Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
ranger | +0.043 |
years | +0.042 |
clearing | +0.039 |
banquet | +0.038 |
Tooth | +0.038 |
Neg logit contributions | |
its | -0.056 |
apy | -0.055 |
ower | -0.053 |
ikes | -0.052 |
isel | -0.051 |
Token | M |
Token ID | 44 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
ranger | +0.046 |
years | +0.044 |
since | +0.044 |
Tooth | +0.042 |
banquet | +0.041 |
Neg logit contributions | |
its | -0.074 |
ower | -0.067 |
apy | -0.067 |
ikes | -0.065 |
aged | -0.064 |
Token | um |
Token ID | 388 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
ranger | +0.052 |
since | +0.048 |
clearing | +0.048 |
years | +0.046 |
Cave | +0.046 |
Neg logit contributions | |
its | -0.065 |
apy | -0.059 |
ower | -0.059 |
isel | -0.056 |
iggle | -0.056 |
Token | woke |
Token ID | 19092 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
ranger | +0.064 |
years | +0.058 |
clearing | +0.057 |
since | +0.056 |
Tooth | +0.055 |
Neg logit contributions | |
its | -0.121 |
ower | -0.112 |
apy | -0.110 |
aged | -0.110 |
isel | -0.109 |
Token | up |
Token ID | 510 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
ranger | +0.038 |
years | +0.036 |
clearing | +0.036 |
since | +0.036 |
café | +0.035 |
Neg logit contributions | |
its | -0.037 |
ower | -0.033 |
apy | -0.033 |
isel | -0.033 |
aged | -0.032 |
Token | early |
Token ID | 1903 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ranger | +0.115 |
years | +0.106 |
clearing | +0.103 |
since | +0.103 |
café | +0.101 |
Neg logit contributions | |
its | -0.187 |
ower | -0.177 |
apy | -0.174 |
aged | -0.173 |
ikes | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
ranger | +0.252 |
years | +0.227 |
clearing | +0.217 |
since | +0.214 |
Fairy | +0.212 |
Neg logit contributions | |
ower | -0.353 |
its | -0.347 |
aged | -0.330 |
apy | -0.327 |
ikes | -0.327 |
Token | She |
Token ID | 1375 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
ranger | +0.076 |
years | +0.072 |
clearing | +0.069 |
since | +0.069 |
café | +0.067 |
Neg logit contributions | |
its | -0.126 |
ower | -0.118 |
apy | -0.115 |
isel | -0.114 |
aged | -0.114 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
ranger | +0.083 |
years | +0.081 |
since | +0.078 |
clearing | +0.078 |
café | +0.076 |
Neg logit contributions | |
its | -0.153 |
ower | -0.145 |
ikes | -0.140 |
isel | -0.139 |
aged | -0.137 |
Token | to |
Token ID | 284 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
its | +0.067 |
ower | +0.063 |
apy | +0.062 |
aged | +0.061 |
isel | +0.061 |
Neg logit contributions | |
ranger | -0.036 |
years | -0.033 |
clearing | -0.033 |
since | -0.032 |
Tooth | -0.031 |
Token | make |
Token ID | 787 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
ranger | +0.043 |
years | +0.042 |
café | +0.041 |
clearing | +0.041 |
since | +0.040 |
Neg logit contributions | |
its | -0.047 |
ower | -0.045 |
aged | -0.043 |
ikes | -0.042 |
isel | -0.042 |
Token | her |
Token ID | 607 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ranger | +0.054 |
since | +0.053 |
Prince | +0.052 |
café | +0.051 |
clearing | +0.051 |
Neg logit contributions | |
its | -0.112 |
ower | -0.104 |
isel | -0.100 |
ikes | -0.100 |
aged | -0.097 |
Token | little |
Token ID | 1310 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
ranger | +0.017 |
years | +0.016 |
clearing | +0.016 |
since | +0.016 |
café | +0.016 |
Neg logit contributions | |
its | -0.025 |
ower | -0.022 |
isel | -0.022 |
apy | -0.022 |
ikes | -0.022 |
Token | boy |
Token ID | 2933 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
its | +0.084 |
ower | +0.079 |
apy | +0.077 |
aged | +0.076 |
isel | +0.076 |
Neg logit contributions | |
ranger | -0.058 |
years | -0.055 |
clearing | -0.054 |
since | -0.054 |
Tooth | -0.052 |
Token | went |
Token ID | 1816 |
Feature activation | +1.43e-04 |
Pos logit contributions | |
ranger | +0.045 |
years | +0.042 |
clearing | +0.041 |
Tooth | +0.041 |
since | +0.039 |
Neg logit contributions | |
its | -0.080 |
apy | -0.076 |
aged | -0.075 |
ower | -0.075 |
ikes | -0.072 |
Token | to |
Token ID | 284 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
years | +0.000 |
ranger | +0.000 |
Tooth | +0.000 |
Fairy | +0.000 |
since | +0.000 |
Neg logit contributions | |
its | -0.000 |
ower | -0.000 |
ikes | -0.000 |
aged | -0.000 |
apy | -0.000 |
Token | Church |
Token ID | 4564 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ranger | +0.040 |
years | +0.038 |
since | +0.036 |
clearing | +0.035 |
Tooth | +0.035 |
Neg logit contributions | |
its | -0.059 |
apy | -0.055 |
ower | -0.055 |
isel | -0.054 |
ikes | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
ranger | +0.259 |
dentist | +0.227 |
Tooth | +0.226 |
grizz | +0.223 |
years | +0.222 |
Neg logit contributions | |
its | -0.319 |
ower | -0.313 |
ikes | -0.302 |
apy | -0.301 |
iggle | -0.296 |
Token | It |
Token ID | 632 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
years | +0.065 |
ranger | +0.064 |
Tooth | +0.059 |
tale | +0.059 |
since | +0.057 |
Neg logit contributions | |
its | -0.081 |
apy | -0.081 |
ower | -0.078 |
isel | -0.076 |
ikes | -0.075 |
Token | was |
Token ID | 373 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ranger | +0.004 |
years | +0.004 |
clearing | +0.003 |
since | +0.003 |
Prince | +0.003 |
Neg logit contributions | |
its | -0.006 |
ower | -0.006 |
apy | -0.006 |
aged | -0.005 |
ikes | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
ranger | +0.026 |
enclosure | +0.025 |
Prince | +0.024 |
café | +0.024 |
banquet | +0.023 |
Neg logit contributions | |
its | -0.034 |
apy | -0.032 |
ower | -0.032 |
aged | -0.031 |
ikes | -0.030 |
Token | big |
Token ID | 1263 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ranger | +0.034 |
enclosure | +0.034 |
since | +0.033 |
years | +0.032 |
mother | +0.032 |
Neg logit contributions | |
ower | -0.026 |
apy | -0.025 |
its | -0.023 |
ikes | -0.021 |
isel | -0.021 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
its | +0.013 |
ower | +0.012 |
apy | +0.012 |
aged | +0.012 |
isel | +0.012 |
Neg logit contributions | |
ranger | -0.006 |
years | -0.006 |
since | -0.006 |
clearing | -0.006 |
café | -0.005 |
Token | T |
Token ID | 51 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
ranger | +0.050 |
years | +0.049 |
since | +0.047 |
Tooth | +0.046 |
dentist | +0.045 |
Neg logit contributions | |
its | -0.079 |
ower | -0.072 |
apy | -0.071 |
ikes | -0.071 |
oom | -0.069 |
Token | eddy |
Token ID | 21874 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
its | +0.007 |
apy | +0.007 |
ower | +0.007 |
isel | +0.007 |
aged | +0.007 |
Neg logit contributions | |
ranger | -0.006 |
years | -0.005 |
since | -0.005 |
Tooth | -0.005 |
clearing | -0.005 |
Token | woke |
Token ID | 19092 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
ranger | +0.020 |
Mrs | +0.018 |
clearing | +0.018 |
banquet | +0.017 |
years | +0.017 |
Neg logit contributions | |
aged | -0.018 |
its | -0.018 |
ged | -0.018 |
iggle | -0.017 |
apy | -0.016 |
Token | up |
Token ID | 510 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
ranger | +0.035 |
years | +0.035 |
since | +0.034 |
clearing | +0.034 |
Tooth | +0.033 |
Neg logit contributions | |
its | -0.036 |
ower | -0.033 |
isel | -0.032 |
apy | -0.032 |
aged | -0.031 |
Token | early |
Token ID | 1903 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ranger | +0.095 |
years | +0.089 |
since | +0.087 |
clearing | +0.087 |
café | +0.083 |
Neg logit contributions | |
its | -0.209 |
ower | -0.195 |
isel | -0.191 |
apy | -0.191 |
aged | -0.189 |
Token | and |
Token ID | 290 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
ranger | +0.226 |
years | +0.206 |
clearing | +0.198 |
Tooth | +0.197 |
dentist | +0.194 |
Neg logit contributions | |
ower | -0.333 |
its | -0.332 |
aged | -0.320 |
apy | -0.317 |
ikes | -0.315 |
Token | he |
Token ID | 339 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
ranger | +0.091 |
years | +0.088 |
since | +0.088 |
clearing | +0.086 |
café | +0.085 |
Neg logit contributions | |
its | -0.099 |
ower | -0.091 |
apy | -0.087 |
