen | +0.003 |
Anne | +0.003 |
Sky | +0.003 |
Neg logit contributions | |
ishy | -0.005 |
obs | -0.005 |
ory | -0.005 |
ashed | -0.005 |
inters | -0.005 |
Token | ch |
Token ID | 442 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ishy | +0.005 |
ory | +0.005 |
obs | +0.005 |
fiber | +0.005 |
uggets | +0.005 |
Neg logit contributions | |
Amanda | -0.003 |
Am | -0.003 |
basement | -0.003 |
Ellen | -0.003 |
Anne | -0.003 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
ishy | +0.023 |
obs | +0.023 |
ouses | +0.022 |
uggets | +0.021 |
preferences | +0.021 |
Neg logit contributions | |
Sky | -0.051 |
Amanda | -0.049 |
Am | -0.048 |
� | -0.047 |
never | -0.046 |
Token | ates |
Token ID | 689 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
ishy | +0.164 |
inters | +0.144 |
ory | +0.139 |
obs | +0.138 |
fiber | +0.136 |
Neg logit contributions | |
Am | -0.180 |
Sky | -0.175 |
Amanda | -0.167 |
never | -0.162 |
K | -0.161 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ishy | +0.025 |
ory | +0.024 |
obs | +0.023 |
fiber | +0.023 |
ashed | +0.023 |
Neg logit contributions | |
Amanda | -0.011 |
Am | -0.011 |
Ellen | -0.011 |
basement | -0.011 |
Anne | -0.011 |
Token | g |
Token ID | 308 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
ishy | +0.042 |
obs | +0.038 |
ory | +0.038 |
fiber | +0.038 |
inters | +0.037 |
Neg logit contributions | |
Amanda | -0.028 |
basement | -0.027 |
Am | -0.027 |
Ellen | -0.027 |
Anne | -0.026 |
Token | ummies |
Token ID | 39578 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ishy | +0.068 |
fiber | +0.063 |
inters | +0.063 |
ashed | +0.061 |
inter | +0.059 |
Neg logit contributions | |
Amanda | -0.093 |
Sky | -0.090 |
Am | -0.088 |
Anne | -0.086 |
George | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ishy | +0.018 |
ory | +0.016 |
obs | +0.016 |
fiber | +0.016 |
ashed | +0.016 |
Neg logit contributions | |
Amanda | -0.009 |
basement | -0.009 |
Am | -0.008 |
Ellen | -0.008 |
Anne | -0.008 |
Token | as |
Token ID | 355 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
ishy | +0.013 |
obs | +0.012 |
ory | +0.012 |
inters | +0.012 |
fiber | +0.012 |
Neg logit contributions | |
Amanda | -0.011 |
Am | -0.011 |
Sky | -0.011 |
Anne | -0.011 |
Ellen | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ishy | +0.029 |
obs | +0.027 |
ory | +0.027 |
inters | +0.026 |
fiber | +0.026 |
Neg logit contributions | |
Amanda | -0.016 |
Am | -0.016 |
basement | -0.015 |
Sky | -0.015 |
Anne | -0.015 |
Token | opened |
Token ID | 4721 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
ishy | +0.049 |
ory | +0.044 |
obs | +0.044 |
ashed | +0.044 |
inters | +0.043 |
Neg logit contributions | |
Amanda | -0.036 |
Sky | -0.035 |
Am | -0.035 |
Anne | -0.034 |
Ellen | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
Sky | +0.012 |
Am | +0.012 |
Amanda | +0.012 |
basement | +0.011 |
Elizabeth | +0.011 |
Neg logit contributions | |
ishy | -0.025 |
obs | -0.023 |
ory | -0.023 |
uggets | -0.022 |
inters | -0.022 |
Token | ch |
Token ID | 442 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Amanda | +0.015 |
Anne | +0.014 |
Sky | +0.014 |
Ellen | +0.013 |
Elizabeth | +0.013 |
Neg logit contributions | |
ishy | -0.030 |
obs | -0.028 |
ory | -0.028 |
inters | -0.027 |
fiber | -0.027 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
ishy | +0.015 |
fiber | +0.013 |
obs | +0.012 |
inters | +0.012 |
uggets | +0.012 |
Neg logit contributions | |
Amanda | -0.033 |
Am | -0.032 |
Sky | -0.032 |
Anne | -0.032 |
Ellen | -0.031 |
Token | ates |
Token ID | 689 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
ishy | +0.151 |
ory | +0.127 |
inters | +0.127 |
ashed | +0.126 |
fiber | +0.124 |
Neg logit contributions | |
Am | -0.198 |
Sky | -0.190 |
Amanda | -0.189 |
Anne | -0.179 |
Jean | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ishy | +0.009 |
obs | +0.009 |
ory | +0.009 |
uggets | +0.008 |
ashed | +0.008 |
Neg logit contributions | |
Amanda | -0.007 |
Sky | -0.007 |
Ellen | -0.007 |
Am | -0.007 |
Anne | -0.007 |
Token | started |
Token ID | 2067 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ishy | +0.058 |
ory | +0.054 |
obs | +0.053 |
ashed | +0.053 |
fiber | +0.052 |
Neg logit contributions | |
Am | -0.036 |
Amanda | -0.035 |
basement | -0.035 |
Ellen | -0.034 |
Sky | -0.034 |
Token | eating |
Token ID | 6600 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Amanda | +0.027 |
Am | +0.026 |
basement | +0.026 |
Sky | +0.026 |
Ellen | +0.025 |
Neg logit contributions | |
ishy | -0.044 |
obs | -0.042 |
ashed | -0.040 |
ory | -0.040 |
inters | -0.040 |
Token | them |
Token ID | 606 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Amanda | +0.008 |
Am | +0.007 |
Anne | +0.007 |
Sky | +0.007 |
Ellen | +0.007 |
Neg logit contributions | |
ishy | -0.015 |
ory | -0.014 |
obs | -0.013 |
fiber | -0.013 |
inters | -0.013 |
Token | friend |
Token ID | 1545 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
ishy | +0.056 |
obs | +0.050 |
ory | +0.050 |
fiber | +0.049 |
ashed | +0.049 |
Neg logit contributions | |
Amanda | -0.040 |
Am | -0.038 |
Sky | -0.038 |
Anne | -0.037 |
Ellen | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
basement | +0.010 |
Am | +0.009 |
loft | +0.009 |
outskirts | +0.009 |
Flash | +0.008 |
Neg logit contributions | |
ory | -0.017 |
ishy | -0.016 |
ashed | -0.016 |
uggets | -0.016 |
uns | -0.015 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ishy | +0.015 |
ory | +0.015 |
uggets | +0.015 |
obs | +0.014 |
ashed | +0.014 |
Neg logit contributions | |
Am | -0.011 |
loft | -0.011 |
basement | -0.011 |
Amanda | -0.011 |
outskirts | -0.011 |
Token | my |
Token ID | 1820 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Amanda | +0.000 |
Am | +0.000 |
Sky | +0.000 |
Anne | +0.000 |
basement | +0.000 |
Neg logit contributions | |
ishy | -0.000 |
ory | -0.000 |
obs | -0.000 |
inters | -0.000 |
fiber | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
ishy | +0.005 |
obs | +0.005 |
ory | +0.005 |
fiber | +0.005 |
inters | +0.005 |
Neg logit contributions | |
Amanda | -0.002 |
Am | -0.002 |
Anne | -0.002 |
Sky | -0.002 |
Ellen | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
ishy | +0.032 |
obs | +0.030 |
ory | +0.030 |
fiber | +0.029 |
ashed | +0.029 |
Neg logit contributions | |
Amanda | -0.014 |
Am | -0.014 |
Sky | -0.013 |
Anne | -0.013 |
Ellen | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ishy | +0.268 |
ory | +0.247 |
fiber | +0.245 |
obs | +0.245 |
ashed | +0.241 |
Neg logit contributions | |
Amanda | -0.081 |
Anne | -0.075 |
Sky | -0.075 |
Am | -0.075 |
Ellen | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ishy | +0.050 |
ory | +0.046 |
obs | +0.046 |
ashed | +0.045 |
inters | +0.045 |
Neg logit contributions | |
Amanda | -0.028 |
basement | -0.027 |
Am | -0.027 |
Sky | -0.027 |
Anne | -0.026 |
Token | Tim |
Token ID | 14967 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ishy | +0.007 |
ashed | +0.006 |
ory | +0.006 |
obs | +0.006 |
inters | +0.006 |
Neg logit contributions | |
Amanda | -0.003 |
Sky | -0.003 |
Am | -0.003 |
Anne | -0.003 |
basement | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
Amanda | +0.010 |
Am | +0.010 |
Sky | +0.010 |
Anne | +0.010 |
Ellen | +0.009 |
Neg logit contributions | |
ishy | -0.016 |
obs | -0.014 |
ory | -0.014 |
fiber | -0.014 |
inters | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Amanda | +0.008 |
Am | +0.008 |
basement | +0.008 |
Sky | +0.008 |
Ellen | +0.008 |
Neg logit contributions | |
ishy | -0.010 |
ory | -0.010 |
obs | -0.010 |
ashed | -0.009 |
fiber | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Amanda | +0.030 |
Anne | +0.027 |
Am | +0.027 |
Sky | +0.027 |
Ellen | +0.026 |
Neg logit contributions | |
ishy | -0.084 |
fiber | -0.078 |
obs | -0.078 |
ory | -0.077 |
inters | -0.076 |
Token | What |
Token ID | 2061 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Amanda | +0.035 |
Sky | +0.033 |
Anne | +0.033 |
Ellen | +0.032 |
Am | +0.032 |
Neg logit contributions | |
ishy | -0.050 |
ory | -0.046 |
fiber | -0.045 |
obs | -0.045 |
ashed | -0.044 |
Token | are |
Token ID | 389 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
ishy | +0.021 |
obs | +0.019 |
ory | +0.019 |
fiber | +0.019 |
inters | +0.019 |
Neg logit contributions | |
Amanda | -0.011 |
Am | -0.011 |
Sky | -0.011 |
Anne | -0.011 |
Ellen | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Amanda | +0.063 |
Am | +0.061 |
Anne | +0.059 |
Sky | +0.058 |
Ellen | +0.056 |
Neg logit contributions | |
ishy | -0.113 |
obs | -0.104 |
ory | -0.104 |
fiber | -0.103 |
inters | -0.102 |
Token | doing |
Token ID | 1804 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ishy | +0.052 |
ory | +0.047 |
uc | +0.047 |
uggets | +0.046 |
obs | +0.046 |
Neg logit contributions | |
Amanda | -0.035 |
Sky | -0.034 |
Am | -0.033 |
Anne | -0.033 |
Ellen | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -6.74e+00 |
Pos logit contributions | |
Am | +0.034 |
Amanda | +0.033 |
Sky | +0.032 |
K | +0.030 |
loft | +0.030 |
Neg logit contributions | |
ishy | -0.057 |
ory | -0.053 |
uggets | -0.052 |
uc | -0.052 |
obs | -0.051 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Amanda | +0.171 |
Am | +0.169 |
Sky | +0.165 |
Anne | +0.165 |
Ellen | +0.162 |
Neg logit contributions | |
ishy | -0.164 |
ory | -0.151 |
fiber | -0.144 |
ashed | -0.138 |
obs | -0.136 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Amanda | +0.051 |
Sky | +0.048 |
Am | +0.047 |
Anne | +0.045 |
Ellen | +0.045 |
Neg logit contributions | |
ishy | -0.082 |
ory | -0.076 |
obs | -0.075 |
inters | -0.072 |
fiber | -0.072 |
Token | Lily |
Token ID | 20037 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
Amanda | +0.025 |
Am | +0.024 |
Sky | +0.024 |
Anne | +0.023 |
Ellen | +0.023 |
Neg logit contributions | |
ishy | -0.049 |
obs | -0.045 |
ory | -0.045 |
fiber | -0.044 |
inters | -0.044 |
Token | ? |
Token ID | 30 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Amanda | +0.020 |
Sky | +0.019 |
Am | +0.019 |
Anne | +0.017 |
Flash | +0.017 |
Neg logit contributions | |
ishy | -0.025 |
ory | -0.023 |
obs | -0.023 |
inters | -0.023 |
uc | -0.022 |
Token | Why |
Token ID | 4162 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Amanda | +0.043 |
Am | +0.042 |
Sky | +0.041 |
Ellen | +0.040 |
Anne | +0.040 |
Neg logit contributions | |
ishy | -0.057 |
obs | -0.053 |
uggets | -0.051 |
inters | -0.051 |
ory | -0.050 |
Token | " |
Token ID | 366 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Amanda | +0.034 |
Am | +0.033 |
basement | +0.033 |
Anne | +0.032 |
Sky | +0.032 |
Neg logit contributions | |
ishy | -0.058 |
obs | -0.056 |
inters | -0.055 |
ashed | -0.054 |
itted | -0.054 |
Token | What |
Token ID | 2061 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Am | +0.038 |
Amanda | +0.037 |
Sky | +0.035 |
basement | +0.034 |
Anne | +0.034 |
Neg logit contributions | |
ishy | -0.071 |
obs | -0.065 |
ory | -0.064 |
ashed | -0.064 |
inters | -0.064 |
Token | are |
Token ID | 389 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
ishy | +0.007 |
obs | +0.006 |
ory | +0.006 |
fiber | +0.006 |
ashed | +0.006 |
Neg logit contributions | |
Amanda | -0.005 |
Am | -0.005 |
Sky | -0.005 |
Anne | -0.005 |
Ellen | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Amanda | +0.065 |
Am | +0.063 |
Anne | +0.060 |
Sky | +0.060 |
Ellen | +0.058 |
Neg logit contributions | |
ishy | -0.130 |
ory | -0.119 |
obs | -0.119 |
fiber | -0.119 |
inters | -0.118 |
Token | doing |
Token ID | 1804 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ishy | +0.045 |
ory | +0.041 |
uc | +0.040 |
obs | +0.040 |
uggets | +0.040 |
Neg logit contributions | |
Amanda | -0.028 |
Sky | -0.027 |
Am | -0.027 |
Anne | -0.026 |
Ellen | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
Am | +0.042 |
Amanda | +0.042 |
Sky | +0.040 |
K | +0.036 |
Jean | +0.036 |
Neg logit contributions | |
ishy | -0.066 |
ory | -0.061 |
uggets | -0.059 |
obs | -0.059 |
uc | -0.059 |
Token | Sara |
Token ID | 24799 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Amanda | +0.147 |
basement | +0.145 |
Ellen | +0.145 |
Anne | +0.145 |
Am | +0.142 |
Neg logit contributions | |
ishy | -0.179 |
ory | -0.169 |
fiber | -0.159 |
uggets | -0.152 |
obs | -0.151 |
Token | and |
Token ID | 290 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
Amanda | +0.027 |
Sky | +0.026 |
Am | +0.025 |
Anne | +0.024 |
Ellen | +0.024 |
Neg logit contributions | |
ishy | -0.040 |
ory | -0.037 |
obs | -0.037 |
inters | -0.035 |
ashed | -0.035 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Amanda | +0.012 |
Am | +0.011 |
Anne | +0.011 |
Sky | +0.011 |
basement | +0.011 |
Neg logit contributions | |
ishy | -0.019 |
ory | -0.018 |
obs | -0.017 |
fiber | -0.017 |
inters | -0.017 |
Token | ? |
Token ID | 30 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Amanda | +0.047 |
Am | +0.045 |
Sky | +0.044 |
Anne | +0.042 |
Ellen | +0.042 |
Neg logit contributions | |
ishy | -0.068 |
ory | -0.063 |
obs | -0.061 |
inters | -0.061 |
ashed | -0.060 |
Token | Why |
Token ID | 4162 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Amanda | +0.048 |
Am | +0.047 |
Sky | +0.046 |
Anne | +0.045 |
Ellen | +0.045 |
Neg logit contributions | |
ishy | -0.071 |
obs | -0.065 |
inters | -0.063 |
ory | -0.063 |
ashed | -0.062 |
Token | " |
Token ID | 1 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Amanda | +0.035 |
Ellen | +0.033 |
basement | +0.033 |
George | +0.033 |
Anne | +0.032 |
Neg logit contributions | |
ishy | -0.064 |
fiber | -0.061 |
ouses | -0.059 |
obs | -0.059 |
uns | -0.058 |
Token | What |
Token ID | 2061 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
Amanda | +0.030 |
Anne | +0.029 |
Sky | +0.029 |
Ellen | +0.028 |
Am | +0.028 |
Neg logit contributions | |
ishy | -0.048 |
ory | -0.044 |
fiber | -0.044 |
obs | -0.043 |
ashed | -0.043 |
Token | are |
Token ID | 389 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
ishy | +0.018 |
obs | +0.017 |
ory | +0.017 |
inters | +0.017 |
ashed | +0.016 |
Neg logit contributions | |
� | -0.012 |
Anne | -0.012 |
Amanda | -0.012 |
also | -0.012 |
Sky | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Amanda | +0.057 |
Am | +0.054 |
Anne | +0.053 |
Sky | +0.053 |
Ellen | +0.051 |
Neg logit contributions | |
ishy | -0.122 |
ory | -0.112 |
obs | -0.112 |
fiber | -0.110 |
inters | -0.109 |
Token | doing |
Token ID | 1804 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ishy | +0.049 |
ory | +0.045 |
uc | +0.044 |
uggets | +0.044 |
ashed | +0.044 |
Neg logit contributions | |
Amanda | -0.031 |
Sky | -0.030 |
Am | -0.030 |
Anne | -0.029 |
Ellen | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
Am | +0.040 |
Amanda | +0.038 |
Sky | +0.037 |
K | +0.036 |
loft | +0.035 |
Neg logit contributions | |
ishy | -0.071 |
ory | -0.066 |
uggets | -0.065 |
uc | -0.064 |
obs | -0.063 |
Token | my |
Token ID | 616 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
outskirts | +0.124 |
basement | +0.123 |
Ellen | +0.122 |
Am | +0.121 |
Amanda | +0.119 |
Neg logit contributions | |
ishy | -0.184 |
ory | -0.171 |
fiber | -0.168 |
ashes | -0.156 |
ashed | -0.154 |