isel | -0.086 |
aged | -0.086 |
Token | was |
Token ID | 373 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
ranger | +0.075 |
years | +0.071 |
clearing | +0.069 |
since | +0.068 |
Tooth | +0.068 |
Neg logit contributions | |
its | -0.096 |
ower | -0.089 |
apy | -0.088 |
aged | -0.087 |
isel | -0.087 |
Token | feeling |
Token ID | 4203 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ranger | +0.038 |
years | +0.035 |
since | +0.034 |
clearing | +0.034 |
Tooth | +0.033 |
Neg logit contributions | |
its | -0.060 |
ower | -0.057 |
apy | -0.056 |
aged | -0.055 |
isel | -0.054 |
Token | sleepy |
Token ID | 42023 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ranger | +0.027 |
enclosure | +0.024 |
clearing | +0.024 |
café | +0.023 |
Tooth | +0.023 |
Neg logit contributions | |
its | -0.030 |
apy | -0.029 |
aged | -0.028 |
ower | -0.028 |
isel | -0.028 |
Token | trip |
Token ID | 5296 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ranger | +0.040 |
clearing | +0.039 |
since | +0.039 |
Tooth | +0.038 |
years | +0.038 |
Neg logit contributions | |
its | -0.046 |
ower | -0.044 |
apy | -0.043 |
aged | -0.042 |
ikes | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
its | +0.028 |
ower | +0.027 |
aged | +0.026 |
ikes | +0.026 |
apy | +0.025 |
Neg logit contributions | |
ranger | -0.016 |
clearing | -0.015 |
years | -0.015 |
Tooth | -0.015 |
Prince | -0.014 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
years | +0.028 |
ranger | +0.028 |
clearing | +0.027 |
Tooth | +0.027 |
Cave | +0.026 |
Neg logit contributions | |
its | -0.042 |
apy | -0.041 |
ower | -0.040 |
aged | -0.040 |
ikes | -0.039 |
Token | woke |
Token ID | 19092 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
ranger | +0.016 |
clearing | +0.015 |
years | +0.015 |
Tooth | +0.015 |
café | +0.014 |
Neg logit contributions | |
its | -0.030 |
aged | -0.029 |
ower | -0.028 |
apy | -0.028 |
ikes | -0.027 |
Token | up |
Token ID | 510 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
ranger | +0.009 |
years | +0.008 |
clearing | +0.008 |
since | +0.008 |
Tooth | +0.008 |
Neg logit contributions | |
its | -0.008 |
ower | -0.007 |
apy | -0.007 |
isel | -0.007 |
aged | -0.007 |
Token | early |
Token ID | 1903 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ranger | +0.125 |
years | +0.114 |
clearing | +0.114 |
Tooth | +0.112 |
Fairy | +0.112 |
Neg logit contributions | |
its | -0.165 |
ower | -0.152 |
aged | -0.151 |
apy | -0.151 |
iggle | -0.145 |
Token | and |
Token ID | 290 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
ranger | +0.220 |
years | +0.204 |
Fairy | +0.199 |
clearing | +0.198 |
Tooth | +0.197 |
Neg logit contributions | |
ower | -0.302 |
its | -0.300 |
aged | -0.285 |
ged | -0.283 |
ikes | -0.278 |
Token | got |
Token ID | 1392 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
ranger | +0.067 |
years | +0.064 |
clearing | +0.062 |
since | +0.061 |
Tooth | +0.061 |
Neg logit contributions | |
its | -0.088 |
apy | -0.082 |
ower | -0.082 |
aged | -0.082 |
isel | -0.080 |
Token | ready |
Token ID | 3492 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
its | +0.063 |
ower | +0.058 |
apy | +0.058 |
aged | +0.057 |
isel | +0.056 |
Neg logit contributions | |
ranger | -0.056 |
years | -0.053 |
clearing | -0.052 |
since | -0.052 |
café | -0.051 |
Token | easily |
Token ID | 3538 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
ranger | +0.012 |
years | +0.011 |
since | +0.011 |
clearing | +0.011 |
café | +0.011 |
Neg logit contributions | |
its | -0.023 |
ower | -0.022 |
apy | -0.021 |
isel | -0.021 |
aged | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
ranger | +0.077 |
clearing | +0.071 |
years | +0.070 |
Tooth | +0.069 |
Prince | +0.069 |
Neg logit contributions | |
its | -0.131 |
ower | -0.125 |
aged | -0.119 |
ikes | -0.119 |
isel | -0.118 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
its | +0.096 |
ower | +0.090 |
apy | +0.088 |
isel | +0.087 |
aged | +0.087 |
Neg logit contributions | |
ranger | -0.060 |
years | -0.057 |
clearing | -0.056 |
since | -0.055 |
café | -0.054 |
Token | named |
Token ID | 3706 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
ranger | +0.036 |
years | +0.032 |
clearing | +0.031 |
since | +0.030 |
Tooth | +0.029 |
Neg logit contributions | |
its | -0.127 |
ower | -0.120 |
apy | -0.119 |
aged | -0.118 |
isel | -0.117 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
ranger | +0.057 |
since | +0.055 |
years | +0.053 |
café | +0.049 |
clearing | +0.049 |
Neg logit contributions | |
its | -0.153 |
ower | -0.143 |
isel | -0.142 |
ikes | -0.141 |
apy | -0.137 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
years | +0.055 |
ranger | +0.055 |
since | +0.052 |
clearing | +0.051 |
café | +0.051 |
Neg logit contributions | |
its | -0.084 |
ower | -0.080 |
ikes | -0.079 |
isel | -0.078 |
apy | -0.076 |
Token | up |
Token ID | 510 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
ranger | +0.030 |
years | +0.029 |
clearing | +0.028 |
since | +0.028 |
Tooth | +0.028 |
Neg logit contributions | |
its | -0.030 |
ower | -0.027 |
isel | -0.027 |
apy | -0.026 |
aged | -0.026 |
Token | early |
Token ID | 1903 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ranger | +0.109 |
years | +0.103 |
clearing | +0.100 |
since | +0.100 |
café | +0.097 |
Neg logit contributions | |
its | -0.184 |
ower | -0.172 |
apy | -0.168 |
isel | -0.168 |
aged | -0.166 |
Token | in |
Token ID | 287 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
ranger | +0.240 |
years | +0.218 |
clearing | +0.216 |
Fairy | +0.212 |
Tooth | +0.212 |
Neg logit contributions | |
its | -0.303 |
ower | -0.302 |
aged | -0.288 |
apy | -0.284 |
ikes | -0.282 |
Token | the |
Token ID | 262 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
ranger | +0.043 |
since | +0.039 |
enclosure | +0.038 |
clearing | +0.038 |
years | +0.038 |
Neg logit contributions | |
its | -0.044 |
apy | -0.041 |
aged | -0.040 |
ower | -0.039 |
isel | -0.039 |
Token | morning |
Token ID | 3329 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
since | +0.102 |
ranger | +0.101 |
years | +0.101 |
indeed | +0.091 |
Fairy | +0.090 |
Neg logit contributions | |
ower | -0.110 |
its | -0.108 |
apy | -0.107 |
aged | -0.099 |
ikes | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
ranger | +0.117 |
grizz | +0.104 |
clearing | +0.102 |
Lion | +0.100 |
years | +0.100 |
Neg logit contributions | |
ower | -0.128 |
its | -0.121 |
apy | -0.119 |
aged | -0.116 |
iggle | -0.115 |
Token | She |
Token ID | 1375 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
ranger | +0.041 |
years | +0.038 |
clearing | +0.037 |
since | +0.037 |
café | +0.036 |
Neg logit contributions | |
its | -0.091 |
ower | -0.086 |
isel | -0.084 |
apy | -0.083 |
aged | -0.083 |
Token | day |
Token ID | 1110 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
ranger | +0.034 |
years | +0.033 |
clearing | +0.032 |
since | +0.032 |
Tooth | +0.031 |
Neg logit contributions | |
its | -0.033 |
ower | -0.031 |
apy | -0.030 |
isel | -0.029 |
aged | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
ranger | +0.009 |
years | +0.009 |
Tooth | +0.008 |
clearing | +0.008 |
café | +0.008 |
Neg logit contributions | |
apy | -0.016 |
its | -0.015 |
aged | -0.015 |
ower | -0.015 |
isel | -0.014 |
Token | she |
Token ID | 673 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
ranger | +0.035 |
years | +0.034 |
clearing | +0.032 |
Tooth | +0.032 |
café | +0.032 |
Neg logit contributions | |
its | -0.044 |
apy | -0.042 |
ower | -0.042 |
aged | -0.041 |
ikes | -0.040 |
Token | woke |
Token ID | 19092 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
ranger | +0.109 |
years | +0.100 |
clearing | +0.100 |
Tooth | +0.099 |
since | +0.097 |
Neg logit contributions | |
its | -0.135 |
aged | -0.121 |
ower | -0.121 |
apy | -0.120 |
isel | -0.119 |
Token | up |
Token ID | 510 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
ranger | +0.015 |
years | +0.015 |
clearing | +0.014 |
since | +0.014 |
café | +0.014 |
Neg logit contributions | |
its | -0.011 |
ower | -0.011 |
apy | -0.010 |
aged | -0.010 |
ikes | -0.010 |