Token | little |
Token ID | 1310 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ishy | +0.010 |
fiber | +0.010 |
inters | +0.009 |
itted | +0.009 |
ory | +0.009 |
Neg logit contributions | |
Amanda | -0.007 |
also | -0.007 |
never | -0.007 |
Anne | -0.007 |
basement | -0.007 |
Token | artists |
Token ID | 7912 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
basement | +0.024 |
Amanda | +0.024 |
Sky | +0.024 |
shop | +0.023 |
also | +0.023 |
Neg logit contributions | |
ishy | -0.041 |
ouses | -0.038 |
itted | -0.038 |
obs | -0.038 |
ashed | -0.038 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Amanda | +0.041 |
Sky | +0.040 |
Am | +0.039 |
Anne | +0.036 |
Elizabeth | +0.036 |
Neg logit contributions | |
ishy | -0.082 |
ory | -0.076 |
obs | -0.074 |
uc | -0.073 |
ashed | -0.072 |
Token | she |
Token ID | 673 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Am | +0.026 |
basement | +0.026 |
Amanda | +0.025 |
Ellen | +0.024 |
loft | +0.024 |
Neg logit contributions | |
ishy | -0.038 |
fiber | -0.034 |
obs | -0.034 |
ory | -0.033 |
itted | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Amanda | +0.004 |
Am | +0.004 |
Sky | +0.004 |
Anne | +0.004 |
Ellen | +0.004 |
Neg logit contributions | |
ishy | -0.005 |
obs | -0.005 |
ory | -0.005 |
fiber | -0.005 |
inters | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Amanda | +0.025 |
Am | +0.024 |
Sky | +0.023 |
Anne | +0.023 |
Ellen | +0.022 |
Neg logit contributions | |
ishy | -0.059 |
obs | -0.055 |
ory | -0.054 |
inters | -0.054 |
ashed | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Amanda | +0.029 |
Am | +0.028 |
Sky | +0.027 |
Anne | +0.027 |
Ellen | +0.027 |
Neg logit contributions | |
ishy | -0.051 |
obs | -0.047 |
ory | -0.047 |
fiber | -0.047 |
inters | -0.046 |
Token | " |
Token ID | 1 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Amanda | +0.041 |
Anne | +0.037 |
Sky | +0.037 |
George | +0.036 |
Ellen | +0.036 |
Neg logit contributions | |
ishy | -0.097 |
fiber | -0.090 |
ory | -0.089 |
obs | -0.089 |
ouses | -0.088 |
Token | Oh |
Token ID | 5812 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Amanda | +0.044 |
Sky | +0.041 |
Anne | +0.041 |
Ellen | +0.041 |
Am | +0.040 |
Neg logit contributions | |
ishy | -0.056 |
ory | -0.051 |
fiber | -0.050 |
ashed | -0.050 |
obs | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
Am | +0.035 |
Amanda | +0.033 |
loft | +0.033 |
Ellen | +0.032 |
Sunshine | +0.032 |
Neg logit contributions | |
ishy | -0.071 |
ory | -0.063 |
fiber | -0.062 |
uc | -0.062 |
ashed | -0.062 |
Token | no |
Token ID | 645 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Amanda | +0.113 |
Am | +0.111 |
Sky | +0.105 |
Ellen | +0.105 |
Anne | +0.104 |
Neg logit contributions | |
ishy | -0.203 |
ory | -0.188 |
fiber | -0.185 |
ashed | -0.179 |
obs | -0.177 |
Token | , |
Token ID | 11 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
Amanda | +0.006 |
Am | +0.006 |
Sky | +0.005 |
Ellen | +0.005 |
Anne | +0.005 |
Neg logit contributions | |
ishy | -0.015 |
ory | -0.014 |
fiber | -0.014 |
obs | -0.014 |
ashed | -0.013 |
Token | what |
Token ID | 644 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Amanda | +0.098 |
Am | +0.096 |
Sky | +0.091 |
Ellen | +0.090 |
Anne | +0.090 |
Neg logit contributions | |
ishy | -0.198 |
ory | -0.182 |
fiber | -0.180 |
ashed | -0.175 |
obs | -0.174 |
Token | a |
Token ID | 257 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
Amanda | +0.030 |
Anne | +0.029 |
Sky | +0.029 |
Am | +0.029 |
basement | +0.028 |
Neg logit contributions | |
ishy | -0.047 |
obs | -0.042 |
ory | -0.042 |
fiber | -0.041 |
inters | -0.041 |
Token | mess |
Token ID | 2085 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
Amanda | +0.077 |
Am | +0.073 |
Ellen | +0.070 |
Sky | +0.070 |
Elizabeth | +0.069 |
Neg logit contributions | |
ishy | -0.104 |
inters | -0.090 |
obs | -0.090 |
ashed | -0.089 |
ory | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Amanda | +0.009 |
basement | +0.009 |
Ellen | +0.009 |
Am | +0.009 |
Anne | +0.009 |
Neg logit contributions | |
ishy | -0.013 |
obs | -0.013 |
ory | -0.013 |
fiber | -0.013 |
uggets | -0.013 |
Token | " |
Token ID | 1 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Amanda | +0.028 |
Ellen | +0.027 |
Jean | +0.027 |
basement | +0.026 |
Anne | +0.026 |
Neg logit contributions | |
ishy | -0.048 |
fiber | -0.046 |
ouses | -0.046 |
ory | -0.046 |
uggets | -0.045 |
Token | What |
Token ID | 2061 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
Amanda | +0.025 |
Anne | +0.024 |
Sky | +0.024 |
Ellen | +0.024 |
June | +0.023 |
Neg logit contributions | |
ishy | -0.034 |
ory | -0.032 |
fiber | -0.032 |
ashed | -0.031 |
obs | -0.031 |
Token | 's |
Token ID | 338 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ishy | +0.025 |
obs | +0.023 |
ory | +0.023 |
fiber | +0.022 |
inters | +0.022 |
Neg logit contributions | |
Amanda | -0.015 |
Am | -0.014 |
Sky | -0.014 |
Anne | -0.014 |
Ellen | -0.013 |
Token | wrong |
Token ID | 2642 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Amanda | +0.035 |
Am | +0.034 |
Sky | +0.033 |
Anne | +0.032 |
June | +0.029 |
Neg logit contributions | |
ishy | -0.075 |
inters | -0.068 |
obs | -0.068 |
ory | -0.067 |
fiber | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
Am | +0.016 |
Amanda | +0.016 |
Sky | +0.015 |
Anne | +0.015 |
Ellen | +0.014 |
Neg logit contributions | |
ishy | -0.039 |
ory | -0.038 |
obs | -0.037 |
uggets | -0.036 |
ashed | -0.035 |
Token | sweet |
Token ID | 6029 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
K | +0.137 |
Ellen | +0.136 |
Am | +0.133 |
outskirts | +0.133 |
basement | +0.133 |
Neg logit contributions | |
ishy | -0.164 |
ory | -0.161 |
fiber | -0.146 |
uggets | -0.143 |
ashes | -0.137 |
Token | ies |
Token ID | 444 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Amanda | +0.034 |
Am | +0.034 |
Sky | +0.033 |
Anne | +0.033 |
Ellen | +0.033 |
Neg logit contributions | |
ishy | -0.014 |
ory | -0.011 |
obs | -0.011 |
fiber | -0.011 |
ashed | -0.010 |
Token | ? |
Token ID | 30 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Amanda | +0.039 |
Sky | +0.038 |
Am | +0.037 |
Anne | +0.036 |
Ellen | +0.035 |
Neg logit contributions | |
ishy | -0.065 |
ory | -0.062 |
obs | -0.059 |
iness | -0.058 |
inters | -0.057 |
Token | What |
Token ID | 1867 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Am | +0.044 |
Amanda | +0.043 |
Ellen | +0.042 |
basement | +0.042 |
Alice | +0.042 |
Neg logit contributions | |
ishy | -0.058 |
obs | -0.054 |
inters | -0.052 |
uggets | -0.051 |
ory | -0.051 |
Token | scared |
Token ID | 12008 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
ishy | +0.035 |
fiber | +0.032 |
preferences | +0.031 |
ory | +0.031 |
obs | +0.031 |
Neg logit contributions | |
Amanda | -0.025 |
Am | -0.025 |
Ellen | -0.024 |
K | -0.023 |
Sky | -0.023 |
Token | Stop |
Token ID | 19485 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Am | +0.023 |
Amanda | +0.022 |
� | +0.022 |
Sky | +0.021 |
Anne | +0.021 |
Neg logit contributions | |
ishy | -0.048 |
ory | -0.044 |
obs | -0.044 |
ouses | -0.043 |
uggets | -0.043 |
Token | it |
Token ID | 340 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Am | +0.021 |
Amanda | +0.021 |
basement | +0.020 |
Sky | +0.020 |
loft | +0.019 |
Neg logit contributions | |
ishy | -0.034 |
obs | -0.032 |
ory | -0.031 |
inters | -0.030 |
fiber | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
Am | +0.046 |
Amanda | +0.045 |
Anne | +0.043 |
Flash | +0.043 |
Alice | +0.042 |
Neg logit contributions | |
ishy | -0.038 |
iness | -0.033 |
ory | -0.033 |
ies | -0.032 |
ashes | -0.032 |
Token | Leave |
Token ID | 17446 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Amanda | +0.058 |
Am | +0.057 |
Anne | +0.055 |
Sky | +0.055 |
Ellen | +0.054 |
Neg logit contributions | |
ishy | -0.085 |
obs | -0.078 |
ory | -0.077 |
inters | -0.076 |
ashed | -0.076 |
Token | our |
Token ID | 674 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Amanda | +0.053 |
Am | +0.053 |
Sky | +0.047 |
Anne | +0.047 |
Ellen | +0.046 |
Neg logit contributions | |
ishy | -0.112 |
ory | -0.104 |
obs | -0.102 |
inters | -0.101 |
fiber | -0.101 |
Token | barrel |
Token ID | 9036 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
basement | +0.029 |
Amanda | +0.029 |
Sky | +0.027 |
never | +0.027 |
George | +0.027 |
Neg logit contributions | |
ishy | -0.053 |
obs | -0.050 |
fiber | -0.049 |
itted | -0.049 |
ory | -0.048 |
Token | alone |
Token ID | 3436 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Amanda | +0.154 |
Am | +0.145 |
Elizabeth | +0.144 |
Ellen | +0.142 |
Anne | +0.141 |
Neg logit contributions | |
ishy | -0.173 |
ashed | -0.153 |
inters | -0.152 |
ashes | -0.150 |
obs | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Amanda | +0.040 |
Am | +0.038 |
Elizabeth | +0.038 |
Ellen | +0.038 |
Anne | +0.038 |
Neg logit contributions | |
ishy | -0.039 |
obs | -0.034 |
ory | -0.034 |
ashed | -0.034 |
inters | -0.034 |
Token | It |
Token ID | 632 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Amanda | +0.047 |
Am | +0.046 |
Sky | +0.045 |
Anne | +0.044 |
Ellen | +0.044 |
Neg logit contributions | |
ishy | -0.069 |
obs | -0.064 |
ory | -0.063 |
inters | -0.062 |
fiber | -0.062 |
Token | 's |
Token ID | 338 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Amanda | +0.041 |
Am | +0.040 |
Ellen | +0.039 |
Anne | +0.038 |
Elizabeth | +0.038 |
Neg logit contributions | |
ishy | -0.062 |
ashed | -0.058 |
inters | -0.057 |
ashes | -0.055 |
obs | -0.053 |
Token | ours |
Token ID | 16903 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Amanda | +0.034 |
Am | +0.032 |
Sky | +0.032 |
Anne | +0.032 |
Ellen | +0.031 |
Neg logit contributions | |
ishy | -0.061 |
obs | -0.056 |
ory | -0.055 |
inters | -0.055 |
ashed | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Amanda | +0.017 |
Am | +0.016 |
Sky | +0.016 |
Anne | +0.016 |
Ellen | +0.016 |
Neg logit contributions | |
ishy | -0.044 |
obs | -0.040 |
ory | -0.040 |
fiber | -0.040 |
inters | -0.040 |
Token | " |
Token ID | 1 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Amanda | +0.028 |
Anne | +0.026 |
Sky | +0.026 |
Am | +0.025 |
Ellen | +0.025 |
Neg logit contributions | |
ishy | -0.085 |
ory | -0.079 |
obs | -0.079 |
fiber | -0.078 |
ashed | -0.078 |
Token | Where |
Token ID | 8496 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Am | +0.026 |
Amanda | +0.026 |
Sky | +0.024 |
Anne | +0.024 |
Ellen | +0.024 |
Neg logit contributions | |
ishy | -0.054 |
obs | -0.049 |
inters | -0.049 |
ory | -0.049 |
ashed | -0.047 |
Token | were |
Token ID | 547 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
ishy | +0.005 |
ory | +0.004 |
obs | +0.004 |
ashed | +0.004 |
fiber | +0.004 |
Neg logit contributions | |
Amanda | -0.003 |
Am | -0.003 |
Sky | -0.003 |
Ellen | -0.003 |
Anne | -0.003 |
Token | you |
Token ID | 345 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Amanda | +0.075 |
Am | +0.074 |
basement | +0.072 |
Anne | +0.072 |
loft | +0.071 |
Neg logit contributions | |
ishy | -0.115 |
ory | -0.112 |
fiber | -0.107 |
obs | -0.105 |
ashed | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
ishy | +0.063 |
ory | +0.062 |
uggets | +0.056 |
obs | +0.055 |
uc | +0.055 |
Neg logit contributions | |
Amanda | -0.040 |
Sky | -0.040 |
Anne | -0.037 |
Am | -0.037 |
Ellen | -0.037 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Amanda | +0.121 |
Am | +0.116 |
Sky | +0.115 |
Anne | +0.114 |
Ellen | +0.113 |
Neg logit contributions | |
ishy | -0.191 |
ory | -0.175 |
obs | -0.172 |
fiber | -0.170 |
ashed | -0.169 |
Token | and |
Token ID | 290 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Amanda | +0.044 |
Sky | +0.042 |
Am | +0.040 |
Anne | +0.039 |
Ellen | +0.038 |
Neg logit contributions | |
ishy | -0.074 |
ory | -0.071 |
obs | -0.068 |
fiber | -0.066 |
ashed | -0.065 |
Token | Lily |
Token ID | 20037 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Amanda | +0.020 |
Sky | +0.019 |
Anne | +0.019 |
Am | +0.019 |
Ellen | +0.019 |
Neg logit contributions | |
ishy | -0.049 |
obs | -0.047 |
inters | -0.045 |
fiber | -0.044 |
ory | -0.044 |
Token | ?" |
Token ID | 1701 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
Amanda | +0.017 |
Sky | +0.017 |
Am | +0.016 |
Anne | +0.015 |
Ellen | +0.015 |
Neg logit contributions | |
ishy | -0.028 |
ory | -0.028 |
obs | -0.026 |
inters | -0.025 |
ashed | -0.025 |
Token | their |
Token ID | 511 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
Amanda | +0.016 |
Am | +0.015 |
Sky | +0.015 |
Anne | +0.015 |
Ellen | +0.015 |
Neg logit contributions | |
ishy | -0.030 |
ory | -0.028 |
obs | -0.028 |
fiber | -0.027 |
ashed | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Amanda | +0.014 |
Am | +0.014 |
Sky | +0.013 |
Anne | +0.013 |
Ellen | +0.013 |
Neg logit contributions | |
ishy | -0.036 |
obs | -0.034 |
ory | -0.033 |
inters | -0.033 |
fiber | -0.033 |
Token | says |
Token ID | 1139 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Sunshine | +0.026 |
Am | +0.026 |
Amanda | +0.026 |
basement | +0.026 |
Ellen | +0.026 |
Neg logit contributions | |
ishy | -0.027 |
ory | -0.024 |
irk | -0.024 |
ashes | -0.024 |
uc | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Am | +0.003 |
basement | +0.003 |
outskirts | +0.003 |
Amanda | +0.003 |
K | +0.003 |
Neg logit contributions | |
ishy | -0.005 |
ory | -0.005 |
obs | -0.005 |
ashed | -0.005 |
uc | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Amanda | +0.037 |
Am | +0.036 |
basement | +0.036 |
Anne | +0.035 |
Ellen | +0.035 |
Neg logit contributions | |
ishy | -0.060 |
obs | -0.057 |
ashed | -0.056 |
fiber | -0.056 |
inters | -0.056 |
Token | Stop |
Token ID | 19485 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Amanda | +0.039 |
Sky | +0.037 |
Anne | +0.037 |
Am | +0.036 |
Ellen | +0.036 |
Neg logit contributions | |
ishy | -0.063 |
ory | -0.057 |
obs | -0.057 |
fiber | -0.056 |
inters | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
Amanda | +0.024 |
Am | +0.024 |
Sky | +0.023 |
basement | +0.022 |
Anne | +0.022 |
Neg logit contributions | |
ishy | -0.048 |
obs | -0.045 |
ory | -0.045 |
fiber | -0.043 |
inters | -0.043 |
Token | stop |
Token ID | 2245 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Amanda | +0.126 |
Am | +0.123 |
Ellen | +0.120 |
Sky | +0.119 |
Anne | +0.119 |
Neg logit contributions | |
ishy | -0.184 |
ory | -0.168 |
fiber | -0.157 |
ashed | -0.156 |
ashes | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
Amanda | +0.041 |
Am | +0.039 |
Sky | +0.039 |
Ellen | +0.038 |
Anne | +0.038 |
Neg logit contributions | |
ishy | -0.075 |
obs | -0.070 |
ory | -0.069 |
fiber | -0.066 |
inters | -0.066 |
Token | stop |
Token ID | 2245 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Amanda | +0.112 |
Am | +0.111 |
Ellen | +0.107 |
Sky | +0.105 |
Anne | +0.105 |
Neg logit contributions | |
ishy | -0.179 |
ory | -0.160 |
fiber | -0.154 |
ashed | -0.152 |
inters | -0.152 |
Token | ! |
Token ID | 0 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Amanda | +0.042 |
Sky | +0.040 |
Am | +0.040 |
Ellen | +0.039 |
Anne | +0.039 |
Neg logit contributions | |
ishy | -0.064 |
obs | -0.059 |
ory | -0.058 |
inters | -0.056 |
fiber | -0.056 |
Token | What |
Token ID | 1867 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
Amanda | +0.064 |
Am | +0.063 |
Sky | +0.062 |
Ellen | +0.061 |
Anne | +0.060 |
Neg logit contributions | |
ishy | -0.082 |
obs | -0.075 |
ory | -0.073 |
inters | -0.073 |
ashed | -0.072 |
Token | 're |
Token ID | 821 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Amanda | +0.006 |
never | +0.006 |
Am | +0.005 |
� | +0.005 |
also | +0.005 |
Neg logit contributions | |
ishy | -0.008 |
obs | -0.008 |
ory | -0.007 |
uggets | -0.007 |
fiber | -0.007 |
Token | glad |
Token ID | 9675 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Amanda | +0.082 |
Am | +0.080 |
Sky | +0.079 |
Anne | +0.078 |
loft | +0.076 |
Neg logit contributions | |
ishy | -0.073 |
itted | -0.062 |
ippers | -0.061 |
akers | -0.060 |
obs | -0.060 |
Token | you |
Token ID | 345 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
basement | +0.039 |
Amanda | +0.039 |
Am | +0.037 |
Ellen | +0.037 |
loft | +0.037 |
Neg logit contributions | |
ishy | -0.064 |
ory | -0.062 |
fiber | -0.060 |
obs | -0.059 |
uggets | -0.058 |
Token | 're |
Token ID | 821 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ishy | +0.061 |
uggets | +0.060 |
obs | +0.060 |
ouses | +0.057 |
ocol | +0.057 |
Neg logit contributions | |
never | -0.031 |
also | -0.030 |
� | -0.029 |
Amanda | -0.027 |
Ellen | -0.026 |
Token | okay |
Token ID | 8788 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
Amanda | +0.043 |
Am | +0.043 |
Sky | +0.041 |
Anne | +0.041 |
loft | +0.040 |
Neg logit contributions | |
ishy | -0.038 |
itted | -0.033 |
akers | -0.033 |
ippers | -0.032 |
uggets | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
ishy | +0.003 |
ory | +0.003 |
obs | +0.002 |
uggets | +0.002 |
fiber | +0.002 |
Neg logit contributions | |
Amanda | -0.002 |
Am | -0.002 |
basement | -0.002 |
Sky | -0.002 |
Ellen | -0.002 |
Token | Anna |
Token ID | 11735 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
basement | +0.099 |
outskirts | +0.099 |
Amanda | +0.096 |
K | +0.096 |
Ellen | +0.095 |
Neg logit contributions | |
ishy | -0.192 |
ory | -0.184 |
fiber | -0.179 |
preferences | -0.170 |
ashed | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Amanda | +0.046 |
Am | +0.044 |
Sky | +0.044 |
Anne | +0.043 |
Ellen | +0.043 |
Neg logit contributions | |
ishy | -0.054 |
obs | -0.049 |
ory | -0.049 |
ashed | -0.048 |
fiber | -0.047 |
Token | We |
Token ID | 775 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Amanda | +0.057 |
Am | +0.054 |
Sky | +0.054 |
Anne | +0.054 |
Ellen | +0.053 |
Neg logit contributions | |
ishy | -0.095 |
obs | -0.086 |
ory | -0.086 |
fiber | -0.085 |
ashed | -0.084 |
Token | love |
Token ID | 1842 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
never | +0.005 |
Amanda | +0.005 |
also | +0.005 |
� | +0.005 |
Am | +0.005 |
Neg logit contributions | |
ishy | -0.007 |
obs | -0.007 |
uggets | -0.007 |
ory | -0.006 |
fiber | -0.006 |
Token | you |
Token ID | 345 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Amanda | +0.024 |
Sky | +0.023 |
Anne | +0.023 |
Am | +0.022 |
never | +0.021 |
Neg logit contributions | |
ishy | -0.073 |
obs | -0.068 |
ory | -0.066 |
ashed | -0.066 |
inters | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Amanda | +0.008 |
Am | +0.008 |
Sky | +0.007 |
Anne | +0.007 |
Ellen | +0.007 |
Neg logit contributions | |
ishy | -0.007 |
obs | -0.006 |
inters | -0.006 |
ory | -0.006 |
ashes | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Amanda | +0.020 |
basement | +0.019 |
Anne | +0.018 |
Sky | +0.018 |
Am | +0.018 |
Neg logit contributions | |
ishy | -0.044 |
ory | -0.040 |
fiber | -0.040 |
obs | -0.039 |
uggets | -0.039 |
Token | said |
Token ID | 531 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
Sky | +0.037 |
Amanda | +0.036 |
Am | +0.036 |
Anne | +0.035 |
basement | +0.035 |
Neg logit contributions | |
ishy | -0.036 |
ashed | -0.033 |
ory | -0.033 |
uc | -0.031 |
inters | -0.031 |
Token | " |
Token ID | 366 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Am | +0.001 |
Amanda | +0.001 |
basement | +0.001 |
Sky | +0.001 |
Ellen | +0.001 |
Neg logit contributions | |
ishy | -0.003 |
ory | -0.003 |
obs | -0.003 |
ashed | -0.003 |
uggets | -0.003 |
Token | Stop |
Token ID | 19485 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Am | +0.033 |
Amanda | +0.032 |
also | +0.030 |
never | +0.030 |
basement | +0.029 |
Neg logit contributions | |
ishy | -0.070 |
obs | -0.063 |
fiber | -0.063 |
ouses | -0.063 |
inters | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
Am | +0.027 |
Amanda | +0.027 |
Sky | +0.027 |
loft | +0.026 |
basement | +0.026 |
Neg logit contributions | |
ishy | -0.058 |
ory | -0.055 |
obs | -0.054 |
uc | -0.052 |
fiber | -0.052 |
Token | L |
Token ID | 406 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Amanda | +0.139 |
Am | +0.135 |
Sky | +0.134 |
Anne | +0.134 |
Ellen | +0.132 |
Neg logit contributions | |
ishy | -0.169 |
ory | -0.152 |
obs | -0.148 |
fiber | -0.147 |
ashed | -0.146 |
Token | ila |
Token ID | 10102 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Am | +0.019 |
Amanda | +0.019 |
Sky | +0.018 |
� | +0.018 |
Anne | +0.018 |
Neg logit contributions | |
ishy | -0.025 |
fiber | -0.022 |
inters | -0.022 |
obs | -0.022 |
uggets | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Amanda | +0.043 |
Sky | +0.041 |
Am | +0.040 |
Anne | +0.040 |
basement | +0.039 |
Neg logit contributions | |
ishy | -0.048 |
obs | -0.045 |
ory | -0.044 |
inters | -0.043 |
ashed | -0.043 |
Token | Sam |
Token ID | 3409 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
never | +0.019 |
Amanda | +0.019 |
also | +0.018 |
Anne | +0.018 |
Sky | +0.017 |
Neg logit contributions | |
ishy | -0.037 |
obs | -0.034 |
ouses | -0.033 |
fiber | -0.033 |
itted | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Amanda | +0.055 |
Am | +0.054 |
Sky | +0.053 |
Anne | +0.051 |
Ellen | +0.051 |
Neg logit contributions | |
ishy | -0.046 |
obs | -0.041 |
inters | -0.041 |
ory | -0.041 |
ashed | -0.039 |
Token | said |
Token ID | 531 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
ishy | +0.046 |
ory | +0.042 |
obs | +0.042 |
ashed | +0.042 |
fiber | +0.042 |
Neg logit contributions | |
Amanda | -0.031 |
Am | -0.030 |
Sky | -0.030 |
basement | -0.029 |
Anne | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
ishy | +0.030 |
ory | +0.028 |
obs | +0.028 |
ashed | +0.028 |
fiber | +0.028 |
Neg logit contributions | |
Am | -0.013 |
Amanda | -0.012 |
basement | -0.012 |
Anne | -0.011 |
Sky | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Amanda | +0.014 |
Am | +0.013 |
Sky | +0.013 |
basement | +0.013 |
Anne | +0.013 |
Neg logit contributions | |
ishy | -0.026 |
obs | -0.025 |
inters | -0.024 |
fiber | -0.024 |
ashed | -0.024 |
Token | Stop |
Token ID | 19485 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Amanda | +0.035 |
Am | +0.033 |
Sky | +0.033 |
Anne | +0.033 |
Ellen | +0.032 |
Neg logit contributions | |
ishy | -0.060 |
obs | -0.055 |
ory | -0.055 |
fiber | -0.054 |
inters | -0.054 |
Token | it |
Token ID | 340 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Amanda | +0.024 |
Am | +0.023 |
Sky | +0.023 |
basement | +0.022 |
Anne | +0.022 |
Neg logit contributions | |
ishy | -0.053 |
obs | -0.049 |
ory | -0.049 |
inters | -0.047 |
fiber | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
Am | +0.038 |
Amanda | +0.038 |
Flash | +0.037 |
Sunshine | +0.036 |
Sky | +0.035 |
Neg logit contributions | |
ishy | -0.041 |
uc | -0.039 |
iness | -0.037 |
ies | -0.037 |
akers | -0.037 |
Token | both |
Token ID | 1111 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Amanda | +0.109 |
Am | +0.107 |
Sky | +0.103 |
Anne | +0.102 |
Ellen | +0.100 |
Neg logit contributions | |
ishy | -0.197 |
ory | -0.179 |
fiber | -0.174 |
ashed | -0.174 |
inters | -0.172 |
Token | of |
Token ID | 286 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Am | +0.057 |
Amanda | +0.057 |
Sky | +0.056 |
Sunshine | +0.055 |
loft | +0.054 |
Neg logit contributions | |
ishy | -0.063 |
iness | -0.057 |
obs | -0.055 |
inters | -0.054 |
uns | -0.053 |
Token | you |
Token ID | 345 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Amanda | +0.037 |
loft | +0.035 |
Sky | +0.033 |
Am | +0.033 |
Anne | +0.033 |
Neg logit contributions | |
fiber | -0.063 |
ishy | -0.061 |
ory | -0.059 |
ocol | -0.058 |
uc | -0.058 |
Token | ! |
Token ID | 0 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
ishy | +0.004 |
uc | +0.004 |
inters | +0.004 |
obs | +0.004 |
ory | +0.004 |
Neg logit contributions | |
Amanda | -0.003 |
Am | -0.003 |
Sunshine | -0.003 |
Ellen | -0.003 |
Sky | -0.003 |
Token | You |
Token ID | 921 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
Amanda | +0.079 |
Am | +0.077 |
Sky | +0.076 |
Anne | +0.075 |
basement | +0.074 |
Neg logit contributions | |
ishy | -0.093 |
obs | -0.084 |
ory | -0.083 |
inters | -0.083 |
ashed | -0.082 |
Token | " |
Token ID | 366 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Amanda | +0.024 |
Am | +0.023 |
basement | +0.023 |
Ellen | +0.022 |
Anne | +0.022 |
Neg logit contributions | |
ishy | -0.048 |
obs | -0.045 |
ory | -0.044 |
fiber | -0.044 |
ashed | -0.044 |
Token | What |
Token ID | 2061 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Am | +0.026 |
Amanda | +0.025 |
Sky | +0.024 |
Anne | +0.024 |
� | +0.023 |
Neg logit contributions | |
ishy | -0.048 |
obs | -0.043 |
inters | -0.043 |
ory | -0.042 |
ashed | -0.042 |
Token | are |
Token ID | 389 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
ishy | +0.037 |
obs | +0.034 |
ory | +0.034 |
inters | +0.034 |
ashed | +0.033 |
Neg logit contributions | |
Amanda | -0.017 |
Am | -0.016 |
Anne | -0.016 |
Sky | -0.016 |
basement | -0.015 |
Token | you |
Token ID | 345 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Amanda | +0.052 |
Am | +0.049 |
Anne | +0.048 |
Sky | +0.048 |
Ellen | +0.047 |
Neg logit contributions | |
ishy | -0.110 |
ory | -0.101 |
obs | -0.101 |
fiber | -0.100 |
inters | -0.099 |
Token | doing |
Token ID | 1804 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ishy | +0.081 |
obs | +0.075 |
ory | +0.074 |
fiber | +0.073 |
ashed | +0.073 |
Neg logit contributions | |
Amanda | -0.033 |
Am | -0.031 |
Sky | -0.030 |
Anne | -0.030 |
Ellen | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
Amanda | +0.032 |
Am | +0.032 |
Sky | +0.030 |
K | +0.029 |
Jean | +0.028 |
Neg logit contributions | |
ishy | -0.056 |
ory | -0.052 |
uggets | -0.051 |
obs | -0.050 |
ippers | -0.050 |
Token | kids |
Token ID | 3988 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Amanda | +0.132 |
Am | +0.129 |
Ellen | +0.127 |
Sky | +0.126 |
Anne | +0.125 |
Neg logit contributions | |
ishy | -0.174 |
ory | -0.158 |
obs | -0.154 |
fiber | -0.153 |
ashed | -0.150 |
Token | ? |
Token ID | 30 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Amanda | +0.052 |
Sky | +0.050 |
Am | +0.049 |
Anne | +0.046 |
Ellen | +0.046 |
Neg logit contributions | |
ishy | -0.075 |
ory | -0.072 |
obs | -0.068 |
inters | -0.067 |
uggets | -0.067 |
Token | You |
Token ID | 921 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Amanda | +0.041 |
Am | +0.040 |
Sky | +0.039 |
basement | +0.039 |
Anne | +0.039 |
Neg logit contributions | |
ishy | -0.054 |
obs | -0.050 |
ory | -0.048 |
inters | -0.048 |
uggets | -0.048 |
Token | are |
Token ID | 389 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ishy | +0.035 |
ory | +0.032 |
obs | +0.032 |
inters | +0.031 |
fiber | +0.031 |
Neg logit contributions | |
Amanda | -0.022 |
Am | -0.021 |
Sky | -0.021 |
Anne | -0.021 |
Ellen | -0.020 |
Token | making |
Token ID | 1642 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Amanda | +0.044 |
Am | +0.041 |
Ellen | +0.040 |
Anne | +0.040 |
Sky | +0.040 |
Neg logit contributions | |
ishy | -0.081 |
ory | -0.075 |
uggets | -0.074 |
obs | -0.073 |
inters | -0.073 |
Token | " |
Token ID | 1 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Amanda | +0.031 |
basement | +0.029 |
George | +0.029 |
Ellen | +0.029 |
Anne | +0.028 |
Neg logit contributions | |
ishy | -0.057 |
fiber | -0.055 |
obs | -0.054 |
ouses | -0.053 |
ory | -0.053 |
Token | Why |
Token ID | 5195 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
Amanda | +0.032 |
Anne | +0.030 |
Sky | +0.030 |
basement | +0.030 |
Ellen | +0.029 |
Neg logit contributions | |
ishy | -0.043 |
ory | -0.041 |
fiber | -0.041 |
obs | -0.039 |
ashed | -0.039 |
Token | are |
Token ID | 389 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
ishy | +0.020 |
obs | +0.018 |
ory | +0.018 |
fiber | +0.018 |
ashed | +0.018 |
Neg logit contributions | |
Amanda | -0.010 |
Am | -0.010 |
Sky | -0.009 |
Anne | -0.009 |
Ellen | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Am | +0.084 |
Amanda | +0.083 |
basement | +0.081 |
loft | +0.081 |
Anne | +0.078 |
Neg logit contributions | |
ishy | -0.119 |
fiber | -0.113 |
ory | -0.113 |
inters | -0.108 |
uggets | -0.107 |
Token | crying |
Token ID | 13774 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ishy | +0.013 |
ory | +0.012 |
uggets | +0.012 |
itted | +0.012 |
uc | +0.011 |
Neg logit contributions | |
Sky | -0.016 |
Amanda | -0.016 |
loft | -0.016 |
Am | -0.016 |
Elizabeth | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
Amanda | +0.003 |
Am | +0.003 |
Sky | +0.003 |
loft | +0.003 |
Anne | +0.003 |
Neg logit contributions | |
ishy | -0.006 |
ory | -0.006 |
obs | -0.005 |
iness | -0.005 |
uc | -0.005 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
K | +0.128 |
outskirts | +0.124 |
basement | +0.123 |
Jean | +0.120 |
Ellen | +0.120 |
Neg logit contributions | |
ory | -0.159 |
ishy | -0.158 |
fiber | -0.146 |
preferences | -0.137 |
ashes | -0.136 |
Token | and |
Token ID | 290 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Amanda | +0.040 |
Sky | +0.039 |
Am | +0.037 |
Ellen | +0.037 |
Anne | +0.036 |
Neg logit contributions | |
ishy | -0.049 |
ory | -0.045 |
obs | -0.045 |
ouses | -0.042 |
inters | -0.042 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ishy | +0.007 |
ory | +0.006 |
fiber | +0.006 |
obs | +0.006 |
ashed | +0.006 |
Neg logit contributions | |
Amanda | -0.007 |
Am | -0.007 |
Ellen | -0.006 |
basement | -0.006 |
Anne | -0.006 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
Amanda | +0.047 |
Am | +0.044 |
Sky | +0.044 |
Anne | +0.041 |
Ellen | +0.040 |
Neg logit contributions | |
ishy | -0.067 |
ory | -0.063 |
obs | -0.061 |
inters | -0.060 |
fiber | -0.058 |
Token | she |
Token ID | 673 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
basement | +0.014 |
Am | +0.013 |
Amanda | +0.013 |
K | +0.013 |
loft | +0.013 |
Neg logit contributions | |
ishy | -0.021 |
ory | -0.020 |
fiber | -0.019 |
obs | -0.019 |
preferences | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ishy | +0.086 |
ory | +0.079 |
fiber | +0.078 |
obs | +0.078 |
inters | +0.077 |
Neg logit contributions | |
Amanda | -0.042 |
Am | -0.041 |
Sky | -0.041 |
Anne | -0.040 |
basement | -0.039 |
Token | says |