Token | early |
Token ID | 1903 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ranger | +0.125 |
years | +0.114 |
clearing | +0.113 |
since | +0.111 |
Tooth | +0.109 |
Neg logit contributions | |
its | -0.173 |
ower | -0.162 |
aged | -0.160 |
apy | -0.159 |
ikes | -0.153 |
Token | to |
Token ID | 284 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
ranger | +0.222 |
years | +0.199 |
THE | +0.192 |
Lion | +0.191 |
Fairy | +0.191 |
Neg logit contributions | |
ower | -0.313 |
its | -0.307 |
aged | -0.293 |
apy | -0.287 |
ged | -0.286 |
Token | see |
Token ID | 766 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
clearing | +0.040 |
years | +0.039 |
since | +0.038 |
Prince | +0.038 |
Tooth | +0.038 |
Neg logit contributions | |
its | -0.058 |
ower | -0.056 |
ikes | -0.054 |
aged | -0.052 |
apy | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
ranger | +0.079 |
years | +0.075 |
clearing | +0.073 |
since | +0.073 |
Tooth | +0.070 |
Neg logit contributions | |
its | -0.137 |
ower | -0.129 |
apy | -0.125 |
isel | -0.124 |
aged | -0.124 |
Token | sunrise |
Token ID | 40048 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
ranger | +0.082 |
since | +0.079 |
years | +0.077 |
clearing | +0.075 |
café | +0.073 |
Neg logit contributions | |
its | -0.110 |
ower | -0.104 |
ikes | -0.097 |
apy | -0.096 |
aged | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +7.17e-03 |
Pos logit contributions | |
ranger | +0.133 |
years | +0.124 |
Tooth | +0.123 |
clearing | +0.122 |
Prince | +0.122 |
Neg logit contributions | |
its | -0.201 |
ower | -0.194 |
apy | -0.188 |
ikes | -0.182 |
aged | -0.181 |
Token | named |
Token ID | 3706 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
ranger | +0.037 |
years | +0.033 |
clearing | +0.032 |
since | +0.031 |
café | +0.030 |
Neg logit contributions | |
its | -0.139 |
ower | -0.132 |
apy | -0.130 |
aged | -0.129 |
isel | -0.129 |
Token | Tim |
Token ID | 5045 |
Feature activation | -5.46e-03 |
Pos logit contributions | |
ranger | +0.096 |
since | +0.090 |
years | +0.090 |
clearing | +0.089 |
café | +0.087 |
Neg logit contributions | |
its | -0.114 |
ower | -0.105 |
apy | -0.101 |
aged | -0.101 |
isel | -0.101 |
Token | my |
Token ID | 1820 |
Feature activation | +5.92e-04 |
Pos logit contributions | |
its | +0.015 |
apy | +0.015 |
ower | +0.014 |
ikes | +0.014 |
isel | +0.014 |
Neg logit contributions | |
ranger | -0.004 |
years | -0.004 |
since | -0.004 |
clearing | -0.003 |
café | -0.003 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
years | +0.001 |
ranger | +0.001 |
since | +0.001 |
clearing | +0.001 |
awoke | +0.001 |
Neg logit contributions | |
its | -0.001 |
ower | -0.001 |
ikes | -0.001 |
isel | -0.001 |
apy | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
ranger | +0.028 |
years | +0.027 |
clearing | +0.026 |
since | +0.026 |
Tooth | +0.026 |
Neg logit contributions | |
its | -0.028 |
ower | -0.026 |
isel | -0.025 |
apy | -0.025 |
aged | -0.024 |
Token | early |
Token ID | 1903 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ranger | +0.107 |
years | +0.101 |
clearing | +0.099 |
since | +0.098 |
café | +0.096 |
Neg logit contributions | |
its | -0.165 |
ower | -0.154 |
apy | -0.150 |
aged | -0.149 |
isel | -0.148 |
Token | in |
Token ID | 287 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ranger | +0.239 |
years | +0.219 |
clearing | +0.213 |
Fairy | +0.213 |
since | +0.212 |
Neg logit contributions | |
ower | -0.297 |
its | -0.294 |
aged | -0.284 |
apy | -0.277 |
ikes | -0.276 |
Token | the |
Token ID | 262 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
ranger | +0.024 |
since | +0.022 |
Fairy | +0.021 |
years | +0.021 |
clearing | +0.021 |
Neg logit contributions | |
its | -0.034 |
apy | -0.032 |
isel | -0.031 |
aged | -0.031 |
ower | -0.031 |
Token | morning |
Token ID | 3329 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
since | +0.084 |
ranger | +0.084 |
years | +0.082 |
Fairy | +0.077 |
indeed | +0.075 |
Neg logit contributions | |
ower | -0.080 |
apy | -0.079 |
its | -0.079 |
ikes | -0.073 |
aged | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
ranger | +0.100 |
grizz | +0.087 |
years | +0.086 |
clearing | +0.085 |
Fairy | +0.085 |
Neg logit contributions | |
ower | -0.110 |
its | -0.102 |
apy | -0.102 |
aged | -0.099 |
iggle | -0.096 |
Token | The |
Token ID | 383 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
ranger | +0.019 |
clearing | +0.016 |
café | +0.016 |
since | +0.015 |
Tooth | +0.014 |
Neg logit contributions | |
its | -0.066 |
aged | -0.062 |
ower | -0.061 |
isel | -0.060 |
apy | -0.059 |
Token | day |
Token ID | 1110 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ranger | +0.036 |
years | +0.035 |
Tooth | +0.034 |
Prince | +0.034 |
clearing | +0.033 |
Neg logit contributions | |
its | -0.023 |
ower | -0.023 |
apy | -0.021 |
aged | -0.020 |
isel | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
ranger | +0.010 |
since | +0.010 |
years | +0.010 |
clearing | +0.009 |
Prince | +0.009 |
Neg logit contributions | |
its | -0.042 |
ower | -0.039 |
ikes | -0.038 |
isel | -0.038 |
aged | -0.037 |
Token | Benny |
Token ID | 44275 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
ranger | +0.022 |
since | +0.020 |
years | +0.020 |
clearing | +0.020 |
Prince | +0.019 |
Neg logit contributions | |
its | -0.044 |
ower | -0.041 |
aged | -0.040 |
isel | -0.040 |
ikes | -0.039 |
Token | woke |
Token ID | 19092 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
its | +0.087 |
aged | +0.084 |
ower | +0.082 |
iggle | +0.077 |
apy | +0.076 |
Neg logit contributions | |
ranger | -0.068 |
years | -0.065 |
Tooth | -0.064 |
clearing | -0.063 |
banquet | -0.063 |
Token | up |
Token ID | 510 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
ranger | +0.013 |
years | +0.013 |
clearing | +0.013 |
since | +0.012 |
Tooth | +0.012 |
Neg logit contributions | |
its | -0.013 |
ower | -0.012 |
apy | -0.011 |
isel | -0.011 |
aged | -0.011 |
Token | early |
Token ID | 1903 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ranger | +0.115 |
years | +0.107 |
clearing | +0.105 |
café | +0.103 |
since | +0.103 |
Neg logit contributions | |
its | -0.171 |
ower | -0.161 |
aged | -0.158 |
apy | -0.156 |
ikes | -0.152 |
Token | and |
Token ID | 290 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
ranger | +0.199 |
years | +0.185 |
clearing | +0.174 |
Fairy | +0.172 |
Prince | +0.172 |
Neg logit contributions | |
its | -0.337 |
ower | -0.333 |
aged | -0.321 |
ikes | -0.313 |
apy | -0.311 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
ranger | +0.061 |
years | +0.059 |
clearing | +0.056 |
Fairy | +0.056 |
Tooth | +0.056 |
Neg logit contributions | |
its | -0.072 |
aged | -0.069 |
apy | -0.068 |
ower | -0.068 |
isel | -0.066 |
Token | that |
Token ID | 326 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
ranger | +0.031 |
years | +0.030 |
since | +0.030 |
clearing | +0.029 |
café | +0.029 |
Neg logit contributions | |
its | -0.049 |
apy | -0.048 |
aged | -0.046 |
ower | -0.046 |
isel | -0.045 |
Token | there |
Token ID | 612 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
years | +0.029 |
ranger | +0.028 |
enclosure | +0.027 |
since | +0.027 |
café | +0.027 |
Neg logit contributions | |
apy | -0.031 |
its | -0.030 |
aged | -0.029 |
ower | -0.029 |
isel | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
its | +0.056 |
apy | +0.052 |
ower | +0.051 |
ikes | +0.050 |
aged | +0.050 |
Neg logit contributions | |
ranger | -0.039 |
years | -0.037 |
since | -0.036 |
Tooth | -0.036 |
clearing | -0.036 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
its | +0.054 |
apy | +0.052 |
ower | +0.050 |
isel | +0.050 |
ikes | +0.049 |
Neg logit contributions | |
ranger | -0.041 |
years | -0.039 |
dentist | -0.037 |
since | -0.037 |
banquet | -0.037 |
Token | M |
Token ID | 44 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ranger | +0.044 |
years | +0.043 |
since | +0.042 |
Tooth | +0.042 |
banquet | +0.040 |
Neg logit contributions | |
its | -0.065 |
ower | -0.059 |
apy | -0.058 |
ikes | -0.058 |
oom | -0.057 |
Token | olly |