Token ID | 1139 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
ishy | +0.051 |
obs | +0.046 |
fiber | +0.045 |
ashed | +0.044 |
itted | +0.044 |
Neg logit contributions | |
Am | -0.050 |
Amanda | -0.049 |
basement | -0.048 |
Ellen | -0.048 |
Anne | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ishy | +0.029 |
ory | +0.027 |
obs | +0.027 |
fiber | +0.027 |
ashed | +0.027 |
Neg logit contributions | |
basement | -0.013 |
Am | -0.012 |
Amanda | -0.012 |
Ellen | -0.012 |
Anne | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
basement | +0.024 |
Amanda | +0.023 |
Ellen | +0.023 |
Am | +0.022 |
Anne | +0.022 |
Neg logit contributions | |
ishy | -0.031 |
obs | -0.030 |
itted | -0.029 |
inters | -0.029 |
fiber | -0.029 |
Token | Hello |
Token ID | 15496 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Amanda | +0.023 |
Am | +0.022 |
Sky | +0.022 |
Anne | +0.021 |
Ellen | +0.021 |
Neg logit contributions | |
ishy | -0.040 |
obs | -0.036 |
ory | -0.036 |
inters | -0.035 |
fiber | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
Ellen | +0.014 |
basement | +0.014 |
Amanda | +0.014 |
Am | +0.014 |
Anne | +0.014 |
Neg logit contributions | |
ishy | -0.040 |
ory | -0.039 |
obs | -0.036 |
fiber | -0.036 |
ashed | -0.035 |
Token | children |
Token ID | 1751 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
outskirts | +0.157 |
basement | +0.155 |
Anne | +0.154 |
Am | +0.151 |
Ellen | +0.151 |
Neg logit contributions | |
ishy | -0.123 |
ory | -0.120 |
fiber | -0.108 |
ocol | -0.106 |
iness | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Amanda | +0.060 |
Am | +0.058 |
Ellen | +0.058 |
June | +0.057 |
Elizabeth | +0.057 |
Neg logit contributions | |
ishy | -0.042 |
ory | -0.039 |
obs | -0.038 |
inters | -0.035 |
akers | -0.034 |
Token | Do |
Token ID | 2141 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
Am | +0.042 |
Amanda | +0.041 |
basement | +0.040 |
Anne | +0.039 |
Sky | +0.039 |
Neg logit contributions | |
ishy | -0.065 |
obs | -0.060 |
ory | -0.059 |
inters | -0.059 |
fiber | -0.059 |
Token | you |
Token ID | 345 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Amanda | +0.007 |
Am | +0.007 |
Sky | +0.007 |
Anne | +0.007 |
Ellen | +0.006 |
Neg logit contributions | |
ishy | -0.017 |
ory | -0.015 |
obs | -0.015 |
fiber | -0.015 |
inters | -0.015 |
Token | want |
Token ID | 765 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
obs | +0.071 |
uc | +0.069 |
mons | +0.066 |
ouses | +0.063 |
asers | +0.062 |
Neg logit contributions | |
never | -0.055 |
� | -0.054 |
also | -0.053 |
hurry | -0.048 |
hide | -0.044 |
Token | said |
Token ID | 531 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
ishy | +0.011 |
ashed | +0.010 |
ory | +0.010 |
obs | +0.010 |
fiber | +0.010 |
Neg logit contributions | |
Amanda | -0.009 |
basement | -0.009 |
Sky | -0.009 |
Am | -0.009 |
Ellen | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ishy | +0.003 |
ory | +0.003 |
fiber | +0.002 |
obs | +0.002 |
ashed | +0.002 |
Neg logit contributions | |
basement | -0.001 |
Am | -0.001 |
Amanda | -0.001 |
outskirts | -0.001 |
K | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Amanda | +0.039 |
basement | +0.039 |
Am | +0.038 |
Anne | +0.037 |
Ellen | +0.036 |
Neg logit contributions | |
ishy | -0.060 |
obs | -0.057 |
fiber | -0.057 |
ashed | -0.057 |
ory | -0.056 |
Token | Thank |
Token ID | 10449 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Amanda | +0.026 |
Am | +0.025 |
Sky | +0.025 |
Anne | +0.024 |
Ellen | +0.024 |
Neg logit contributions | |
ishy | -0.057 |
obs | -0.052 |
ory | -0.052 |
inters | -0.051 |
ashed | -0.051 |
Token | you |
Token ID | 345 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Amanda | +0.017 |
Am | +0.016 |
Sky | +0.015 |
Anne | +0.015 |
Ellen | +0.015 |
Neg logit contributions | |
ishy | -0.038 |
ory | -0.035 |
obs | -0.035 |
fiber | -0.035 |
ashed | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
ishy | +0.006 |
ory | +0.006 |
obs | +0.006 |
fiber | +0.006 |
uggets | +0.006 |
Neg logit contributions | |
Amanda | -0.003 |
basement | -0.003 |
Am | -0.003 |
Ellen | -0.003 |
Sky | -0.003 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Amanda | +0.119 |
Am | +0.117 |
basement | +0.111 |
Anne | +0.111 |
Sky | +0.111 |
Neg logit contributions | |
ishy | -0.182 |
ory | -0.175 |
fiber | -0.171 |
preferences | -0.160 |
ashed | -0.158 |
Token | and |
Token ID | 290 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Amanda | +0.029 |
Am | +0.028 |
Sky | +0.027 |
Anne | +0.027 |
Ellen | +0.027 |
Neg logit contributions | |
ishy | -0.045 |
obs | -0.041 |
ory | -0.041 |
fiber | -0.040 |
ashed | -0.040 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Amanda | +0.005 |
Sky | +0.005 |
Anne | +0.005 |
Am | +0.005 |
Elizabeth | +0.005 |
Neg logit contributions | |
ishy | -0.009 |
obs | -0.009 |
inters | -0.008 |
ouses | -0.008 |
ashed | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Amanda | +0.040 |
Am | +0.039 |
Sky | +0.038 |
Anne | +0.038 |
Ellen | +0.037 |
Neg logit contributions | |
ishy | -0.055 |
obs | -0.050 |
ory | -0.049 |
fiber | -0.048 |
inters | -0.048 |
Token | I |
Token ID | 314 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Amanda | +0.039 |
Sky | +0.038 |
Anne | +0.037 |
Am | +0.037 |
Ellen | +0.037 |
Neg logit contributions | |
ishy | -0.067 |
ory | -0.061 |
obs | -0.061 |
ashed | -0.060 |
fiber | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Amanda | +0.023 |
Anne | +0.022 |
Ellen | +0.022 |
Am | +0.022 |
basement | +0.022 |
Neg logit contributions | |
ishy | -0.040 |
obs | -0.038 |
fiber | -0.037 |
ory | -0.037 |
ouses | -0.036 |
Token | " |
Token ID | 1 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Amanda | +0.031 |
Anne | +0.030 |
Ellen | +0.028 |
basement | +0.028 |
George | +0.028 |
Neg logit contributions | |
ishy | -0.080 |
fiber | -0.075 |
ory | -0.075 |
obs | -0.075 |
ouses | -0.073 |
Token | What |
Token ID | 2061 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Amanda | +0.039 |
Anne | +0.039 |
Sky | +0.038 |
Ellen | +0.037 |
June | +0.037 |
Neg logit contributions | |
ishy | -0.053 |
ory | -0.051 |
fiber | -0.049 |
obs | -0.048 |
ashed | -0.048 |
Token | 's |
Token ID | 338 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ishy | +0.015 |
obs | +0.014 |
ory | +0.014 |
inters | +0.014 |
fiber | +0.014 |
Neg logit contributions | |
Amanda | -0.010 |
Anne | -0.010 |
Am | -0.010 |
Sky | -0.010 |
basement | -0.009 |
Token | wrong |
Token ID | 2642 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
Amanda | +0.033 |
Am | +0.031 |
Sky | +0.030 |
Anne | +0.030 |
Ellen | +0.028 |
Neg logit contributions | |
ishy | -0.083 |
obs | -0.076 |
ory | -0.076 |
inters | -0.075 |
fiber | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
Amanda | +0.014 |
Sky | +0.014 |
Am | +0.014 |
Anne | +0.013 |
Ellen | +0.013 |
Neg logit contributions | |
ishy | -0.034 |
ory | -0.033 |
obs | -0.031 |
uggets | -0.031 |
fiber | -0.030 |
Token | my |
Token ID | 616 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Anne | +0.150 |
Ellen | +0.149 |
basement | +0.149 |
June | +0.147 |
Amanda | +0.147 |
Neg logit contributions | |
ishy | -0.148 |
ory | -0.143 |
fiber | -0.129 |
obs | -0.122 |
ashes | -0.120 |
Token | adorable |
Token ID | 29012 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ishy | +0.008 |
fiber | +0.008 |
inters | +0.007 |
uns | +0.007 |
uggets | +0.007 |
Neg logit contributions | |
Amanda | -0.007 |
Anne | -0.007 |
basement | -0.007 |
never | -0.006 |
also | -0.006 |
Token | children |
Token ID | 1751 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Amanda | +0.006 |
Anne | +0.006 |
basement | +0.006 |
June | +0.006 |
Sky | +0.006 |
Neg logit contributions | |
ishy | -0.009 |
inters | -0.008 |
fiber | -0.008 |
obs | -0.008 |
ashed | -0.008 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Amanda | +0.034 |
Sky | +0.034 |
Am | +0.034 |
Anne | +0.031 |
K | +0.031 |
Neg logit contributions | |
ishy | -0.051 |
ory | -0.049 |
obs | -0.045 |
inters | -0.045 |
uc | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
Amanda | +0.026 |
basement | +0.026 |
Am | +0.026 |
Anne | +0.026 |
Ellen | +0.025 |
Neg logit contributions | |
ishy | -0.044 |
ory | -0.041 |
obs | -0.040 |
fiber | -0.040 |
inters | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
Amanda | +0.014 |
Am | +0.014 |
Sky | +0.014 |
Anne | +0.013 |
Ellen | +0.013 |
Neg logit contributions | |
ishy | -0.035 |
obs | -0.032 |
ory | -0.032 |
inters | -0.031 |
fiber | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
Amanda | +0.015 |
basement | +0.015 |
Sky | +0.015 |
Anne | +0.015 |
Am | +0.014 |
Neg logit contributions | |
ishy | -0.017 |
ashed | -0.015 |
ory | -0.015 |
obs | -0.015 |
inters | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Am | +0.001 |
basement | +0.001 |
Amanda | +0.001 |
K | +0.001 |
outskirts | +0.001 |
Neg logit contributions | |
ishy | -0.002 |
ory | -0.002 |
ashed | -0.002 |
fiber | -0.002 |
obs | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Amanda | +0.035 |
Am | +0.034 |
basement | +0.033 |
Ellen | +0.032 |
Sky | +0.032 |
Neg logit contributions | |
ishy | -0.064 |
obs | -0.060 |
fiber | -0.059 |
ashed | -0.059 |
inters | -0.059 |
Token | Stop |
Token ID | 19485 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Amanda | +0.036 |
Am | +0.034 |
Sky | +0.034 |
Anne | +0.034 |
Ellen | +0.033 |
Neg logit contributions | |
ishy | -0.067 |
obs | -0.061 |
ory | -0.061 |
inters | -0.060 |
fiber | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
Amanda | +0.025 |
Am | +0.025 |
Sky | +0.025 |
basement | +0.023 |
Anne | +0.023 |
Neg logit contributions | |
ishy | -0.049 |
ory | -0.046 |
obs | -0.046 |
fiber | -0.044 |
ashed | -0.044 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Amanda | +0.120 |
Am | +0.118 |
Ellen | +0.116 |
Jean | +0.114 |
Sky | +0.113 |
Neg logit contributions | |
ishy | -0.180 |
ory | -0.168 |
fiber | -0.157 |
ashed | -0.154 |
ashes | -0.152 |
Token | and |
Token ID | 290 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
Amanda | +0.034 |
Sky | +0.032 |
Am | +0.032 |
basement | +0.031 |
Ellen | +0.031 |
Neg logit contributions | |
ishy | -0.042 |
obs | -0.039 |
ory | -0.039 |
ashed | -0.037 |
akers | -0.036 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Amanda | +0.016 |
Am | +0.016 |
Ellen | +0.016 |
Sky | +0.015 |
Anne | +0.015 |
Neg logit contributions | |
ishy | -0.022 |
ory | -0.020 |
obs | -0.019 |
fiber | -0.019 |
ashed | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
Amanda | +0.046 |
Am | +0.045 |
Sky | +0.043 |
Anne | +0.042 |
basement | +0.041 |
Neg logit contributions | |
ishy | -0.055 |
obs | -0.050 |
ory | -0.049 |
inters | -0.049 |
ashed | -0.047 |
Token | stop |
Token ID | 2245 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Amanda | +0.076 |
Am | +0.074 |
Ellen | +0.072 |
Sky | +0.070 |
Anne | +0.068 |
Neg logit contributions | |
ishy | -0.127 |
ory | -0.118 |
inters | -0.115 |
ashed | -0.114 |
fiber | -0.114 |
Token | She |
Token ID | 1375 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
Amanda | +0.008 |
Am | +0.007 |
Sky | +0.007 |
Anne | +0.007 |
Ellen | +0.007 |
Neg logit contributions | |
ishy | -0.023 |
ory | -0.021 |
obs | -0.021 |
fiber | -0.021 |
ashed | -0.021 |
Token | says |
Token ID | 1139 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Amanda | +0.021 |
Sunshine | +0.021 |
Am | +0.021 |
basement | +0.021 |
Ellen | +0.021 |
Neg logit contributions | |
ishy | -0.022 |
ory | -0.020 |
obs | -0.020 |
irk | -0.020 |
fiber | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Am | +0.006 |
basement | +0.006 |
Amanda | +0.006 |
outskirts | +0.006 |
Anne | +0.006 |
Neg logit contributions | |
ishy | -0.012 |
ory | -0.012 |
obs | -0.011 |
ashed | -0.011 |
uc | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Amanda | +0.035 |
Am | +0.034 |
basement | +0.033 |
Anne | +0.032 |
Sky | +0.032 |
Neg logit contributions | |
ishy | -0.064 |
obs | -0.060 |
inters | -0.059 |
ashed | -0.059 |
fiber | -0.059 |
Token | Oh |
Token ID | 5812 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Amanda | +0.034 |
Am | +0.033 |
Sky | +0.032 |
Anne | +0.032 |
Ellen | +0.031 |
Neg logit contributions | |
ishy | -0.065 |
obs | -0.059 |
ory | -0.059 |
inters | -0.058 |
ashed | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
Am | +0.028 |
loft | +0.027 |
Amanda | +0.026 |
cinema | +0.026 |
basement | +0.026 |
Neg logit contributions | |
ishy | -0.057 |
ory | -0.051 |
fiber | -0.051 |
uc | -0.051 |
obs | -0.049 |
Token | Sara |
Token ID | 24799 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Amanda | +0.116 |
Am | +0.114 |
Anne | +0.113 |
Ellen | +0.112 |
June | +0.112 |
Neg logit contributions | |
ishy | -0.181 |
ory | -0.166 |
fiber | -0.164 |
inters | -0.154 |
obs | -0.153 |
Token | and |
Token ID | 290 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Amanda | +0.015 |
Am | +0.014 |
Sky | +0.014 |
Anne | +0.014 |
basement | +0.014 |
Neg logit contributions | |
ishy | -0.028 |
obs | -0.026 |
ory | -0.025 |
fiber | -0.024 |
ashed | -0.024 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Amanda | +0.007 |
Sky | +0.007 |
Am | +0.007 |
Anne | +0.006 |
Ellen | +0.006 |
Neg logit contributions | |
ishy | -0.015 |
obs | -0.014 |
ory | -0.014 |
ashed | -0.014 |
inters | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
Amanda | +0.032 |
Am | +0.031 |
Sky | +0.030 |
Anne | +0.029 |
basement | +0.029 |
Neg logit contributions | |
ishy | -0.062 |
ory | -0.057 |
obs | -0.056 |
inters | -0.055 |
fiber | -0.055 |
Token | what |
Token ID | 644 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Amanda | +0.081 |
Am | +0.081 |
Ellen | +0.076 |
Sky | +0.076 |
Anne | +0.075 |
Neg logit contributions | |
ishy | -0.122 |
fiber | -0.112 |
ory | -0.112 |
inters | -0.109 |
obs | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Amanda | +0.024 |
Anne | +0.023 |
Ellen | +0.023 |
Sky | +0.023 |
Am | +0.022 |
Neg logit contributions | |
ishy | -0.037 |
obs | -0.035 |
fiber | -0.034 |
ory | -0.034 |
uggets | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Amanda | +0.034 |
Anne | +0.032 |
Sky | +0.031 |
Ellen | +0.031 |
basement | +0.030 |
Neg logit contributions | |
ishy | -0.081 |
fiber | -0.076 |
ory | -0.075 |
obs | -0.074 |
ouses | -0.074 |
Token | What |
Token ID | 2061 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
Amanda | +0.041 |
Anne | +0.039 |
Sky | +0.039 |
Ellen | +0.038 |
Jean | +0.038 |
Neg logit contributions | |
ishy | -0.053 |
fiber | -0.049 |
ory | -0.049 |
ashed | -0.049 |
obs | -0.047 |
Token | 's |
Token ID | 338 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ishy | +0.028 |
obs | +0.026 |
ory | +0.026 |
inters | +0.025 |
ashed | +0.025 |
Neg logit contributions | |
Amanda | -0.012 |
Am | -0.011 |
Sky | -0.011 |
Anne | -0.011 |
Ellen | -0.011 |
Token | wrong |
Token ID | 2642 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
Amanda | +0.028 |
Am | +0.026 |
Sky | +0.025 |
Anne | +0.025 |
Ellen | +0.024 |
Neg logit contributions | |
ishy | -0.082 |
obs | -0.075 |
ory | -0.075 |
fiber | -0.074 |
inters | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