Token ID | 5098 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
ranger | +0.050 |
clearing | +0.048 |
since | +0.048 |
Prince | +0.046 |
Cave | +0.045 |
Neg logit contributions | |
its | -0.057 |
apy | -0.051 |
ower | -0.051 |
iggle | -0.049 |
ikes | -0.047 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ranger | +0.071 |
clearing | +0.065 |
Tooth | +0.064 |
dentist | +0.063 |
years | +0.063 |
Neg logit contributions | |
its | -0.084 |
aged | -0.080 |
ower | -0.078 |
apy | -0.078 |
ged | -0.075 |
Token | up |
Token ID | 510 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
ranger | +0.025 |
years | +0.024 |
since | +0.024 |
clearing | +0.024 |
Tooth | +0.023 |
Neg logit contributions | |
its | -0.024 |
ower | -0.022 |
isel | -0.022 |
apy | -0.021 |
aged | -0.021 |
Token | early |
Token ID | 1903 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ranger | +0.094 |
years | +0.090 |
clearing | +0.087 |
since | +0.087 |
café | +0.084 |
Neg logit contributions | |
its | -0.179 |
ower | -0.167 |
isel | -0.163 |
apy | -0.163 |
ikes | -0.161 |
Token | in |
Token ID | 287 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
ranger | +0.223 |
years | +0.205 |
clearing | +0.198 |
Tooth | +0.195 |
since | +0.195 |
Neg logit contributions | |
its | -0.320 |
ower | -0.314 |
aged | -0.301 |
apy | -0.300 |
ikes | -0.294 |
Token | the |
Token ID | 262 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
ranger | +0.036 |
years | +0.030 |
dentist | +0.030 |
Lion | +0.030 |
grizz | +0.030 |
Neg logit contributions | |
its | -0.038 |
apy | -0.038 |
isel | -0.035 |
aged | -0.035 |
ower | -0.035 |
Token | morning |
Token ID | 3329 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
ranger | +0.089 |
years | +0.084 |
since | +0.083 |
indeed | +0.081 |
Fairy | +0.078 |
Neg logit contributions | |
apy | -0.089 |
ower | -0.088 |
its | -0.084 |
aged | -0.079 |
ikes | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
ranger | +0.101 |
grizz | +0.087 |
years | +0.085 |
dentist | +0.083 |
clearing | +0.083 |
Neg logit contributions | |
ower | -0.130 |
its | -0.126 |
apy | -0.124 |
aged | -0.120 |
iggle | -0.117 |
Token | She |
Token ID | 1375 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
ranger | +0.045 |
years | +0.043 |
dentist | +0.040 |
Tooth | +0.039 |
clearing | +0.039 |
Neg logit contributions | |
its | -0.064 |
apy | -0.061 |
ower | -0.060 |
isel | -0.058 |
aged | -0.058 |
Token | day |
Token ID | 1110 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
its | +0.090 |
aged | +0.083 |
isel | +0.082 |
ower | +0.082 |
ikes | +0.081 |
Neg logit contributions | |
ranger | -0.061 |
years | -0.059 |
clearing | -0.058 |
café | -0.058 |
since | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
its | +0.033 |
ower | +0.031 |
apy | +0.030 |
aged | +0.030 |
isel | +0.030 |
Neg logit contributions | |
ranger | -0.013 |
years | -0.012 |
clearing | -0.011 |
since | -0.011 |
café | -0.011 |
Token | she |
Token ID | 673 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
ranger | +0.007 |
years | +0.007 |
clearing | +0.007 |
enclosure | +0.006 |
café | +0.006 |
Neg logit contributions | |
its | -0.009 |
apy | -0.009 |
ower | -0.008 |
aged | -0.008 |
ikes | -0.008 |
Token | woke |
Token ID | 19092 |
Feature activation | -3.98e-04 |
Pos logit contributions | |
ranger | +0.083 |
years | +0.079 |
clearing | +0.077 |
since | +0.077 |
café | +0.075 |
Neg logit contributions | |
its | -0.099 |
ower | -0.091 |
apy | -0.089 |
aged | -0.088 |
isel | -0.088 |
Token | up |
Token ID | 510 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
its | +0.001 |
ower | +0.001 |
isel | +0.001 |
apy | +0.001 |
ikes | +0.001 |
Neg logit contributions | |
ranger | -0.001 |
years | -0.001 |
since | -0.001 |
Tooth | -0.001 |
clearing | -0.001 |
Token | early |
Token ID | 1903 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ranger | +0.106 |
years | +0.100 |
clearing | +0.098 |
since | +0.097 |
café | +0.095 |
Neg logit contributions | |
its | -0.168 |
ower | -0.156 |
apy | -0.153 |
isel | -0.151 |
aged | -0.151 |
Token | and |
Token ID | 290 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
ranger | +0.205 |
years | +0.189 |
clearing | +0.183 |
since | +0.180 |
café | +0.177 |
Neg logit contributions | |
its | -0.338 |
ower | -0.324 |
aged | -0.312 |
apy | -0.312 |
ikes | -0.309 |
Token | went |
Token ID | 1816 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
ranger | +0.054 |
years | +0.052 |
clearing | +0.050 |
since | +0.050 |
café | +0.049 |
Neg logit contributions | |
its | -0.074 |
ower | -0.069 |
apy | -0.067 |
isel | -0.067 |
aged | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
its | +0.041 |
ower | +0.039 |
aged | +0.038 |
apy | +0.038 |
ikes | +0.037 |
Neg logit contributions | |
ranger | -0.030 |
years | -0.030 |
since | -0.028 |
Tooth | -0.028 |
clearing | -0.027 |
Token | school |
Token ID | 1524 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
ranger | +0.018 |
clearing | +0.018 |
years | +0.018 |
café | +0.018 |
Tooth | +0.018 |
Neg logit contributions | |
its | -0.037 |
ower | -0.035 |
aged | -0.033 |
isel | -0.033 |
apy | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ranger | +0.107 |
clearing | +0.105 |
Tooth | +0.102 |
grizz | +0.101 |
Fairy | +0.100 |
Neg logit contributions | |
its | -0.147 |
ower | -0.143 |
ikes | -0.139 |
aged | -0.138 |
apy | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
its | +0.198 |
aged | +0.190 |
ower | +0.188 |
apy | +0.181 |
ikes | +0.179 |
Neg logit contributions | |
clearing | -0.121 |
ranger | -0.121 |
Tooth | -0.119 |
dentist | -0.118 |
café | -0.117 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
its | +0.032 |
apy | +0.031 |
ower | +0.030 |
aged | +0.030 |
isel | +0.029 |
Neg logit contributions | |
years | -0.022 |
ranger | -0.021 |
Tooth | -0.021 |
since | -0.021 |
banquet | -0.020 |
Token | Bob |
Token ID | 18861 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
ranger | +0.045 |
years | +0.045 |
Tooth | +0.043 |
since | +0.043 |
dentist | +0.042 |
Neg logit contributions | |
its | -0.076 |
ower | -0.069 |
apy | -0.069 |
ikes | -0.068 |
oom | -0.066 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
ranger | +0.039 |
years | +0.036 |
clearing | +0.035 |
Tooth | +0.035 |
Prince | +0.034 |
Neg logit contributions | |
its | -0.057 |
ower | -0.053 |
aged | -0.052 |
apy | -0.051 |
isel | -0.051 |
Token | up |
Token ID | 510 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
ranger | +0.030 |
years | +0.028 |
clearing | +0.028 |
since | +0.028 |
café | +0.027 |
Neg logit contributions | |
its | -0.027 |
ower | -0.024 |
apy | -0.024 |
isel | -0.023 |
aged | -0.023 |
Token | early |
Token ID | 1903 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ranger | +0.099 |
years | +0.093 |
clearing | +0.091 |
since | +0.090 |
café | +0.088 |
Neg logit contributions | |
its | -0.175 |
ower | -0.164 |
apy | -0.160 |
isel | -0.159 |
aged | -0.158 |
Token | one |
Token ID | 530 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ranger | +0.219 |
years | +0.202 |
Tooth | +0.195 |
dentist | +0.194 |
clearing | +0.192 |
Neg logit contributions | |
ower | -0.310 |
its | -0.310 |
aged | -0.295 |
apy | -0.293 |
ikes | -0.290 |
Token | day |
Token ID | 1110 |
Feature activation | -1.49e-03 |
Pos logit contributions | |
ranger | +0.054 |
Prince | +0.051 |
grizz | +0.050 |
Tooth | +0.049 |
café | +0.048 |
Neg logit contributions | |
its | -0.051 |
ower | -0.048 |
apy | -0.046 |
ikes | -0.044 |
iggle | -0.043 |
Token | feeling |
Token ID | 4203 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
its | +0.003 |
ower | +0.003 |
apy | +0.003 |
aged | +0.003 |
ikes | +0.003 |
Neg logit contributions | |
ranger | -0.002 |
years | -0.002 |
clearing | -0.002 |
Tooth | -0.002 |
café | -0.002 |
Token | alert |
Token ID | 7995 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
its | +0.007 |
ower | +0.007 |
apy | +0.006 |
isel | +0.006 |
aged | +0.006 |
Neg logit contributions | |
ranger | -0.006 |
years | -0.005 |
clearing | -0.005 |
since | -0.005 |
café | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
ranger | +0.024 |