Amanda | +0.011 |
Am | +0.011 |
Sky | +0.011 |
Anne | +0.011 |
Ellen | +0.010 |
Neg logit contributions | |
ishy | -0.028 |
ory | -0.027 |
obs | -0.026 |
uggets | -0.026 |
fiber | -0.025 |
Token | kids |
Token ID | 3988 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Amanda | +0.158 |
Am | +0.155 |
Sky | +0.153 |
Anne | +0.152 |
Ellen | +0.150 |
Neg logit contributions | |
ishy | -0.145 |
ory | -0.131 |
fiber | -0.126 |
obs | -0.124 |
ashed | -0.122 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Amanda | +0.054 |
Sky | +0.052 |
Am | +0.051 |
Anne | +0.048 |
Ellen | +0.047 |
Neg logit contributions | |
ishy | -0.083 |
ory | -0.080 |
obs | -0.076 |
inters | -0.075 |
uc | -0.073 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Amanda | +0.029 |
Am | +0.028 |
Sky | +0.028 |
Anne | +0.027 |
basement | +0.027 |
Neg logit contributions | |
ishy | -0.057 |
ory | -0.052 |
obs | -0.052 |
fiber | -0.051 |
ashed | -0.050 |
Token | asks |
Token ID | 7893 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Amanda | +0.049 |
Sky | +0.049 |
basement | +0.048 |
outskirts | +0.048 |
never | +0.047 |
Neg logit contributions | |
ishy | -0.053 |
obs | -0.051 |
ory | -0.050 |
uns | -0.047 |
irk | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ishy | +0.012 |
obs | +0.011 |
fiber | +0.011 |
ory | +0.011 |
inters | +0.011 |
Neg logit contributions | |
Amanda | -0.008 |
Sky | -0.007 |
Am | -0.007 |
Anne | -0.007 |
Ellen | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Amanda | +0.028 |
Am | +0.027 |
basement | +0.027 |
Sky | +0.026 |
Anne | +0.026 |
Neg logit contributions | |
ishy | -0.056 |
obs | -0.053 |
ashed | -0.052 |
ory | -0.052 |
uggets | -0.051 |
Token | Don |
Token ID | 3987 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
Am | +0.034 |
Amanda | +0.033 |
never | +0.031 |
Alice | +0.031 |
Ellen | +0.031 |
Neg logit contributions | |
ishy | -0.073 |
obs | -0.067 |
ory | -0.066 |
inters | -0.065 |
ouses | -0.065 |
Token | 't |
Token ID | 470 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
Amanda | +0.010 |
loft | +0.010 |
basement | +0.009 |
Am | +0.009 |
Sky | +0.009 |
Neg logit contributions | |
ishy | -0.019 |
abs | -0.019 |
uc | -0.019 |
ashed | -0.018 |
ory | -0.018 |
Token | be |
Token ID | 307 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Amanda | +0.018 |
Am | +0.017 |
Sky | +0.017 |
Anne | +0.017 |
basement | +0.017 |
Neg logit contributions | |
ishy | -0.022 |
ory | -0.020 |
fiber | -0.020 |
inters | -0.019 |
obs | -0.019 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Amanda | +0.012 |
Sky | +0.011 |
Am | +0.011 |
Anne | +0.011 |
basement | +0.011 |
Neg logit contributions | |
ishy | -0.012 |
obs | -0.011 |
inters | -0.011 |
ashed | -0.010 |
ory | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
ishy | +0.005 |
ory | +0.005 |
obs | +0.005 |
ashed | +0.004 |
inters | +0.004 |
Neg logit contributions | |
Am | -0.002 |
Amanda | -0.002 |
Sky | -0.002 |
basement | -0.002 |
Anne | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Amanda | +0.118 |
Am | +0.114 |
Sky | +0.112 |
Anne | +0.111 |
Ellen | +0.109 |
Neg logit contributions | |
ishy | -0.184 |
ory | -0.169 |
fiber | -0.166 |
obs | -0.164 |
ashed | -0.164 |
Token | and |
Token ID | 290 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Amanda | +0.037 |
Am | +0.036 |
Sky | +0.035 |
Anne | +0.034 |
Ellen | +0.034 |
Neg logit contributions | |
ishy | -0.045 |
obs | -0.041 |
ory | -0.040 |
ashed | -0.039 |
inters | -0.039 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Amanda | +0.024 |
Am | +0.023 |
Sky | +0.023 |
Anne | +0.023 |
Ellen | +0.022 |
Neg logit contributions | |
ishy | -0.049 |
obs | -0.045 |
ory | -0.044 |
fiber | -0.044 |
inters | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Amanda | +0.043 |
Am | +0.042 |
Sky | +0.041 |
Anne | +0.040 |
Ellen | +0.040 |
Neg logit contributions | |
ishy | -0.055 |
ory | -0.050 |
obs | -0.049 |
ashed | -0.048 |
inters | -0.048 |
Token | You |
Token ID | 921 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Amanda | +0.045 |
Am | +0.043 |
Sky | +0.043 |
Anne | +0.042 |
Ellen | +0.042 |
Neg logit contributions | |
ishy | -0.078 |
obs | -0.071 |
ory | -0.071 |
fiber | -0.070 |
inters | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
ishy | +0.015 |
ory | +0.014 |
obs | +0.014 |
fiber | +0.014 |
inters | +0.014 |
Neg logit contributions | |
Amanda | -0.006 |
Am | -0.006 |
Sky | -0.006 |
Anne | -0.006 |
Ellen | -0.006 |
Token | Anna |
Token ID | 31160 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
Amanda | +0.012 |
basement | +0.011 |
Sky | +0.011 |
Anne | +0.011 |
Ellen | +0.011 |
Neg logit contributions | |
ishy | -0.014 |
fiber | -0.014 |
ory | -0.014 |
ouses | -0.013 |
uggets | -0.013 |
Token | took |
Token ID | 1718 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Amanda | +0.018 |
Am | +0.018 |
Ellen | +0.018 |
basement | +0.018 |
Sky | +0.017 |
Neg logit contributions | |
ishy | -0.023 |
ory | -0.021 |
ashed | -0.021 |
obs | -0.020 |
fiber | -0.020 |
Token | some |
Token ID | 617 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Amanda | +0.008 |
Am | +0.007 |
basement | +0.007 |
Ellen | +0.007 |
Anne | +0.007 |
Neg logit contributions | |
ishy | -0.021 |
obs | -0.019 |
ory | -0.019 |
ashed | -0.019 |
fiber | -0.019 |
Token | carrots |
Token ID | 34397 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ishy | +0.004 |
obs | +0.004 |
ory | +0.004 |
ashed | +0.003 |
ouses | +0.003 |
Neg logit contributions | |
Amanda | -0.003 |
Sky | -0.003 |
Am | -0.003 |
Anne | -0.003 |
shop | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
Amanda | +0.025 |
Am | +0.023 |
Sky | +0.023 |
Anne | +0.023 |
Ellen | +0.023 |
Neg logit contributions | |
ishy | -0.050 |
obs | -0.046 |
ory | -0.046 |
fiber | -0.045 |
ashed | -0.045 |
Token | put |
Token ID | 1234 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ishy | +0.120 |
obs | +0.109 |
ory | +0.108 |
inters | +0.106 |
fiber | +0.105 |
Neg logit contributions | |
Amanda | -0.086 |
Sky | -0.083 |
Am | -0.083 |
Anne | -0.082 |
Ellen | -0.080 |
Token | them |
Token ID | 606 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Amanda | +0.004 |
Am | +0.003 |
Sky | +0.003 |
Anne | +0.003 |
Ellen | +0.003 |
Neg logit contributions | |
ishy | -0.010 |
obs | -0.009 |
ory | -0.009 |
fiber | -0.009 |
inters | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ishy | +0.010 |
obs | +0.009 |
ory | +0.009 |
fiber | +0.009 |
inters | +0.009 |
Neg logit contributions | |
Amanda | -0.003 |
Am | -0.003 |
Sky | -0.003 |
Anne | -0.003 |
Ellen | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Amanda | +0.009 |
Am | +0.009 |
Ellen | +0.009 |
basement | +0.009 |
Anne | +0.008 |
Neg logit contributions | |
ishy | -0.021 |
ory | -0.020 |
obs | -0.020 |
uggets | -0.020 |
fiber | -0.019 |
Token | plate |
Token ID | 7480 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
ishy | +0.094 |
obs | +0.084 |
ashed | +0.084 |
ory | +0.083 |
inters | +0.082 |
Neg logit contributions | |
Sky | -0.069 |
Amanda | -0.069 |
Anne | -0.067 |
Am | -0.067 |
basement | -0.065 |
Token | wanted |
Token ID | 2227 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
Amanda | +0.016 |
Sky | +0.016 |
Anne | +0.016 |
Am | +0.016 |
Elizabeth | +0.016 |
Neg logit contributions | |
ishy | -0.017 |
ory | -0.017 |
ashed | -0.016 |
inters | -0.015 |
obs | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ishy | +0.019 |
uggets | +0.019 |
obs | +0.019 |
ory | +0.018 |
fiber | +0.018 |
Neg logit contributions | |
Amanda | -0.020 |
Am | -0.020 |
Ellen | -0.019 |
Anne | -0.019 |
K | -0.019 |
Token | go |
Token ID | 467 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Am | +0.003 |
Amanda | +0.003 |
Ellen | +0.003 |
Anne | +0.003 |
Sky | +0.003 |
Neg logit contributions | |
ishy | -0.003 |
fiber | -0.003 |
ory | -0.003 |
preferences | -0.003 |
ashes | -0.003 |
Token | exploring |
Token ID | 13504 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Amanda | +0.059 |
Am | +0.059 |
Anne | +0.057 |
Ellen | +0.055 |
Sky | +0.055 |
Neg logit contributions | |
ishy | -0.087 |
ory | -0.081 |
obs | -0.079 |
ashed | -0.078 |
inters | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Am | +0.011 |
Amanda | +0.011 |
Ellen | +0.010 |
Anne | +0.010 |
Elizabeth | +0.010 |
Neg logit contributions | |
ishy | -0.018 |
ory | -0.016 |
obs | -0.016 |
uggets | -0.016 |
inters | -0.015 |
Token | |
Token ID | 220 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
ishy | +0.009 |
obs | +0.009 |
ashed | +0.009 |
ory | +0.009 |
inters | +0.009 |
Neg logit contributions | |
Am | -0.008 |
Amanda | -0.008 |
basement | -0.008 |
Sky | -0.008 |
never | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
ishy | +0.182 |
obs | +0.168 |
ory | +0.167 |
inters | +0.165 |
fiber | +0.164 |
Neg logit contributions | |
Amanda | -0.076 |
Am | -0.073 |
Sky | -0.071 |
Anne | -0.071 |
Ellen | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ishy | +0.010 |
ory | +0.010 |
uggets | +0.009 |
obs | +0.009 |
ouses | +0.009 |
Neg logit contributions | |
basement | -0.008 |
Sky | -0.008 |
helicopter | -0.008 |
Amanda | -0.008 |
loft | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
Sky | +0.008 |
Amanda | +0.008 |
basement | +0.008 |
Anne | +0.008 |
Ellen | +0.007 |
Neg logit contributions | |
ishy | -0.014 |
abs | -0.014 |
ashed | -0.014 |
fiber | -0.013 |
ory | -0.013 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Sky | +0.013 |
Amanda | +0.013 |
shop | +0.013 |
also | +0.013 |
Am | +0.013 |
Neg logit contributions | |
ishy | -0.035 |
obs | -0.033 |
inters | -0.032 |
ashed | -0.032 |
ouses | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
basement | +0.042 |
Amanda | +0.041 |
Sky | +0.041 |
Am | +0.040 |
Ellen | +0.040 |
Neg logit contributions | |
ishy | -0.044 |
ashed | -0.043 |
ory | -0.043 |
obs | -0.039 |
inters | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Am | +0.008 |
Amanda | +0.008 |
Sky | +0.008 |
basement | +0.007 |
K | +0.007 |
Neg logit contributions | |
ishy | -0.016 |
obs | -0.015 |
fiber | -0.015 |
ory | -0.015 |
inters | -0.015 |
Token | letter |
Token ID | 3850 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Amanda | +0.005 |
Am | +0.005 |
Sky | +0.005 |
Anne | +0.005 |
Ellen | +0.005 |
Neg logit contributions | |
ishy | -0.009 |
obs | -0.009 |
ory | -0.008 |
fiber | -0.008 |
inters | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
Am | +0.008 |
Amanda | +0.008 |
basement | +0.008 |
Sky | +0.008 |
Ellen | +0.008 |
Neg logit contributions | |
ishy | -0.014 |
obs | -0.014 |
itted | -0.013 |
ory | -0.013 |
ouses | -0.013 |
Token | clutching |
Token ID | 48281 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ishy | +0.021 |
obs | +0.020 |
ory | +0.019 |
itted | +0.019 |
ashed | +0.019 |
Neg logit contributions | |
Amanda | -0.014 |
basement | -0.014 |
Sky | -0.014 |
Am | -0.014 |
Ellen | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
ishy | +0.016 |
obs | +0.014 |
ory | +0.014 |
fiber | +0.014 |
inters | +0.014 |
Neg logit contributions | |
Amanda | -0.006 |
Am | -0.005 |
Sky | -0.005 |
Anne | -0.005 |
basement | -0.005 |
Token | tight |
Token ID | 5381 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
ishy | +0.021 |
obs | +0.019 |
ory | +0.019 |
ashed | +0.018 |
inters | +0.018 |
Neg logit contributions | |
Amanda | -0.013 |
Am | -0.013 |
Sky | -0.013 |
basement | -0.013 |
Anne | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ishy | +0.130 |
obs | +0.118 |
ory | +0.118 |
fiber | +0.115 |
inters | +0.115 |
Neg logit contributions | |
Amanda | -0.077 |
Am | -0.074 |
Sky | -0.073 |
Anne | -0.073 |
Ellen | -0.071 |
Token | her |
Token ID | 607 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
Amanda | +0.017 |
Sky | +0.017 |
Am | +0.016 |
basement | +0.016 |
Anne | +0.016 |
Neg logit contributions | |
ishy | -0.036 |
obs | -0.033 |
ory | -0.033 |
fiber | -0.033 |
uggets | -0.033 |
Token | hands |
Token ID | 2832 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ishy | +0.095 |
ashed | +0.087 |
ory | +0.087 |
inters | +0.084 |
obs | +0.083 |
Neg logit contributions | |
Amanda | -0.088 |
Anne | -0.087 |
Am | -0.086 |
� | -0.085 |
Sky | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
ishy | +0.065 |
obs | +0.059 |
ory | +0.059 |
ashed | +0.057 |
inters | +0.057 |
Neg logit contributions | |
Amanda | -0.045 |
Am | -0.044 |
Sky | -0.044 |
Anne | -0.043 |
Ellen | -0.042 |
Token | She |
Token ID | 1375 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
ishy | +0.017 |
obs | +0.016 |
ory | +0.015 |
itted | +0.015 |
inters | +0.015 |
Neg logit contributions | |
Amanda | -0.009 |
Am | -0.009 |
basement | -0.009 |
Sky | -0.009 |
Anne | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
Amanda | +0.026 |
Am | +0.025 |
Sky | +0.025 |
Anne | +0.024 |
basement | +0.024 |
Neg logit contributions | |
ishy | -0.029 |
obs | -0.026 |
ory | -0.026 |
fiber | -0.025 |
ashed | -0.025 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ishy | +0.024 |
ory | +0.022 |
obs | +0.022 |
inters | +0.021 |
fiber | +0.021 |
Neg logit contributions | |
Amanda | -0.014 |
Am | -0.014 |
Anne | -0.014 |
Sky | -0.013 |
Ellen | -0.013 |
Token | I |
Token ID | 314 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
Amanda | +0.008 |
basement | +0.008 |
Am | +0.008 |
Sky | +0.007 |
Ellen | +0.007 |
Neg logit contributions | |
ishy | -0.011 |
ory | -0.011 |
ouses | -0.010 |
obs | -0.010 |
fiber | -0.010 |
Token | go |
Token ID | 467 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ishy | +0.116 |
obs | +0.107 |
fiber | +0.105 |
inters | +0.105 |
ory | +0.104 |
Neg logit contributions | |
Amanda | -0.053 |
Am | -0.050 |
� | -0.050 |
Sky | -0.049 |
never | -0.048 |
Token | ." |
Token ID | 526 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Amanda | +0.055 |
Am | +0.054 |
Anne | +0.053 |
Sky | +0.053 |
Elizabeth | +0.053 |
Neg logit contributions | |
ishy | -0.075 |
ory | -0.069 |
obs | -0.069 |
inters | -0.067 |
ouses | -0.066 |
Token | |
Token ID | 220 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ishy | +0.025 |
obs | +0.023 |
ory | +0.023 |
fiber | +0.023 |
inters | +0.023 |
Neg logit contributions | |
Amanda | -0.009 |
Sky | -0.008 |
Am | -0.008 |
Anne | -0.008 |
Ellen | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ishy | +0.128 |
obs | +0.119 |
ory | +0.118 |
inters | +0.116 |
fiber | +0.115 |
Neg logit contributions | |
Amanda | -0.062 |
Am | -0.060 |
basement | -0.058 |
Anne | -0.058 |
Sky | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
ishy | +0.007 |
ory | +0.007 |
obs | +0.007 |
fiber | +0.007 |
ouses | +0.007 |
Neg logit contributions | |
basement | -0.004 |
Amanda | -0.004 |
Ellen | -0.004 |
Anne | -0.004 |
Am | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Amanda | +0.013 |
basement | +0.013 |
Anne | +0.012 |
Ellen | +0.012 |
Sky | +0.011 |
Neg logit contributions | |
fiber | -0.023 |
ory | -0.022 |
ishy | -0.022 |
ouses | -0.022 |
obs | -0.022 |
Token | shell |
Token ID | 7582 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
also | +0.034 |
shop | +0.033 |
� | +0.031 |
never | +0.030 |
Am | +0.029 |
Neg logit contributions | |
ishy | -0.060 |
inters | -0.059 |
obs | -0.058 |
uggets | -0.057 |
uns | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Amanda | +0.058 |
basement | +0.056 |
Ellen | +0.056 |
Am | +0.056 |
Anne | +0.054 |
Neg logit contributions | |
ishy | -0.077 |
ashed | -0.071 |
ory | -0.070 |
obs | -0.069 |
fiber | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
ishy | +0.033 |
obs | +0.031 |
inters | +0.030 |
fiber | +0.030 |
uggets | +0.029 |
Neg logit contributions | |
Amanda | -0.017 |
Am | -0.017 |
Ellen | -0.017 |
Anne | -0.017 |
Sky | -0.016 |
Token | branch |
Token ID | 8478 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
ishy | +0.012 |
ory | +0.011 |
obs | +0.011 |
inters | +0.011 |
fiber | +0.010 |
Neg logit contributions | |
Amanda | -0.007 |
Anne | -0.006 |
Ellen | -0.006 |
Am | -0.006 |
Sky | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ishy | +0.001 |
obs | +0.001 |
inters | +0.001 |
ashed | +0.001 |
ory | +0.001 |
Neg logit contributions | |
Amanda | -0.001 |
Am | -0.001 |
Ellen | -0.001 |
Anne | -0.001 |
Sky | -0.001 |
Token | ripped |
Token ID | 19551 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ishy | +0.101 |
obs | +0.092 |
ory | +0.091 |
ashed | +0.090 |
fiber | +0.090 |
Neg logit contributions | |
Amanda | -0.060 |
Am | -0.058 |
Sky | -0.057 |
Anne | -0.057 |
Ellen | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ishy | +0.043 |
obs | +0.039 |
ory | +0.039 |
fiber | +0.038 |
inters | +0.038 |
Neg logit contributions | |
Amanda | -0.018 |
Am | -0.017 |
Sky | -0.017 |
Anne | -0.017 |
Ellen | -0.016 |
Token | |
Token ID | 220 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
ishy | +0.039 |
obs | +0.035 |
ory | +0.035 |
fiber | +0.035 |
inters | +0.035 |
Neg logit contributions | |
Amanda | -0.014 |
Sky | -0.013 |
Anne | -0.013 |
Am | -0.013 |
Ellen | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ishy | +0.225 |
ory | +0.208 |
obs | +0.206 |
fiber | +0.205 |
ashed | +0.202 |
Neg logit contributions | |
Amanda | -0.068 |
Sky | -0.063 |
Anne | -0.063 |
Am | -0.062 |
Ellen | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
ishy | +0.039 |
ory | +0.036 |
obs | +0.036 |
ashed | +0.036 |
inters | +0.035 |
Neg logit contributions | |
Amanda | -0.020 |
Am | -0.020 |
Sky | -0.020 |
basement | -0.020 |
Anne | -0.019 |
Token | L |
Token ID | 43 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
Amanda | +0.001 |
Sky | +0.001 |
Am | +0.001 |
Anne | +0.001 |
basement | +0.001 |
Neg logit contributions | |
ishy | -0.002 |
ashed | -0.002 |
ory | -0.002 |
obs | -0.002 |
inters | -0.002 |
Token | ily |
Token ID | 813 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ishy | +0.018 |
obs | +0.017 |
fiber | +0.017 |
inters | +0.017 |
ory | +0.016 |
Neg logit contributions | |
Amanda | -0.013 |
basement | -0.013 |
Anne | -0.013 |
also | -0.013 |
Am | -0.013 |
Token | 's |
Token ID | 338 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Amanda | +0.025 |
Sky | +0.024 |
Am | +0.024 |
basement | +0.024 |
Ellen | +0.024 |
Neg logit contributions | |
ishy | -0.036 |
ashed | -0.034 |
obs | -0.032 |
ory | -0.032 |
inters | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ishy | +0.070 |
ory | +0.065 |
fiber | +0.064 |
obs | +0.063 |
ashed | +0.063 |
Neg logit contributions | |
Sky | -0.034 |
also | -0.033 |
Amanda | -0.033 |
� | -0.033 |
never | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Amanda | +0.005 |
Sky | +0.004 |
Anne | +0.004 |
Am | +0.004 |
George | +0.004 |
Neg logit contributions | |
ishy | -0.010 |
ory | -0.009 |
ashed | -0.009 |
obs | -0.009 |
uc | -0.009 |
Token | wishes |
Token ID | 12802 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
also | +0.014 |
never | +0.014 |
Amanda | +0.014 |
Sky | +0.014 |
� | +0.014 |
Neg logit contributions | |
ishy | -0.022 |
uggets | -0.021 |
obs | -0.021 |
ory | -0.021 |
ouses | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
ishy | +0.018 |
obs | +0.016 |
ory | +0.016 |
fiber | +0.016 |
inters | +0.016 |
Neg logit contributions | |
Amanda | -0.012 |
Am | -0.011 |
Sky | -0.011 |
Anne | -0.011 |
Ellen | -0.011 |
Token | did |
Token ID | 750 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
ishy | +0.028 |
obs | +0.026 |
ory | +0.026 |
uggets | +0.026 |
fiber | +0.025 |
Neg logit contributions | |
never | -0.013 |
also | -0.013 |
Sky | -0.012 |
Amanda | -0.012 |
� | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Amanda | +0.000 |
Sky | +0.000 |
never | +0.000 |
Am | +0.000 |
Anne | +0.000 |
Neg logit contributions | |
ishy | -0.000 |
obs | -0.000 |
ory | -0.000 |
inters | -0.000 |
ashed | -0.000 |
Token | bite |
Token ID | 13197 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
ishy | +0.053 |
obs | +0.049 |
ory | +0.048 |
ashed | +0.047 |
fiber | +0.047 |
Neg logit contributions | |
Amanda | -0.024 |
Sky | -0.023 |
never | -0.023 |
Am | -0.023 |
Anne | -0.023 |
Token | Mia |
Token ID | 32189 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Sky | +0.008 |
Amanda | +0.007 |
Anne | +0.007 |
Am | +0.007 |
George | +0.007 |
Neg logit contributions | |
ishy | -0.021 |
ashed | -0.020 |
obs | -0.020 |
itted | -0.020 |
ouses | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ishy | +0.014 |
ory | +0.013 |
obs | +0.013 |
fiber | +0.013 |
ashed | +0.013 |
Neg logit contributions | |
Amanda | -0.009 |
Am | -0.009 |
Sky | -0.009 |
Anne | -0.009 |
Ellen | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
Amanda | +0.005 |
Sky | +0.005 |
Anne | +0.005 |
Am | +0.004 |
George | +0.004 |
Neg logit contributions | |
ishy | -0.010 |
ory | -0.009 |
ashed | -0.009 |
obs | -0.009 |
uc | -0.009 |
Token | wishes |
Token ID | 12802 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Amanda | +0.016 |
Sky | +0.016 |
also | +0.016 |
never | +0.016 |
Am | +0.016 |
Neg logit contributions | |
ishy | -0.026 |
obs | -0.024 |
uggets | -0.024 |
ory | -0.024 |
inters | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ishy | +0.014 |
ory | +0.013 |
ashed | +0.012 |
fiber | +0.012 |
obs | +0.012 |
Neg logit contributions | |
Amanda | -0.008 |
Am | -0.008 |
basement | -0.007 |
Sky | -0.007 |
loft | -0.007 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ishy | +0.057 |
obs | +0.054 |
inters | +0.053 |
ory | +0.053 |
uns | +0.052 |
Neg logit contributions | |
Amanda | -0.022 |
Anne | -0.021 |
Sky | -0.021 |
basement | -0.021 |
Am | -0.021 |
Token | told |
Token ID | 1297 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
Amanda | +0.025 |
Sky | +0.025 |
Am | +0.024 |
basement | +0.024 |
Anne | +0.023 |
Neg logit contributions | |
ishy | -0.030 |
ory | -0.028 |
ashed | -0.027 |
obs | -0.027 |
fiber | -0.026 |
Token | her |
Token ID | 607 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ishy | +0.022 |
fiber | +0.020 |
ory | +0.020 |
inters | +0.020 |
preferences | +0.019 |
Neg logit contributions | |
Am | -0.014 |
Amanda | -0.013 |
basement | -0.012 |
loft | -0.012 |
K | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ishy | +0.064 |
obs | +0.059 |
ory | +0.059 |
fiber | +0.058 |
ashed | +0.058 |
Neg logit contributions | |
Amanda | -0.021 |
Am | -0.020 |
Sky | -0.020 |
Anne | -0.019 |
Ellen | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
ishy | +0.078 |
obs | +0.069 |
ory | +0.069 |
ashed | +0.068 |
fiber | +0.068 |
Neg logit contributions | |
never | -0.028 |
Amanda | -0.027 |
Anne | -0.026 |
Sky | -0.026 |
Am | -0.025 |
Token | worry |
Token ID | 5490 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ishy | +0.032 |
obs | +0.030 |
ashed | +0.030 |
inters | +0.029 |
ouses | +0.029 |
Neg logit contributions | |
Amanda | -0.015 |
never | -0.014 |
also | -0.014 |
� | -0.014 |
Am | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
ishy | +0.057 |
obs | +0.052 |
ory | +0.051 |
fiber | +0.051 |
inters | +0.050 |
Neg logit contributions | |
Amanda | -0.037 |
Anne | -0.035 |
Sky | -0.035 |
Am | -0.035 |
Ellen | -0.034 |
Token | They |
Token ID | 1119 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
Am | +0.002 |
Amanda | +0.002 |
basement | +0.002 |
Ellen | +0.002 |
Sky | +0.001 |
Neg logit contributions | |
ishy | -0.003 |
ashed | -0.003 |
obs | -0.003 |
itted | -0.003 |
inters | -0.003 |
Token | set |
Token ID | 900 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Amanda | +0.019 |
Sky | +0.018 |
Am | +0.018 |
Anne | +0.018 |
basement | +0.017 |
Neg logit contributions | |
ishy | -0.026 |
ory | -0.024 |
ashed | -0.024 |
obs | -0.024 |
inters | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Am | +0.045 |
basement | +0.043 |
Amanda | +0.041 |
K | +0.040 |
outskirts | +0.040 |
Neg logit contributions | |
ishy | -0.097 |
obs | -0.094 |
uggets | -0.091 |
ashes | -0.091 |
ashed | -0.091 |
Token | world |
Token ID | 995 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Amanda | +0.007 |
Am | +0.007 |
Sky | +0.007 |
Anne | +0.007 |
Ellen | +0.007 |
Neg logit contributions | |
ishy | -0.012 |
obs | -0.011 |
ory | -0.011 |
ashed | -0.011 |
inters | -0.011 |
Token | around |
Token ID | 1088 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ishy | +0.051 |
obs | +0.047 |
ory | +0.045 |
ashed | +0.044 |
ouses | +0.044 |
Neg logit contributions | |
Amanda | -0.036 |
Am | -0.036 |
basement | -0.034 |
Sky | -0.033 |
Ellen | -0.033 |
Token | him |
Token ID | 683 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ishy | +0.011 |
obs | +0.010 |
ory | +0.010 |
fiber | +0.010 |
inters | +0.010 |
Neg logit contributions | |
Amanda | -0.006 |
Am | -0.005 |
Sky | -0.005 |
Anne | -0.005 |
Ellen | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ishy | +0.088 |
obs | +0.080 |
ory | +0.080 |
fiber | +0.079 |
ashed | +0.079 |
Neg logit contributions | |
Amanda | -0.052 |
Sky | -0.050 |
Anne | -0.049 |
Am | -0.049 |
� | -0.048 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Amanda | +0.006 |
Am | +0.006 |
Sky | +0.006 |
Anne | +0.005 |
Ellen | +0.005 |
Neg logit contributions | |
ishy | -0.015 |
obs | -0.013 |
ory | -0.013 |
fiber | -0.013 |
inters | -0.013 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ishy | +0.077 |
ory | +0.071 |
obs | +0.071 |
ashed | +0.069 |
inters | +0.069 |
Neg logit contributions | |
Amanda | -0.037 |
Am | -0.035 |
Sky | -0.034 |
Ellen | -0.034 |
Anne | -0.034 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ishy | +0.047 |
obs | +0.042 |
fiber | +0.040 |
ory | +0.039 |
inters | +0.039 |
Neg logit contributions | |
Amanda | -0.066 |
Anne | -0.064 |
Sky | -0.064 |
Am | -0.063 |
Ellen | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ishy | +0.095 |
obs | +0.089 |
ory | +0.089 |
ashed | +0.087 |
inters | +0.087 |
Neg logit contributions | |
Sky | -0.013 |
Amanda | -0.013 |
Anne | -0.013 |
never | -0.013 |
also | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ishy | +0.016 |
obs | +0.014 |
ory | +0.014 |
fiber | +0.014 |
inters | +0.014 |
Neg logit contributions | |
Amanda | -0.014 |
Am | -0.014 |
Sky | -0.013 |
Anne | -0.013 |
Ellen | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
ishy | +0.058 |
ory | +0.055 |
ashed | +0.053 |
uggets | +0.051 |
fiber | +0.051 |
Neg logit contributions | |
Am | -0.029 |
basement | -0.027 |
Amanda | -0.026 |
loft | -0.026 |
outskirts | -0.024 |
Token | there |
Token ID | 612 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Am | +0.009 |
Amanda | +0.009 |
basement | +0.008 |
Ellen | +0.008 |
Elizabeth | +0.008 |
Neg logit contributions | |
ishy | -0.019 |
ashed | -0.017 |
ory | -0.016 |
inters | -0.016 |
uggets | -0.016 |
Token | love |
Token ID | 1842 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ishy | +0.010 |
obs | +0.010 |
uggets | +0.009 |
ouses | +0.009 |
ory | +0.009 |
Neg logit contributions | |
never | -0.008 |
� | -0.008 |
also | -0.008 |
Amanda | -0.007 |
hurry | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Sky | +0.016 |
Amanda | +0.016 |
Anne | +0.015 |
never | +0.015 |
Am | +0.015 |
Neg logit contributions | |
ishy | -0.050 |
obs | -0.045 |
ashed | -0.045 |
ory | -0.045 |
inters | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
ishy | +0.055 |
ory | +0.051 |
fiber | +0.050 |
obs | +0.050 |
ashed | +0.049 |
Neg logit contributions | |
Amanda | -0.029 |
Am | -0.027 |
Ellen | -0.027 |
Sky | -0.027 |
Anne | -0.026 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Amanda | +0.082 |
Am | +0.079 |
Sky | +0.078 |
Anne | +0.078 |
Ellen | +0.077 |
Neg logit contributions | |
ishy | -0.130 |
ory | -0.118 |
obs | -0.118 |
fiber | -0.116 |
ashed | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Amanda | +0.038 |
Am | +0.037 |
Sky | +0.036 |
Anne | +0.036 |
Ellen | +0.036 |
Neg logit contributions | |
ishy | -0.057 |
obs | -0.051 |
ory | -0.051 |
fiber | -0.050 |
inters | -0.050 |
Token | We |
Token ID | 775 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
Amanda | +0.039 |
Sky | +0.038 |
Anne | +0.037 |
Am | +0.037 |
� | +0.037 |
Neg logit contributions | |
ishy | -0.074 |
ory | -0.069 |
obs | -0.068 |
ashed | -0.067 |
inters | -0.067 |
Token | will |
Token ID | 481 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ishy | +0.021 |
obs | +0.020 |
uggets | +0.020 |
ouses | +0.019 |
ory | +0.019 |
Neg logit contributions | |
never | -0.018 |
also | -0.018 |
� | -0.018 |
hurry | -0.016 |
Amanda | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Amanda | +0.037 |
Sky | +0.036 |
Am | +0.035 |
Anne | +0.035 |
Ellen | +0.035 |
Neg logit contributions | |
ishy | -0.054 |
fiber | -0.052 |
ory | -0.049 |
preferences | -0.048 |
inters | -0.048 |
Token | play |
Token ID | 711 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Amanda | +0.000 |
Am | +0.000 |
Sky | +0.000 |
Anne | +0.000 |
Ellen | +0.000 |
Neg logit contributions | |
ishy | -0.001 |
ory | -0.001 |
fiber | -0.001 |
inters | -0.001 |
obs | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Amanda | +0.046 |
Am | +0.043 |
Ellen | +0.042 |
Anne | +0.042 |
Sky | +0.040 |
Neg logit contributions | |
ishy | -0.102 |
obs | -0.093 |
ory | -0.093 |
fiber | -0.091 |
uggets | -0.091 |
Token | jam |
Token ID | 16853 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Amanda | +0.051 |
Sky | +0.051 |
Am | +0.050 |
Anne | +0.050 |
basement | +0.049 |
Neg logit contributions | |
ishy | -0.074 |
obs | -0.067 |
ory | -0.067 |
ashed | -0.067 |
itted | -0.066 |
Token | oc |
Token ID | 420 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Amanda | +0.063 |
Am | +0.061 |
Anne | +0.061 |
Ellen | +0.061 |
Sky | +0.061 |
Neg logit contributions | |
ishy | -0.059 |
obs | -0.052 |
ory | -0.052 |
ashed | -0.051 |
fiber | -0.050 |
Token | eros |
Token ID | 27498 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ishy | +0.018 |
obs | +0.016 |
ory | +0.016 |
inters | +0.016 |
ashed | +0.016 |
Neg logit contributions | |
Amanda | -0.013 |
Sky | -0.012 |
Am | -0.012 |
Anne | -0.012 |
Ellen | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Amanda | +0.040 |
basement | +0.040 |
Am | +0.039 |
Ellen | +0.038 |
Anne | +0.037 |
Neg logit contributions | |
ishy | -0.050 |
ashed | -0.048 |
ory | -0.045 |
ushed | -0.044 |
uc | -0.043 |
Token | very |
Token ID | 845 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
Amanda | +0.036 |