clearing | +0.022 |
dentist | +0.022 |
Tooth | +0.021 |
café | +0.021 |
Neg logit contributions | |
its | -0.032 |
ower | -0.031 |
aged | -0.031 |
ikes | -0.030 |
apy | -0.029 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
ranger | +0.030 |
years | +0.029 |
clearing | +0.029 |
since | +0.028 |
Prince | +0.028 |
Neg logit contributions | |
its | -0.025 |
ower | -0.024 |
apy | -0.023 |
aged | -0.022 |
isel | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
years | +0.065 |
ranger | +0.065 |
Cave | +0.062 |
Tooth | +0.062 |
grizz | +0.061 |
Neg logit contributions | |
apy | -0.075 |
aged | -0.075 |
ower | -0.074 |
its | -0.073 |
oom | -0.072 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ranger | +0.013 |
years | +0.012 |
since | +0.012 |
clearing | +0.012 |
café | +0.011 |
Neg logit contributions | |
its | -0.024 |
ower | -0.022 |
isel | -0.021 |
apy | -0.021 |
aged | -0.021 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
ranger | +0.026 |
years | +0.024 |
clearing | +0.024 |
Tooth | +0.023 |
Prince | +0.023 |
Neg logit contributions | |
its | -0.026 |
aged | -0.024 |
ower | -0.023 |
apy | -0.023 |
isel | -0.022 |
Token | up |
Token ID | 510 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
ranger | +0.002 |
years | +0.002 |
since | +0.002 |
clearing | +0.002 |
Tooth | +0.002 |
Neg logit contributions | |
its | -0.002 |
ower | -0.002 |
isel | -0.002 |
apy | -0.002 |
aged | -0.002 |
Token | early |
Token ID | 1903 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ranger | +0.118 |
clearing | +0.107 |
years | +0.107 |
enclosure | +0.106 |
café | +0.105 |
Neg logit contributions | |
its | -0.159 |
ower | -0.151 |
aged | -0.148 |
apy | -0.145 |
ikes | -0.141 |
Token | and |
Token ID | 290 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
ranger | +0.198 |
years | +0.181 |
clearing | +0.174 |
Prince | +0.170 |
Tooth | +0.169 |
Neg logit contributions | |
its | -0.339 |
ower | -0.332 |
aged | -0.319 |
apy | -0.314 |
ikes | -0.314 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ranger | +0.062 |
years | +0.059 |
clearing | +0.056 |
Tooth | +0.055 |
Fairy | +0.055 |
Neg logit contributions | |
its | -0.071 |
apy | -0.069 |
aged | -0.068 |
ower | -0.068 |
isel | -0.066 |
Token | that |
Token ID | 326 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ranger | +0.030 |
years | +0.028 |
clearing | +0.027 |
since | +0.027 |
café | +0.026 |
Neg logit contributions | |
its | -0.054 |
ower | -0.051 |
apy | -0.050 |
aged | -0.049 |
isel | -0.049 |
Token | her |
Token ID | 607 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
ranger | +0.037 |
years | +0.036 |
enclosure | +0.035 |
clearing | +0.034 |
since | +0.034 |
Neg logit contributions | |
apy | -0.035 |
its | -0.035 |
ower | -0.033 |
aged | -0.033 |
ikes | -0.032 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
ranger | +0.030 |
years | +0.029 |
since | +0.029 |
clearing | +0.028 |
café | +0.028 |
Neg logit contributions | |
its | -0.041 |
ower | -0.039 |
apy | -0.038 |
aged | -0.037 |
isel | -0.037 |
Token | morning |
Token ID | 3329 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
ranger | +0.070 |
Tooth | +0.067 |
Prince | +0.066 |
years | +0.066 |
since | +0.066 |
Neg logit contributions | |
its | -0.054 |
apy | -0.049 |
ower | -0.049 |
isel | -0.046 |
aged | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ranger | +0.075 |
years | +0.073 |
enclosure | +0.069 |
Tooth | +0.068 |
dentist | +0.067 |
Neg logit contributions | |
apy | -0.101 |
aged | -0.091 |
its | -0.089 |
ower | -0.089 |
ged | -0.087 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ranger | +0.030 |
years | +0.030 |
enclosure | +0.028 |
clearing | +0.027 |
tale | +0.027 |
Neg logit contributions | |
apy | -0.040 |
its | -0.038 |
ower | -0.037 |
aged | -0.037 |
ikes | -0.036 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
ranger | +0.031 |
clearing | +0.028 |
years | +0.027 |
Tooth | +0.027 |
THE | +0.027 |
Neg logit contributions | |
its | -0.034 |
aged | -0.031 |
iggle | -0.029 |
ower | -0.029 |
apy | -0.028 |
Token | up |
Token ID | 510 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
ranger | +0.004 |
years | +0.004 |
clearing | +0.004 |
since | +0.004 |
café | +0.004 |
Neg logit contributions | |
its | -0.003 |
ower | -0.003 |
apy | -0.002 |
aged | -0.002 |
ikes | -0.002 |
Token | early |
Token ID | 1903 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ranger | +0.119 |
years | +0.109 |
clearing | +0.107 |
since | +0.106 |
café | +0.104 |
Neg logit contributions | |
its | -0.159 |
ower | -0.149 |
aged | -0.147 |
apy | -0.146 |
iggle | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ranger | +0.227 |
years | +0.208 |
THE | +0.206 |
Lion | +0.201 |
grizz | +0.199 |
Neg logit contributions | |
ower | -0.289 |
its | -0.279 |
aged | -0.269 |
ged | -0.264 |
iggle | -0.263 |
Token | She |
Token ID | 1375 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
ranger | +0.021 |
years | +0.020 |
clearing | +0.019 |
since | +0.019 |
café | +0.019 |
Neg logit contributions | |
its | -0.037 |
ower | -0.035 |
apy | -0.034 |
aged | -0.034 |
isel | -0.034 |
Token | heard |
Token ID | 2982 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
ranger | +0.062 |
Prince | +0.056 |
clearing | +0.056 |
Tooth | +0.055 |
since | +0.055 |
Neg logit contributions | |
its | -0.074 |
apy | -0.070 |
aged | -0.068 |
ower | -0.067 |
isel | -0.066 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.85e-04 |
Pos logit contributions | |
ranger | +0.057 |
years | +0.053 |
clearing | +0.052 |
since | +0.052 |
café | +0.050 |
Neg logit contributions | |
its | -0.092 |
apy | -0.087 |
ower | -0.085 |
aged | -0.085 |
ikes | -0.083 |
Token | crying |
Token ID | 13774 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ranger | +0.001 |
years | +0.001 |
clearing | +0.001 |
since | +0.001 |
Tooth | +0.001 |
Neg logit contributions | |
its | -0.001 |
ower | -0.001 |
apy | -0.001 |
aged | -0.001 |
ikes | -0.001 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
its | +0.086 |
ower | +0.079 |
aged | +0.077 |
apy | +0.077 |
isel | +0.077 |
Neg logit contributions | |
ranger | -0.048 |
years | -0.045 |
clearing | -0.044 |
since | -0.044 |
café | -0.043 |
Token | named |
Token ID | 3706 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ranger | +0.057 |
clearing | +0.049 |
years | +0.048 |
since | +0.048 |
Tooth | +0.047 |
Neg logit contributions | |
its | -0.162 |
ower | -0.154 |
apy | -0.153 |
aged | -0.153 |
isel | -0.150 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
ranger | +0.056 |
since | +0.054 |
years | +0.052 |
clearing | +0.050 |
café | +0.049 |
Neg logit contributions | |
its | -0.137 |
ower | -0.129 |
isel | -0.127 |
ikes | -0.126 |
apy | -0.124 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
years | +0.052 |
ranger | +0.051 |
since | +0.051 |
clearing | +0.048 |
café | +0.047 |
Neg logit contributions | |
its | -0.087 |
ower | -0.082 |
ikes | -0.081 |
apy | -0.080 |
isel | -0.080 |
Token | up |
Token ID | 510 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
ranger | +0.030 |
years | +0.029 |
clearing | +0.029 |
since | +0.029 |
Tooth | +0.028 |
Neg logit contributions | |
its | -0.030 |
ower | -0.028 |
isel | -0.027 |
apy | -0.027 |
aged | -0.026 |
Token | early |
Token ID | 1903 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ranger | +0.109 |
years | +0.102 |
clearing | +0.100 |
since | +0.099 |
café | +0.097 |
Neg logit contributions | |
its | -0.172 |
ower | -0.160 |
apy | -0.156 |
aged | -0.155 |
isel | -0.155 |
Token | today |
Token ID | 1909 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
ranger | +0.238 |
years | +0.220 |
clearing | +0.216 |
since | +0.214 |
Fairy | +0.212 |
Neg logit contributions | |
ower | -0.287 |
its | -0.285 |
aged | -0.276 |
apy | -0.270 |
ikes | -0.265 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
ranger | +0.136 |
grizz | +0.122 |
clearing | +0.122 |
years | +0.118 |
cal | +0.118 |
Neg logit contributions | |
ower | -0.163 |
its | -0.161 |
apy | -0.157 |
aged | -0.148 |
iggle | -0.147 |
Token | She |