basement | +0.035 |
Am | +0.035 |
Anne | +0.034 |
Ellen | +0.033 |
Neg logit contributions | |
ishy | -0.049 |
itted | -0.045 |
ashed | -0.044 |
inters | -0.044 |
uggets | -0.042 |
Token | slow |
Token ID | 3105 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Amanda | +0.018 |
Am | +0.017 |
Sky | +0.017 |
Anne | +0.017 |
Ellen | +0.016 |
Neg logit contributions | |
ishy | -0.027 |
obs | -0.025 |
ory | -0.025 |
fiber | -0.024 |
inters | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ishy | +0.072 |
obs | +0.066 |
ory | +0.066 |
inters | +0.065 |
fiber | +0.065 |
Neg logit contributions | |
Amanda | -0.035 |
Am | -0.034 |
Sky | -0.033 |
Anne | -0.033 |
Ellen | -0.032 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ishy | +0.046 |
ory | +0.040 |
ashed | +0.040 |
inters | +0.040 |
obs | +0.040 |
Neg logit contributions | |
Amanda | -0.038 |
Am | -0.037 |
Anne | -0.036 |
Sky | -0.035 |
basement | -0.035 |
Token | 't |
Token ID | 470 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ishy | +0.034 |
inters | +0.032 |
obs | +0.032 |
itted | +0.031 |
fiber | +0.031 |
Neg logit contributions | |
Amanda | -0.015 |
basement | -0.014 |
Anne | -0.014 |
Am | -0.013 |
Ellen | -0.013 |
Token | move |
Token ID | 1445 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ishy | +0.034 |
obs | +0.032 |
ory | +0.031 |
uggets | +0.031 |
fiber | +0.030 |
Neg logit contributions | |
Amanda | -0.023 |
Sky | -0.023 |
Am | -0.022 |
never | -0.022 |
Ellen | -0.022 |
Token | out |
Token ID | 503 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
ishy | +0.005 |
obs | +0.005 |
ory | +0.005 |
inters | +0.005 |
ashed | +0.005 |
Neg logit contributions | |
Amanda | -0.003 |
Am | -0.003 |
Anne | -0.003 |
Sky | -0.003 |
basement | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Amanda | +0.001 |
Am | +0.001 |
basement | +0.001 |
Ellen | +0.001 |
Elizabeth | +0.001 |
Neg logit contributions | |
ishy | -0.001 |
obs | -0.001 |
inters | -0.001 |
ashed | -0.001 |
iness | -0.001 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Amanda | +0.006 |
Am | +0.005 |
Sky | +0.005 |
Ellen | +0.005 |
basement | +0.005 |
Neg logit contributions | |
ishy | -0.007 |
obs | -0.006 |
ory | -0.006 |
ashed | -0.006 |
inters | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Am | +0.021 |
Amanda | +0.020 |
basement | +0.019 |
loft | +0.019 |
Anne | +0.018 |
Neg logit contributions | |
ishy | -0.027 |
ops | -0.025 |
inters | -0.024 |
powers | -0.024 |
iness | -0.024 |
Token | get |
Token ID | 651 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ishy | +0.007 |
ory | +0.007 |
inters | +0.007 |
obs | +0.007 |
fiber | +0.006 |
Neg logit contributions | |
Amanda | -0.005 |
Am | -0.005 |
Elizabeth | -0.005 |
Sky | -0.005 |
Anne | -0.005 |
Token | out |
Token ID | 503 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Amanda | +0.033 |
Am | +0.031 |
Sky | +0.031 |
Anne | +0.031 |
basement | +0.030 |
Neg logit contributions | |
ishy | -0.068 |
ory | -0.062 |
obs | -0.062 |
inters | -0.061 |
ashed | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Amanda | +0.027 |
Am | +0.026 |
Sky | +0.026 |
Anne | +0.025 |
Ellen | +0.025 |
Neg logit contributions | |
ishy | -0.044 |
obs | -0.040 |
ory | -0.039 |
inters | -0.039 |
ashed | -0.039 |
Token | Wendy |
Token ID | 28314 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Am | +0.007 |
Amanda | +0.007 |
basement | +0.007 |
Anne | +0.007 |
Sky | +0.007 |
Neg logit contributions | |
ishy | -0.013 |
obs | -0.012 |
ory | -0.012 |
ashed | -0.012 |
itted | -0.012 |
Token | understood |
Token ID | 7247 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
basement | +0.032 |
Sky | +0.030 |
Amanda | +0.030 |
Ellen | +0.029 |
Am | +0.029 |
Neg logit contributions | |
ishy | -0.038 |
ashed | -0.036 |
obs | -0.036 |
ory | -0.036 |
ushed | -0.035 |
Token | her |
Token ID | 607 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ishy | +0.007 |
ory | +0.007 |
fiber | +0.007 |
obs | +0.007 |
preferences | +0.006 |
Neg logit contributions | |
Sky | -0.004 |
Amanda | -0.004 |
Am | -0.004 |
basement | -0.004 |
Anne | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ishy | +0.049 |
obs | +0.044 |
ory | +0.044 |
fiber | +0.043 |
inters | +0.043 |
Neg logit contributions | |
Amanda | -0.031 |
Am | -0.029 |
Sky | -0.029 |
Anne | -0.029 |
Ellen | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ishy | +0.014 |
ory | +0.013 |
obs | +0.013 |
ashed | +0.012 |
inters | +0.012 |
Neg logit contributions | |
Amanda | -0.005 |
basement | -0.005 |
Sky | -0.005 |
Am | -0.005 |
Anne | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ishy | +0.042 |
ashed | +0.041 |
ory | +0.040 |
obs | +0.040 |
ushed | +0.039 |
Neg logit contributions | |
Am | -0.042 |
Amanda | -0.040 |
Sky | -0.040 |
basement | -0.040 |
cinema | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
ishy | +0.004 |
obs | +0.004 |
ory | +0.004 |
inters | +0.004 |
ashed | +0.004 |
Neg logit contributions | |
Amanda | -0.003 |
Am | -0.003 |
Sky | -0.002 |
Anne | -0.002 |
Ellen | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Ellen | +0.011 |
Amanda | +0.011 |
Sky | +0.011 |
Elizabeth | +0.010 |
Am | +0.010 |
Neg logit contributions | |
ishy | -0.028 |
ory | -0.025 |
fiber | -0.025 |
obs | -0.025 |
uggets | -0.025 |
Token | ocean |
Token ID | 9151 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Amanda | +0.006 |
Ellen | +0.005 |
Sky | +0.005 |
Anne | +0.005 |
Elizabeth | +0.005 |
Neg logit contributions | |
ishy | -0.007 |
ory | -0.006 |
obs | -0.006 |
inters | -0.006 |
ashed | -0.006 |
Token | ." |
Token ID | 526 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Amanda | +0.012 |
Am | +0.012 |
Ellen | +0.012 |
Sky | +0.012 |
Anne | +0.012 |
Neg logit contributions | |
ishy | -0.014 |
obs | -0.013 |
ory | -0.013 |
inters | -0.012 |
ashed | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ishy | +0.021 |
ory | +0.020 |
obs | +0.019 |
uggets | +0.019 |
fiber | +0.019 |
Neg logit contributions | |
Amanda | -0.011 |
basement | -0.011 |
Am | -0.011 |
Sky | -0.010 |
Ellen | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
ishy | +0.014 |
ory | +0.013 |
obs | +0.013 |
uggets | +0.013 |
fiber | +0.013 |
Neg logit contributions | |
basement | -0.008 |
Amanda | -0.008 |
Sky | -0.008 |
Ellen | -0.008 |
loft | -0.008 |
Token | N |
Token ID | 45 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Amanda | +0.006 |
basement | +0.006 |
Sky | +0.006 |
Anne | +0.006 |
arriving | +0.006 |
Neg logit contributions | |
ishy | -0.009 |
ory | -0.009 |
fiber | -0.009 |
uggets | -0.008 |
ouses | -0.008 |
Token | emo |
Token ID | 41903 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
ishy | +0.083 |
fiber | +0.077 |
inters | +0.074 |
ashed | +0.069 |
obs | +0.069 |
Neg logit contributions | |
Am | -0.070 |
Amanda | -0.069 |
also | -0.067 |
Anne | -0.066 |
never | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
basement | +0.019 |
Amanda | +0.019 |
Ellen | +0.019 |
Am | +0.019 |
Sky | +0.018 |
Neg logit contributions | |
ishy | -0.025 |
ory | -0.024 |
ashed | -0.023 |
obs | -0.022 |
fiber | -0.022 |
Token | curious |
Token ID | 11040 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
basement | +0.015 |
Amanda | +0.014 |
loft | +0.014 |
Am | +0.014 |
Ellen | +0.014 |
Neg logit contributions | |
ishy | -0.017 |
itted | -0.015 |
ashed | -0.015 |
uggets | -0.014 |
thirst | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
ishy | +0.112 |
fiber | +0.103 |
inters | +0.103 |
obs | +0.103 |
ory | +0.103 |
Neg logit contributions | |
Amanda | -0.041 |
Anne | -0.040 |
� | -0.038 |
Sky | -0.038 |
George | -0.038 |
Token | spoon |
Token ID | 24556 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Amanda | +0.003 |
Am | +0.003 |
Sky | +0.003 |
Anne | +0.003 |
Ellen | +0.003 |
Neg logit contributions | |
ishy | -0.004 |
obs | -0.003 |
ory | -0.003 |
inters | -0.003 |
ashed | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
ishy | +0.019 |
fiber | +0.017 |
ory | +0.017 |
inters | +0.017 |
obs | +0.017 |
Neg logit contributions | |
Amanda | -0.010 |
Am | -0.009 |
� | -0.009 |
Sky | -0.009 |
Anne | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
ishy | +0.013 |
obs | +0.012 |
ory | +0.012 |
fiber | +0.012 |
ashed | +0.012 |
Neg logit contributions | |
Amanda | -0.007 |
Am | -0.007 |
Sky | -0.007 |
Anne | -0.007 |
Ellen | -0.006 |
Token | took |
Token ID | 1718 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ishy | +0.025 |
ory | +0.023 |
obs | +0.023 |
ashed | +0.023 |
fiber | +0.022 |
Neg logit contributions | |
Amanda | -0.018 |
Ellen | -0.017 |
Am | -0.017 |
Sky | -0.017 |
basement | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Amanda | +0.003 |
Am | +0.003 |
Sky | +0.003 |
Anne | +0.003 |
Ellen | +0.003 |
Neg logit contributions | |
ishy | -0.012 |
obs | -0.011 |
ory | -0.011 |
inters | -0.011 |
fiber | -0.011 |
Token | big |
Token ID | 1263 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Amanda | +0.004 |
Am | +0.004 |
Sky | +0.004 |
Anne | +0.004 |
� | +0.004 |
Neg logit contributions | |
ishy | -0.007 |
obs | -0.007 |
ory | -0.006 |
fiber | -0.006 |
inters | -0.006 |
Token | bite |
Token ID | 13197 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Amanda | +0.023 |
Sky | +0.022 |
Am | +0.022 |
Anne | +0.021 |
Ellen | +0.021 |
Neg logit contributions | |
ishy | -0.036 |
obs | -0.033 |
ory | -0.033 |
inters | -0.032 |
fiber | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
ishy | +0.037 |
obs | +0.034 |
ory | +0.034 |
inters | +0.033 |
fiber | +0.033 |
Neg logit contributions | |
Amanda | -0.018 |
Am | -0.017 |
Sky | -0.017 |
Anne | -0.017 |
Ellen | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ishy | +0.138 |
obs | +0.125 |
ory | +0.124 |
inters | +0.122 |
fiber | +0.122 |
Neg logit contributions | |
Amanda | -0.088 |
Am | -0.084 |
Sky | -0.084 |
Anne | -0.084 |
Ellen | -0.081 |
Token | was |
Token ID | 373 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ishy | +0.044 |
ashed | +0.038 |
obs | +0.038 |
ory | +0.038 |
fiber | +0.038 |
Neg logit contributions | |
Amanda | -0.034 |
Am | -0.033 |
Ellen | -0.033 |
basement | -0.032 |
Sky | -0.032 |
Token | sweet |
Token ID | 6029 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
Amanda | +0.003 |
Sky | +0.003 |
also | +0.003 |
never | +0.003 |
Am | +0.003 |
Neg logit contributions | |
ishy | -0.006 |
obs | -0.006 |
ory | -0.006 |
ouses | -0.006 |
inters | -0.006 |
Token | lion |
Token ID | 18744 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Amanda | +0.016 |
Am | +0.015 |
Sky | +0.015 |
Anne | +0.015 |
basement | +0.015 |
Neg logit contributions | |
ishy | -0.026 |
obs | -0.024 |
ory | -0.024 |
fiber | -0.023 |
ashed | -0.023 |
Token | away |
Token ID | 1497 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Amanda | +0.053 |
Am | +0.050 |
Anne | +0.050 |
Ellen | +0.050 |
Sky | +0.048 |
Neg logit contributions | |
ishy | -0.087 |
obs | -0.079 |
ory | -0.078 |
inters | -0.078 |
ashed | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
ishy | +0.013 |
ory | +0.011 |
obs | +0.011 |
uggets | +0.011 |
inters | +0.011 |
Neg logit contributions | |
Amanda | -0.012 |
Ellen | -0.012 |
Anne | -0.011 |
Elizabeth | -0.011 |
Am | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
Amanda | +0.011 |
Sky | +0.011 |
Am | +0.010 |
Anne | +0.010 |
Ellen | +0.010 |
Neg logit contributions | |
ishy | -0.023 |
ory | -0.021 |
obs | -0.020 |
ashed | -0.020 |
fiber | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Amanda | +0.009 |
Am | +0.009 |
Sky | +0.009 |
Anne | +0.009 |
Ellen | +0.008 |
Neg logit contributions | |
ishy | -0.024 |
obs | -0.022 |
ory | -0.022 |
fiber | -0.022 |
ashed | -0.021 |
Token | Tom |
Token ID | 13787 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
Amanda | +0.041 |
Anne | +0.040 |
Ellen | +0.039 |
Sky | +0.038 |
George | +0.038 |
Neg logit contributions | |
ishy | -0.048 |
fiber | -0.044 |
obs | -0.044 |
ory | -0.043 |
inters | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
Amanda | +0.048 |
Ellen | +0.046 |
Am | +0.045 |
Anne | +0.045 |
basement | +0.044 |
Neg logit contributions | |
ishy | -0.064 |
obs | -0.058 |
ory | -0.058 |
ashed | -0.057 |
fiber | -0.056 |
Token | Jen |
Token ID | 13364 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
ishy | +0.002 |
ashed | +0.002 |
inters | +0.002 |
ory | +0.002 |
ashes | +0.002 |
Neg logit contributions | |
Am | -0.002 |
basement | -0.002 |
Amanda | -0.002 |
Ellen | -0.002 |
Anne | -0.002 |
Token | say |
Token ID | 910 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Amanda | +0.014 |
Am | +0.013 |
Anne | +0.013 |
Ellen | +0.013 |
Sky | +0.013 |
Neg logit contributions | |
ishy | -0.022 |
ory | -0.019 |
obs | -0.019 |
inters | -0.019 |
fiber | -0.019 |
Token | thank |
Token ID | 5875 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
ishy | +0.012 |
fiber | +0.011 |
ashed | +0.011 |
obs | +0.011 |
ory | +0.011 |
Neg logit contributions | |
Amanda | -0.009 |
Am | -0.009 |
basement | -0.009 |
Anne | -0.009 |
Ellen | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Amanda | +0.005 |
Am | +0.005 |
Anne | +0.005 |
Sky | +0.005 |
Ellen | +0.005 |
Neg logit contributions | |
ishy | -0.012 |
ory | -0.011 |
obs | -0.011 |
fiber | -0.011 |
inters | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Amanda | +0.008 |
Sky | +0.008 |
Am | +0.008 |
Anne | +0.008 |
Ellen | +0.007 |
Neg logit contributions | |
ishy | -0.023 |
obs | -0.021 |
ory | -0.021 |
inters | -0.021 |
fiber | -0.021 |
Token | another |
Token ID | 1194 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ishy | +0.053 |
obs | +0.049 |
ory | +0.049 |
fiber | +0.048 |
inters | +0.048 |
Neg logit contributions | |
Amanda | -0.019 |
Am | -0.018 |
Sky | -0.018 |
Anne | -0.018 |
Ellen | -0.017 |
Token | towel |
Token ID | 24808 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
Amanda | +0.027 |
Am | +0.026 |
Sky | +0.026 |
Anne | +0.025 |
Ellen | +0.025 |
Neg logit contributions | |
ishy | -0.035 |
ory | -0.031 |
obs | -0.031 |
fiber | -0.031 |
ashed | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Amanda | +0.015 |
Am | +0.014 |
Sky | +0.014 |
Anne | +0.014 |
Ellen | +0.014 |
Neg logit contributions | |
ishy | -0.030 |
obs | -0.027 |
ory | -0.027 |
fiber | -0.027 |
inters | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
ishy | +0.064 |
ashed | +0.061 |
ory | +0.060 |
fiber | +0.059 |
obs | +0.059 |
Neg logit contributions | |
basement | -0.039 |
Am | -0.039 |
Amanda | -0.038 |
Sky | -0.037 |
Ellen | -0.037 |
Token | little |
Token ID | 1310 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Amanda | +0.011 |
Am | +0.010 |
Sky | +0.010 |
Anne | +0.010 |
Ellen | +0.010 |
Neg logit contributions | |
ishy | -0.018 |
obs | -0.016 |
ory | -0.016 |
fiber | -0.016 |
inters | -0.016 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Amanda | +0.005 |
Anne | +0.005 |
shop | +0.005 |
Ellen | +0.005 |
Sky | +0.004 |
Neg logit contributions | |
ishy | -0.007 |
uggets | -0.007 |
obs | -0.007 |
fiber | -0.007 |
inters | -0.007 |
Token | happily |
Token ID | 18177 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Amanda | +0.037 |