Token ID | 1375 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
ranger | +0.030 |
since | +0.028 |
years | +0.028 |
clearing | +0.027 |
café | +0.027 |
Neg logit contributions | |
its | -0.074 |
ower | -0.069 |
isel | -0.068 |
apy | -0.067 |
aged | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | +7.19e-03 |
Pos logit contributions | |
ranger | +0.068 |
clearing | +0.063 |
years | +0.063 |
since | +0.062 |
café | +0.061 |
Neg logit contributions | |
its | -0.082 |
ower | -0.075 |
apy | -0.075 |
aged | -0.074 |
isel | -0.072 |
Token | so |
Token ID | 523 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
ranger | +0.009 |
years | +0.009 |
clearing | +0.008 |
since | +0.008 |
Tooth | +0.008 |
Neg logit contributions | |
its | -0.016 |
ower | -0.015 |
isel | -0.015 |
apy | -0.015 |
ikes | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ranger | +0.027 |
years | +0.025 |
clearing | +0.025 |
since | +0.025 |
Tooth | +0.024 |
Neg logit contributions | |
its | -0.024 |
ower | -0.022 |
apy | -0.022 |
aged | -0.021 |
isel | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
ranger | +0.010 |
years | +0.009 |
since | +0.009 |
clearing | +0.009 |
café | +0.008 |
Neg logit contributions | |
its | -0.033 |
ower | -0.031 |
isel | -0.030 |
ikes | -0.030 |
aged | -0.029 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ranger | +0.018 |
since | +0.016 |
years | +0.016 |
clearing | +0.016 |
café | +0.015 |
Neg logit contributions | |
its | -0.034 |
ower | -0.031 |
isel | -0.031 |
ikes | -0.030 |
aged | -0.030 |
Token | woke |
Token ID | 19092 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
ranger | +0.020 |
clearing | +0.019 |
Fairy | +0.018 |
Tooth | +0.018 |
years | +0.018 |
Neg logit contributions | |
its | -0.034 |
aged | -0.032 |
ower | -0.032 |
apy | -0.030 |
ikes | -0.030 |
Token | up |
Token ID | 510 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
ranger | +0.003 |
years | +0.003 |
since | +0.003 |
Tooth | +0.003 |
clearing | +0.003 |
Neg logit contributions | |
its | -0.004 |
ower | -0.003 |
isel | -0.003 |
apy | -0.003 |
aged | -0.003 |
Token | early |
Token ID | 1903 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ranger | +0.102 |
years | +0.096 |
clearing | +0.094 |
since | +0.093 |
café | +0.091 |
Neg logit contributions | |
its | -0.178 |
ower | -0.167 |
apy | -0.163 |
isel | -0.162 |
aged | -0.162 |
Token | and |
Token ID | 290 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
ranger | +0.182 |
years | +0.169 |
clearing | +0.164 |
since | +0.158 |
Tooth | +0.157 |
Neg logit contributions | |
its | -0.351 |
ower | -0.338 |
aged | -0.327 |
apy | -0.324 |
ikes | -0.322 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
ranger | +0.060 |
years | +0.058 |
clearing | +0.056 |
Tooth | +0.055 |
Fairy | +0.054 |
Neg logit contributions | |
its | -0.070 |
aged | -0.066 |
apy | -0.066 |
ower | -0.066 |
isel | -0.063 |
Token | that |
Token ID | 326 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ranger | +0.028 |
years | +0.026 |
clearing | +0.026 |
since | +0.025 |
café | +0.025 |
Neg logit contributions | |
its | -0.051 |
ower | -0.048 |
apy | -0.047 |
aged | -0.046 |
isel | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
ranger | +0.033 |
years | +0.032 |
clearing | +0.032 |
enclosure | +0.031 |
since | +0.031 |
Neg logit contributions | |
its | -0.033 |
apy | -0.031 |
ower | -0.031 |
aged | -0.030 |
ikes | -0.029 |
Token | sun |
Token ID | 4252 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
ranger | +0.060 |
years | +0.058 |
clearing | +0.057 |
since | +0.057 |
café | +0.054 |
Neg logit contributions | |
its | -0.080 |
ower | -0.075 |
ikes | -0.072 |
apy | -0.071 |
aged | -0.071 |
Token | who |
Token ID | 508 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ranger | +0.096 |
Prince | +0.093 |
banquet | +0.091 |
clearing | +0.091 |
Tooth | +0.088 |
Neg logit contributions | |
ower | -0.161 |
aged | -0.159 |
its | -0.159 |
apy | -0.154 |
ot | -0.152 |
Token | wanted |
Token ID | 2227 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
ranger | +0.065 |
years | +0.062 |
clearing | +0.061 |
since | +0.061 |
café | +0.060 |
Neg logit contributions | |
its | -0.062 |
ower | -0.057 |
apy | -0.055 |
isel | -0.055 |
ikes | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
aged | +0.060 |
apy | +0.058 |
its | +0.057 |
ower | +0.054 |
ubs | +0.053 |
Neg logit contributions | |
clearing | -0.069 |
ranger | -0.069 |
grizz | -0.069 |
Fairy | -0.067 |
enclosure | -0.067 |
Token | go |
Token ID | 467 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
ranger | +0.048 |
café | +0.045 |
years | +0.045 |
Tooth | +0.044 |
dentist | +0.044 |
Neg logit contributions | |
its | -0.049 |
ower | -0.046 |
aged | -0.044 |
ikes | -0.043 |
isel | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
ranger | +0.050 |
years | +0.048 |
since | +0.047 |
clearing | +0.046 |
Tooth | +0.046 |
Neg logit contributions | |
its | -0.061 |
ower | -0.057 |
apy | -0.056 |
aged | -0.056 |
ikes | -0.056 |
Token | church |
Token ID | 4928 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ranger | +0.049 |
years | +0.046 |
since | +0.045 |
clearing | +0.043 |
Fairy | +0.042 |
Neg logit contributions | |
its | -0.075 |
apy | -0.069 |
ower | -0.068 |
ikes | -0.067 |
isel | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
ranger | +0.226 |
grizz | +0.212 |
clearing | +0.210 |
Tooth | +0.208 |
Fairy | +0.206 |
Neg logit contributions | |
its | -0.294 |
ower | -0.294 |
ikes | -0.281 |
aged | -0.277 |
apy | -0.267 |
Token | She |
Token ID | 1375 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
ranger | +0.046 |
since | +0.042 |
years | +0.041 |
clearing | +0.041 |
café | +0.040 |
Neg logit contributions | |
its | -0.112 |
ower | -0.105 |
apy | -0.103 |
isel | -0.103 |
aged | -0.102 |
Token | got |
Token ID | 1392 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
years | +0.067 |
ranger | +0.067 |
since | +0.063 |
clearing | +0.063 |
café | +0.062 |
Neg logit contributions | |
its | -0.111 |
ower | -0.106 |
isel | -0.102 |
ikes | -0.102 |
apy | -0.100 |
Token | up |
Token ID | 510 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
its | +0.071 |
ower | +0.066 |
apy | +0.065 |
isel | +0.065 |
aged | +0.064 |
Neg logit contributions | |
ranger | -0.041 |
years | -0.039 |
clearing | -0.037 |
since | -0.037 |
café | -0.036 |
Token | early |
Token ID | 1903 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ranger | +0.085 |
clearing | +0.079 |
years | +0.076 |
since | +0.076 |
Prince | +0.076 |
Neg logit contributions | |
its | -0.117 |
ower | -0.111 |
aged | -0.109 |
apy | -0.108 |
ikes | -0.105 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
its | +0.073 |
ower | +0.066 |
apy | +0.066 |
isel | +0.066 |
ikes | +0.065 |
Neg logit contributions | |
ranger | -0.048 |
banquet | -0.045 |
café | -0.044 |
years | -0.044 |
clearing | -0.043 |
Token | M |
Token ID | 44 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
ranger | +0.043 |
years | +0.042 |
since | +0.041 |
Tooth | +0.040 |
banquet | +0.039 |
Neg logit contributions | |
its | -0.071 |
ower | -0.064 |
ikes | -0.063 |
apy | -0.063 |
oom | -0.061 |
Token | ila |
Token ID | 10102 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
ranger | +0.045 |
clearing | +0.044 |
since | +0.043 |
Prince | +0.041 |
Fairy | +0.040 |
Neg logit contributions | |
its | -0.055 |
apy | -0.049 |
ower | -0.048 |
iggle | -0.048 |
isel | -0.046 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ranger | +0.056 |
clearing | +0.054 |
years | +0.051 |
Tooth | +0.051 |
banquet | +0.050 |
Neg logit contributions | |
its | -0.074 |
aged | -0.068 |
ower | -0.068 |
apy | -0.065 |
isel | -0.064 |
Token | up |
Token ID | 510 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
ranger | +0.025 |
years | +0.024 |
since | +0.024 |
clearing | +0.024 |
Tooth | +0.023 |
Neg logit contributions | |
its | -0.026 |
isel | -0.023 |
ower | -0.023 |
apy | -0.023 |
aged | -0.022 |
Token | early |
Token ID | 1903 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ranger | +0.093 |
years | +0.091 |
since | +0.089 |
clearing | +0.087 |