Am | +0.036 |
Sky | +0.035 |
Anne | +0.035 |
Ellen | +0.034 |
Neg logit contributions | |
ishy | -0.058 |
obs | -0.053 |
ory | -0.053 |
fiber | -0.052 |
inters | -0.052 |
Token | accepted |
Token ID | 6292 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ishy | +0.041 |
obs | +0.038 |
ory | +0.037 |
inters | +0.037 |
fiber | +0.037 |
Neg logit contributions | |
Amanda | -0.029 |
Am | -0.028 |
Sky | -0.028 |
Anne | -0.028 |
Ellen | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Amanda | +0.005 |
Am | +0.004 |
Sky | +0.004 |
Anne | +0.004 |
Ellen | +0.004 |
Neg logit contributions | |
ishy | -0.015 |
obs | -0.013 |
ory | -0.013 |
inters | -0.013 |
ashed | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
ishy | +0.010 |
obs | +0.009 |
ory | +0.009 |
fiber | +0.009 |
inters | +0.009 |
Neg logit contributions | |
Amanda | -0.004 |
Am | -0.004 |
Sky | -0.004 |
Anne | -0.004 |
basement | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ory | +0.020 |
fiber | +0.019 |
ishy | +0.019 |
ment | +0.018 |
ouses | +0.018 |
Neg logit contributions | |
basement | -0.014 |
loft | -0.012 |
outskirts | -0.012 |
Am | -0.012 |
cinema | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
basement | +0.019 |
Amanda | +0.018 |
Am | +0.018 |
loft | +0.018 |
Anne | +0.018 |
Neg logit contributions | |
ishy | -0.032 |
ory | -0.031 |
fiber | -0.030 |
uggets | -0.029 |
inters | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ishy | +0.035 |
ory | +0.034 |
uggets | +0.033 |
obs | +0.032 |
fiber | +0.032 |
Neg logit contributions | |
basement | -0.020 |
Am | -0.019 |
Ellen | -0.018 |
Amanda | -0.018 |
outskirts | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
basement | +0.022 |
Amanda | +0.021 |
Am | +0.021 |
Ellen | +0.020 |
Anne | +0.020 |
Neg logit contributions | |
ishy | -0.033 |
obs | -0.031 |
ory | -0.031 |
itted | -0.031 |
ashed | -0.031 |
Token | Hello |
Token ID | 15496 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
Amanda | +0.015 |
Am | +0.014 |
Sky | +0.014 |
Anne | +0.014 |
Ellen | +0.014 |
Neg logit contributions | |
ishy | -0.023 |
obs | -0.021 |
ory | -0.021 |
fiber | -0.021 |
ashed | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
basement | +0.007 |
Am | +0.007 |
never | +0.007 |
Amanda | +0.007 |
Ellen | +0.006 |
Neg logit contributions | |
ory | -0.017 |
ishy | -0.017 |
fiber | -0.016 |
obs | -0.016 |
uggets | -0.016 |
Token | Mr |
Token ID | 1770 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
basement | +0.104 |
outskirts | +0.097 |
Anne | +0.095 |
Am | +0.095 |
loft | +0.095 |
Neg logit contributions | |
ory | -0.139 |
ishy | -0.138 |
fiber | -0.131 |
obs | -0.120 |
ocol | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ishy | +0.084 |
ashed | +0.077 |
inters | +0.075 |
obs | +0.074 |
fiber | +0.074 |
Neg logit contributions | |
Sky | -0.044 |
Amanda | -0.043 |
Am | -0.042 |
Anne | -0.040 |
Elizabeth | -0.039 |
Token | Lee |
Token ID | 5741 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
basement | +0.029 |
Amanda | +0.029 |
Anne | +0.029 |
Ellen | +0.028 |
Am | +0.028 |
Neg logit contributions | |
ishy | -0.051 |
ory | -0.050 |
obs | -0.049 |
uggets | -0.047 |
fiber | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Amanda | +0.027 |
basement | +0.027 |
Am | +0.027 |
Ellen | +0.027 |
Anne | +0.026 |
Neg logit contributions | |
ishy | -0.027 |
ory | -0.025 |
obs | -0.025 |
ouses | -0.023 |
fiber | -0.023 |
Token | I |
Token ID | 314 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
basement | +0.032 |
Am | +0.030 |
never | +0.029 |
Amanda | +0.029 |
outskirts | +0.029 |
Neg logit contributions | |
ishy | -0.043 |
ory | -0.043 |
obs | -0.041 |
uggets | -0.040 |
fiber | -0.040 |
Token | said |
Token ID | 531 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ishy | +0.040 |
ory | +0.040 |
ashed | +0.037 |
obs | +0.036 |
uc | +0.036 |
Neg logit contributions | |
Amanda | -0.049 |
Sky | -0.048 |
Am | -0.048 |
basement | -0.048 |
Anne | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
ishy | +0.058 |
ashed | +0.056 |
itted | +0.055 |
ory | +0.055 |
obs | +0.054 |
Neg logit contributions | |
Am | -0.032 |
basement | -0.031 |
Amanda | -0.029 |
Elizabeth | -0.029 |
Anne | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
ishy | +0.002 |
obs | +0.002 |
uggets | +0.002 |
ory | +0.002 |
itted | +0.002 |
Neg logit contributions | |
basement | -0.002 |
Am | -0.002 |
Amanda | -0.002 |
Sky | -0.002 |
Ellen | -0.002 |
Token | Can |
Token ID | 6090 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Am | +0.001 |
Amanda | +0.001 |
Anne | +0.001 |
Ellen | +0.001 |
Sky | +0.001 |
Neg logit contributions | |
ishy | -0.003 |
obs | -0.003 |
ory | -0.003 |
inters | -0.003 |
fiber | -0.003 |
Token | I |
Token ID | 314 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Am | +0.008 |
Amanda | +0.008 |
basement | +0.008 |
loft | +0.007 |
Anne | +0.007 |
Neg logit contributions | |
ishy | -0.014 |
fiber | -0.014 |
ory | -0.013 |
inters | -0.013 |
obs | -0.013 |
Token | go |
Token ID | 467 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
ishy | +0.067 |
ory | +0.062 |
obs | +0.060 |
ashed | +0.059 |
inters | +0.059 |
Neg logit contributions | |
Amanda | -0.036 |
Am | -0.035 |
Anne | -0.035 |
Sky | -0.034 |
basement | -0.034 |
Token | bat |
Token ID | 7365 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Amanda | +0.064 |
Am | +0.063 |
Anne | +0.061 |
Sky | +0.060 |
Elizabeth | +0.060 |
Neg logit contributions | |
ishy | -0.107 |
ory | -0.101 |
obs | -0.096 |
ashed | -0.095 |
inters | -0.094 |
Token | he |
Token ID | 258 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Amanda | +0.033 |
Am | +0.031 |
Sky | +0.031 |
Anne | +0.031 |
Ellen | +0.030 |
Neg logit contributions | |
ishy | -0.042 |
ory | -0.038 |
obs | -0.037 |
ashed | -0.037 |
inters | -0.036 |
Token | in |
Token ID | 287 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Amanda | +0.025 |
Am | +0.024 |
Ellen | +0.023 |
Sky | +0.023 |
Jean | +0.023 |
Neg logit contributions | |
ishy | -0.052 |
ory | -0.050 |
uggets | -0.047 |
ashed | -0.047 |
ouses | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
Amanda | +0.041 |
Sky | +0.041 |
Anne | +0.038 |
Elizabeth | +0.038 |
Am | +0.038 |
Neg logit contributions | |
ishy | -0.086 |
ory | -0.081 |
obs | -0.078 |
fiber | -0.077 |
uggets | -0.076 |
Token | sea |
Token ID | 5417 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
Amanda | +0.015 |
Sky | +0.014 |
Am | +0.014 |
Anne | +0.014 |
Ellen | +0.014 |
Neg logit contributions | |
ishy | -0.015 |
ory | -0.014 |
obs | -0.013 |
ashed | -0.013 |
inters | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Amanda | +0.011 |
Am | +0.011 |
Sky | +0.010 |
Anne | +0.010 |
Ellen | +0.010 |
Neg logit contributions | |
ishy | -0.021 |
obs | -0.020 |
fiber | -0.020 |
ory | -0.020 |
inters | -0.019 |
Token | factory |
Token ID | 8860 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Amanda | +0.017 |
Am | +0.017 |
basement | +0.017 |
Sky | +0.017 |
Anne | +0.016 |
Neg logit contributions | |
ishy | -0.033 |
ory | -0.031 |
obs | -0.030 |
ashed | -0.030 |
fiber | -0.030 |
Token | cars |
Token ID | 5006 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Amanda | +0.026 |
Am | +0.026 |
Sky | +0.024 |
Elizabeth | +0.024 |
Ellen | +0.024 |
Neg logit contributions | |
ishy | -0.031 |
obs | -0.029 |
ory | -0.027 |
inters | -0.027 |
ashed | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ishy | +0.004 |
obs | +0.004 |
ory | +0.004 |
inters | +0.004 |
ashed | +0.004 |
Neg logit contributions | |
Amanda | -0.003 |
Am | -0.003 |
Anne | -0.003 |
Sky | -0.003 |
Ellen | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Amanda | +0.001 |
Sky | +0.001 |
Am | +0.001 |
Anne | +0.001 |
Ellen | +0.001 |
Neg logit contributions | |
ishy | -0.001 |
ory | -0.001 |
obs | -0.001 |
fiber | -0.001 |
ashed | -0.001 |
Token | filled |
Token ID | 5901 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ishy | +0.006 |
ory | +0.005 |
obs | +0.005 |
ashed | +0.005 |
fiber | +0.005 |
Neg logit contributions | |
Amanda | -0.004 |
Sky | -0.004 |
Am | -0.004 |
Anne | -0.004 |
Ellen | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Amanda | +0.041 |
Am | +0.039 |
Sky | +0.038 |
Anne | +0.037 |
Ellen | +0.037 |
Neg logit contributions | |
ishy | -0.131 |
obs | -0.121 |
ory | -0.121 |
ashed | -0.119 |
fiber | -0.119 |
Token | floor |
Token ID | 4314 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Amanda | +0.020 |
Am | +0.019 |
basement | +0.019 |
Sky | +0.019 |
Anne | +0.018 |
Neg logit contributions | |
ishy | -0.051 |
ory | -0.047 |
obs | -0.047 |
fiber | -0.046 |
ashed | -0.046 |
Token | with |
Token ID | 351 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Amanda | +0.040 |
Ellen | +0.039 |
Am | +0.039 |
Elizabeth | +0.038 |
June | +0.038 |
Neg logit contributions | |
ishy | -0.068 |
obs | -0.062 |
ashed | -0.062 |
ashes | -0.061 |
ory | -0.061 |
Token | them |
Token ID | 606 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
Amanda | +0.003 |
never | +0.003 |
also | +0.003 |
Sky | +0.003 |
� | +0.003 |
Neg logit contributions | |
ishy | -0.008 |
ory | -0.007 |
obs | -0.007 |
ouses | -0.007 |
abs | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
ishy | +0.029 |
obs | +0.027 |
ory | +0.027 |
ashed | +0.026 |
inters | +0.026 |
Neg logit contributions | |
Amanda | -0.019 |
Am | -0.019 |
Anne | -0.018 |
Sky | -0.018 |
Ellen | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ishy | +0.045 |
obs | +0.040 |
inters | +0.040 |
fiber | +0.040 |
ory | +0.039 |
Neg logit contributions | |
Amanda | -0.025 |
Am | -0.024 |
Anne | -0.024 |
Sky | -0.023 |
never | -0.023 |
Token | |
Token ID | 220 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Amanda | +0.010 |
basement | +0.010 |
Am | +0.010 |
Sky | +0.010 |
Anne | +0.010 |
Neg logit contributions | |
ishy | -0.021 |
ory | -0.020 |
obs | -0.020 |
ashed | -0.019 |
fiber | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
ishy | +0.102 |
obs | +0.096 |
ory | +0.095 |
ashed | +0.094 |
ouses | +0.094 |
Neg logit contributions | |
Amanda | -0.051 |
Am | -0.049 |
basement | -0.048 |
Anne | -0.047 |
Sky | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
basement | +0.015 |
Amanda | +0.015 |
Anne | +0.014 |
Ellen | +0.014 |
Sky | +0.014 |
Neg logit contributions | |
ishy | -0.023 |
ory | -0.022 |
uggets | -0.022 |
ouses | -0.022 |
obs | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
basement | +0.028 |
Anne | +0.028 |
Amanda | +0.028 |
Sky | +0.026 |
Ellen | +0.026 |
Neg logit contributions | |
ishy | -0.055 |
ory | -0.054 |
fiber | -0.054 |
ashed | -0.053 |
uggets | -0.053 |
Token | family |
Token ID | 1641 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
Amanda | +0.040 |
Am | +0.038 |
Sky | +0.038 |
Anne | +0.038 |
Ellen | +0.037 |
Neg logit contributions | |
ishy | -0.059 |
ory | -0.054 |
fiber | -0.052 |
ashed | -0.052 |
obs | -0.052 |
Token | was |
Token ID | 373 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
basement | +0.084 |
Elizabeth | +0.082 |
June | +0.080 |
Ellen | +0.080 |
Sky | +0.079 |
Neg logit contributions | |
ory | -0.086 |
ashed | -0.083 |
ishy | -0.080 |
ushed | -0.078 |
uc | -0.074 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
basement | +0.061 |
loft | +0.057 |
Sky | +0.055 |
Elizabeth | +0.054 |
outskirts | +0.053 |
Neg logit contributions | |
ishy | -0.071 |
uggets | -0.069 |
ory | -0.068 |
itted | -0.068 |
ashed | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
Amanda | +0.002 |
basement | +0.002 |
Am | +0.002 |
Sky | +0.002 |
Anne | +0.002 |
Neg logit contributions | |
ishy | -0.005 |
ory | -0.004 |
obs | -0.004 |
ashed | -0.004 |
fiber | -0.004 |
Token | have |
Token ID | 423 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
basement | +0.014 |
Amanda | +0.013 |
Sky | +0.013 |
Anne | +0.013 |
loft | +0.013 |
Neg logit contributions | |
ishy | -0.021 |
ory | -0.020 |
fiber | -0.020 |
preferences | -0.018 |
uggets | -0.018 |
Token | helped |
Token ID | 4193 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Amanda | +0.010 |
Sky | +0.010 |
Am | +0.010 |
basement | +0.010 |
Anne | +0.009 |
Neg logit contributions | |
ishy | -0.018 |
ory | -0.017 |
obs | -0.017 |
fiber | -0.017 |
ashed | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
Amanda | +0.027 |
Ellen | +0.026 |
Jean | +0.025 |
Sky | +0.024 |
Anne | +0.024 |
Neg logit contributions | |
ishy | -0.038 |
fiber | -0.037 |
ory | -0.037 |
uggets | -0.037 |
ashed | -0.036 |
Token | Can |
Token ID | 6090 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Amanda | +0.013 |
Am | +0.013 |
Sky | +0.012 |
Anne | +0.012 |
Ellen | +0.012 |
Neg logit contributions | |
ishy | -0.021 |
obs | -0.019 |
ory | -0.019 |
inters | -0.018 |
ashed | -0.018 |
Token | we |
Token ID | 356 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Am | +0.035 |
basement | +0.034 |
Amanda | +0.033 |
loft | +0.033 |
Jean | +0.031 |
Neg logit contributions | |
fiber | -0.045 |
ishy | -0.044 |
ory | -0.043 |
uggets | -0.041 |
preferences | -0.041 |
Token | leave |
Token ID | 2666 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
ishy | +0.023 |
ory | +0.021 |
fiber | +0.020 |
obs | +0.020 |
inters | +0.020 |
Neg logit contributions | |
Amanda | -0.016 |
Am | -0.016 |
Ellen | -0.016 |
Elizabeth | -0.015 |
Anne | -0.015 |
Token | our |
Token ID | 674 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
Amanda | +0.049 |
Am | +0.048 |
K | +0.045 |
Ellen | +0.045 |
Con | +0.044 |
Neg logit contributions | |
ishy | -0.107 |
ory | -0.103 |
uggets | -0.100 |
obs | -0.098 |
fiber | -0.096 |
Token | building |
Token ID | 2615 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
Amanda | +0.012 |
Sky | +0.012 |
basement | +0.011 |
Anne | +0.011 |
Am | +0.011 |
Neg logit contributions | |
ishy | -0.029 |
ory | -0.027 |
obs | -0.026 |
fiber | -0.026 |
ashed | -0.026 |
Token | here |
Token ID | 994 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Amanda | +0.070 |
Am | +0.068 |
Ellen | +0.065 |
Elizabeth | +0.065 |
Sky | +0.061 |
Neg logit contributions | |
ishy | -0.122 |
obs | -0.111 |
ashed | -0.110 |
ory | -0.109 |
ouses | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
Amanda | +0.024 |
Am | +0.024 |
Ellen | +0.023 |
Sky | +0.022 |
Jean | +0.022 |
Neg logit contributions | |
ishy | -0.041 |
ory | -0.040 |
uggets | -0.037 |
obs | -0.036 |
ashed | -0.036 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Am | +0.099 |
Amanda | +0.098 |
Ellen | +0.097 |
K | +0.094 |
Sky | +0.093 |
Neg logit contributions | |
ishy | -0.129 |
ory | -0.119 |
fiber | -0.114 |
uggets | -0.111 |
ashed | -0.110 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Amanda | +0.051 |
Am | +0.050 |
Sky | +0.048 |
basement | +0.048 |
Ellen | +0.046 |
Neg logit contributions | |
ishy | -0.093 |
ory | -0.087 |
obs | -0.083 |
inters | -0.082 |
uggets | -0.081 |
Token | Anna |
Token ID | 11735 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
Am | +0.020 |
Amanda | +0.020 |
basement | +0.019 |
Ellen | +0.019 |
Sky | +0.019 |
Neg logit contributions | |
ishy | -0.029 |
ory | -0.027 |
fiber | -0.027 |
obs | -0.026 |
uggets | -0.026 |