café | +0.084 |
Neg logit contributions | |
its | -0.168 |
ower | -0.156 |
isel | -0.154 |
apy | -0.153 |
ikes | -0.152 |
Token | on |
Token ID | 319 |
Feature activation | +3.71e-04 |
Pos logit contributions | |
ranger | +0.211 |
years | +0.193 |
clearing | +0.187 |
Tooth | +0.184 |
café | +0.183 |
Neg logit contributions | |
its | -0.312 |
ower | -0.309 |
aged | -0.296 |
apy | -0.294 |
ikes | -0.291 |
Token | her |
Token ID | 607 |
Feature activation | +9.06e-03 |
Pos logit contributions | |
ranger | +0.001 |
years | +0.000 |
clearing | +0.000 |
since | +0.000 |
grizz | +0.000 |
Neg logit contributions | |
its | -0.001 |
apy | -0.001 |
ower | -0.001 |
aged | -0.001 |
ikes | -0.001 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ranger | +0.014 |
years | +0.013 |
since | +0.013 |
clearing | +0.013 |
café | +0.013 |
Neg logit contributions | |
its | -0.017 |
ower | -0.016 |
isel | -0.016 |
apy | -0.016 |
aged | -0.015 |
Token | morning |
Token ID | 3329 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
ranger | +0.028 |
grizz | +0.025 |
clearing | +0.025 |
cal | +0.024 |
years | +0.024 |
Neg logit contributions | |
ower | -0.035 |
its | -0.033 |
ikes | -0.033 |
apy | -0.032 |
iggle | -0.032 |
Token | feeling |
Token ID | 4203 |
Feature activation | +9.10e-03 |
Pos logit contributions | |
ranger | +0.096 |
clearing | +0.085 |
years | +0.083 |
grizz | +0.082 |
Tooth | +0.080 |
Neg logit contributions | |
ower | -0.134 |
its | -0.134 |
apy | -0.128 |
aged | -0.127 |
ikes | -0.123 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
its | +0.091 |
ower | +0.090 |
apy | +0.088 |
isel | +0.085 |
aged | +0.083 |
Neg logit contributions | |
ranger | -0.072 |
years | -0.072 |
since | -0.069 |
clearing | -0.067 |
Tooth | -0.066 |
Token | named |
Token ID | 3706 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
ranger | +0.039 |
years | +0.034 |
clearing | +0.034 |
since | +0.033 |
Tooth | +0.033 |
Neg logit contributions | |
its | -0.107 |
ower | -0.101 |
apy | -0.101 |
aged | -0.100 |
isel | -0.099 |
Token | Jenny |
Token ID | 28437 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ranger | +0.057 |
since | +0.054 |
years | +0.053 |
clearing | +0.051 |
café | +0.050 |
Neg logit contributions | |
its | -0.134 |
ower | -0.126 |
isel | -0.124 |
ikes | -0.122 |
apy | -0.121 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ranger | +0.041 |
years | +0.039 |
since | +0.038 |
clearing | +0.037 |
café | +0.037 |
Neg logit contributions | |
its | -0.065 |
ower | -0.060 |
apy | -0.059 |
isel | -0.059 |
ikes | -0.059 |
Token | up |
Token ID | 510 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
ranger | +0.024 |
years | +0.023 |
clearing | +0.022 |
since | +0.022 |
Tooth | +0.022 |
Neg logit contributions | |
its | -0.022 |
ower | -0.020 |
apy | -0.020 |
isel | -0.020 |
aged | -0.020 |
Token | early |
Token ID | 1903 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ranger | +0.101 |
years | +0.095 |
clearing | +0.093 |
since | +0.092 |
café | +0.090 |
Neg logit contributions | |
its | -0.162 |
ower | -0.152 |
apy | -0.148 |
aged | -0.147 |
isel | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
ranger | +0.224 |
years | +0.203 |
clearing | +0.202 |
Fairy | +0.200 |
Prince | +0.198 |
Neg logit contributions | |
ower | -0.293 |
its | -0.289 |
aged | -0.278 |
apy | -0.271 |
ikes | -0.270 |
Token | She |
Token ID | 1375 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
ranger | +0.035 |
years | +0.032 |
since | +0.032 |
clearing | +0.031 |
café | +0.031 |
Neg logit contributions | |
its | -0.077 |
ower | -0.072 |
apy | -0.071 |
isel | -0.070 |
aged | -0.070 |
Token | was |
Token ID | 373 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
ranger | +0.065 |
years | +0.060 |
clearing | +0.060 |
since | +0.059 |
café | +0.058 |
Neg logit contributions | |
its | -0.083 |
ower | -0.077 |
apy | -0.076 |
aged | -0.075 |
isel | -0.074 |
Token | so |
Token ID | 523 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
ranger | +0.010 |
years | +0.010 |
clearing | +0.009 |
since | +0.009 |
café | +0.009 |
Neg logit contributions | |
its | -0.015 |
ower | -0.014 |
isel | -0.014 |
ikes | -0.014 |
apy | -0.014 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
its | +0.068 |
isel | +0.065 |
ikes | +0.064 |
ged | +0.061 |
uing | +0.061 |
Neg logit contributions | |
years | -0.033 |
ranger | -0.029 |
café | -0.028 |
banquet | -0.028 |
Mrs | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
its | +0.041 |
ower | +0.038 |
apy | +0.037 |
ikes | +0.037 |
iggle | +0.036 |
Neg logit contributions | |
ranger | -0.031 |
Tooth | -0.029 |
café | -0.029 |
clearing | -0.028 |
dentist | -0.028 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
its | +0.053 |
apy | +0.051 |
ower | +0.049 |
isel | +0.049 |
ikes | +0.049 |
Neg logit contributions | |
ranger | -0.035 |
café | -0.032 |
years | -0.032 |
banquet | -0.031 |
cafe | -0.031 |
Token | Jack |
Token ID | 14295 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
ranger | +0.040 |
years | +0.038 |
since | +0.037 |
Tooth | +0.036 |
dentist | +0.035 |
Neg logit contributions | |
its | -0.061 |
ower | -0.055 |
apy | -0.055 |
ikes | -0.054 |
oom | -0.053 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
its | +0.020 |
ower | +0.019 |
aged | +0.018 |
apy | +0.018 |
isel | +0.018 |
Neg logit contributions | |
ranger | -0.017 |
clearing | -0.015 |
years | -0.015 |
Tooth | -0.015 |
café | -0.015 |
Token | up |
Token ID | 510 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
ranger | +0.019 |
years | +0.018 |
since | +0.018 |
clearing | +0.018 |
Prince | +0.017 |
Neg logit contributions | |
its | -0.019 |
ower | -0.017 |
isel | -0.017 |
apy | -0.017 |
aged | -0.016 |
Token | early |
Token ID | 1903 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ranger | +0.096 |
years | +0.090 |
clearing | +0.088 |
since | +0.087 |
café | +0.085 |
Neg logit contributions | |
its | -0.169 |
ower | -0.158 |
apy | -0.154 |
isel | -0.153 |
aged | -0.153 |
Token | in |
Token ID | 287 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
ranger | +0.220 |
years | +0.200 |
clearing | +0.193 |
Tooth | +0.193 |
café | +0.191 |
Neg logit contributions | |
ower | -0.298 |
its | -0.294 |
aged | -0.282 |
apy | -0.280 |
ikes | -0.279 |
Token | the |
Token ID | 262 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
ranger | +0.028 |
years | +0.024 |
Tooth | +0.024 |
since | +0.024 |
Fairy | +0.024 |
Neg logit contributions | |
its | -0.036 |
apy | -0.035 |
isel | -0.034 |
ower | -0.033 |
aged | -0.033 |
Token | morning |
Token ID | 3329 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
ranger | +0.088 |
years | +0.083 |
since | +0.080 |
indeed | +0.079 |
Fairy | +0.077 |
Neg logit contributions | |
apy | -0.088 |
ower | -0.087 |
its | -0.083 |
ikes | -0.079 |
aged | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
ranger | +0.096 |
grizz | +0.082 |
years | +0.081 |
clearing | +0.080 |
dentist | +0.079 |
Neg logit contributions | |
ower | -0.125 |
its | -0.121 |
apy | -0.119 |
aged | -0.115 |
ikes | -0.113 |
Token | he |
Token ID | 339 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ranger | +0.067 |
years | +0.063 |
clearing | +0.062 |
since | +0.061 |
Tooth | +0.060 |
Neg logit contributions | |
its | -0.084 |
ower | -0.078 |
apy | -0.077 |
aged | -0.076 |
isel | -0.075 |
Token | bear |
Token ID | 6842 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
Tooth | +0.086 |
clearing | +0.085 |
ranger | +0.084 |
grizz | +0.083 |
Prince | +0.083 |
Neg logit contributions | |
ower | -0.107 |
its | -0.106 |
ikes | -0.100 |
aged | -0.100 |
apy | -0.098 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
ranger | +0.042 |
years | +0.041 |
clearing | +0.040 |
Tooth | +0.039 |
café | +0.039 |
Neg logit contributions | |
its | -0.067 |
aged | -0.063 |
ower | -0.063 |
apy | -0.062 |
ikes | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
its | +0.002 |
apy | +0.002 |
aged | +0.002 |
ower | +0.002 |
ikes | +0.002 |
Neg logit contributions | |
clearing | -0.001 |
ranger | -0.001 |
years | -0.001 |
café | -0.001 |
Tooth | -0.001 |
Token | wake |
Token ID | 7765 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
ranger | +0.068 |
years | +0.063 |
clearing | +0.062 |
café | +0.061 |
since | +0.061 |
Neg logit contributions | |
its | -0.066 |
ower | -0.064 |
aged | -0.060 |
ikes | -0.059 |
apy | -0.059 |
Token | up |
Token ID | 510 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
ranger | +0.116 |
years | +0.110 |
clearing | +0.108 |
since | +0.108 |
café | +0.106 |
Neg logit contributions | |
its | -0.122 |
ower | -0.112 |
apy | -0.109 |
isel | -0.108 |
aged | -0.107 |
Token | early |
Token ID | 1903 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ranger | +0.100 |
clearing | +0.093 |
years | +0.090 |
café | +0.088 |
Tooth | +0.088 |
Neg logit contributions | |
its | -0.153 |
ower | -0.146 |
apy | -0.144 |
aged | -0.139 |
ikes | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
ranger | +0.213 |
clearing | +0.197 |
years | +0.194 |
Fairy | +0.188 |
enclosure | +0.187 |
Neg logit contributions | |
its | -0.286 |
ower | -0.284 |
ikes | -0.269 |
aged | -0.263 |
iggle | -0.261 |
Token | He |
Token ID | 679 |
Feature activation | +8.97e-03 |
Pos logit contributions | |
years | +0.021 |
ranger | +0.020 |
banquet | +0.020 |
tale | +0.020 |
Tooth | +0.019 |
Neg logit contributions | |
apy | -0.026 |
its | -0.025 |
ower | -0.025 |
ikes | -0.024 |
aged | -0.024 |
Token | shook |
Token ID | 14682 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
ranger | +0.014 |
years | +0.014 |
since | +0.013 |
Prince | +0.013 |
Tooth | +0.013 |
Neg logit contributions | |
its | -0.016 |
apy | -0.015 |
aged | -0.014 |
ower | -0.014 |
isel | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
ranger | +0.052 |
years | +0.050 |
clearing | +0.049 |
since | +0.049 |
café | +0.047 |
Neg logit contributions | |
its | -0.085 |
ower | -0.079 |
apy | -0.076 |
isel | -0.076 |
ikes | -0.076 |
Token | head |
Token ID | 1182 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
its | +0.036 |
ower | +0.033 |
apy | +0.031 |
aged | +0.031 |
isel | +0.031 |
Neg logit contributions | |
ranger | -0.042 |
years | -0.040 |
clearing | -0.039 |
since | -0.039 |
café | -0.038 |
Token | surprise |
Token ID | 5975 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
its | +0.029 |
ower | +0.027 |
ikes | +0.025 |
isel | +0.025 |
apy | +0.025 |
Neg logit contributions | |
ranger | -0.023 |
since | -0.023 |
years | -0.022 |
clearing | -0.022 |
Fairy | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
its | +0.055 |
ower | +0.051 |
ikes | +0.049 |
apy | +0.049 |
aged | +0.048 |
Neg logit contributions | |
clearing | -0.033 |
ranger | -0.032 |
years | -0.032 |
Tooth | -0.031 |
since | -0.030 |
Token | He |
Token ID | 679 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
its | +0.014 |
ower | +0.013 |
apy | +0.013 |
isel | +0.013 |
aged | +0.013 |
Neg logit contributions | |
ranger | -0.007 |
years | -0.007 |
clearing | -0.007 |
since | -0.007 |
café | -0.007 |
Token | threw |
Token ID | 9617 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
its | +0.021 |
aged | +0.019 |
apy | +0.018 |
isel | +0.018 |
ower | +0.017 |
Neg logit contributions | |
clearing | -0.023 |
ranger | -0.022 |
since | -0.022 |
Fairy | -0.022 |
Prince | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
its | +0.062 |
ower | +0.060 |
apy | +0.057 |
ikes | +0.057 |
aged | +0.057 |
Neg logit contributions | |
ranger | -0.034 |
years | -0.031 |
since | -0.030 |
clearing | -0.030 |
Prince | -0.029 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
its | +0.046 |
ikes | +0.043 |
ower | +0.042 |
aged | +0.042 |
oving | +0.040 |
Neg logit contributions | |
ranger | -0.043 |
clearing | -0.040 |
café | -0.039 |
Prince | -0.038 |
Tooth | -0.038 |
Token | rum |
Token ID | 6582 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
apy | +0.299 |
its | +0.297 |
inters | +0.296 |
ower | +0.286 |
ikes | +0.272 |
Neg logit contributions | |
years | -0.406 |
ranger | -0.375 |
mother | -0.363 |
since | -0.354 |
grizz | -0.342 |
Token | . |
Token ID | 13 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
its | +0.143 |
ower | +0.134 |
apy | +0.131 |
isel | +0.131 |
aged | +0.130 |
Neg logit contributions | |
ranger | -0.067 |
years | -0.063 |
since | -0.060 |
clearing | -0.060 |
café | -0.058 |
Token | He |
Token ID | 679 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
its | +0.019 |
ower | +0.018 |
apy | +0.018 |
isel | +0.017 |
aged | +0.017 |
Neg logit contributions | |
ranger | -0.009 |
years | -0.008 |
clearing | -0.008 |
since | -0.008 |
café | -0.007 |
Token | kicked |
Token ID | 12165 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
its | +0.019 |
aged | +0.017 |
apy | +0.017 |
ower | +0.017 |
isel | +0.017 |
Neg logit contributions | |
ranger | -0.020 |
clearing | -0.019 |
since | -0.019 |
years | -0.019 |
Fairy | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +6.79e-03 |
Pos logit contributions | |
its | +0.140 |
ower | +0.134 |
apy | +0.130 |
isel | +0.128 |
ikes | +0.128 |
Neg logit contributions | |
ranger | -0.060 |
years | -0.056 |
since | -0.055 |
clearing | -0.053 |
Prince | -0.051 |
Token | stubborn |
Token ID | 24444 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
ranger | +0.050 |
years | +0.048 |
since | +0.047 |
clearing | +0.047 |
café | +0.046 |
Neg logit contributions | |
its | -0.056 |
ower | -0.051 |
aged | -0.050 |
apy | -0.050 |
isel | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
clearing | +0.010 |
ranger | +0.010 |
Tooth | +0.009 |
Fairy | +0.009 |
banquet | +0.009 |
Neg logit contributions | |
its | -0.016 |
ower | -0.014 |
aged | -0.014 |
ikes | -0.014 |
apy | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
its | +0.029 |
ower | +0.027 |
apy | +0.027 |
aged | +0.026 |
isel | +0.026 |
Neg logit contributions | |
ranger | -0.016 |
years | -0.014 |
clearing | -0.014 |
since | -0.014 |
café | -0.014 |
Token | throws |
Token ID | 12542 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
ranger | +0.022 |
clearing | +0.020 |
since | +0.020 |
years | +0.020 |
café | +0.020 |
Neg logit contributions | |
its | -0.023 |
ower | -0.020 |
apy | -0.020 |
isel | -0.019 |
aged | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
its | +0.099 |
ower | +0.098 |
ikes | +0.093 |
isel | +0.093 |
apy | +0.092 |
Neg logit contributions | |
ranger | -0.047 |
years | -0.043 |
since | -0.042 |
clearing | -0.042 |
Prince | -0.041 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
its | +0.046 |
ikes | +0.045 |
aged | +0.044 |
ower | +0.043 |
oving | +0.042 |
Neg logit contributions | |
ranger | -0.061 |
café | -0.057 |
clearing | -0.057 |
cafe | -0.056 |
Prince | -0.055 |
Token | rum |
Token ID | 6582 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
inters | +0.308 |
apy | +0.307 |
its | +0.295 |
ower | +0.291 |
isel | +0.284 |
Neg logit contributions | |
years | -0.399 |
mother | -0.357 |
ranger | -0.352 |
since | -0.336 |
Fairy | -0.326 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
its | +0.154 |
isel | +0.145 |
ower | +0.145 |
apy | +0.142 |
aged | +0.140 |
Neg logit contributions | |
ranger | -0.064 |
years | -0.061 |
since | -0.058 |
clearing | -0.055 |
Tooth | -0.053 |
Token | She |
Token ID | 1375 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
its | +0.039 |
ower | +0.036 |
apy | +0.036 |
isel | +0.035 |
aged | +0.035 |
Neg logit contributions | |
ranger | -0.018 |
years | -0.017 |
clearing | -0.016 |
since | -0.016 |
café | -0.016 |
Token | kicks |
Token ID | 17364 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
ranger | +0.023 |
clearing | +0.022 |
since | +0.022 |
years | +0.021 |
Fairy | +0.021 |
Neg logit contributions | |
its | -0.022 |
apy | -0.018 |
isel | -0.018 |
aged | -0.018 |
ower | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -8.52e-03 |
Pos logit contributions | |
its | +0.147 |
ower | +0.143 |
isel | +0.139 |
apy | +0.138 |
aged | +0.137 |
Neg logit contributions | |
ranger | -0.058 |
years | -0.055 |
since | -0.054 |
Prince | -0.050 |
clearing | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ranger | +0.022 |
clearing | +0.021 |
Tooth | +0.020 |
Fairy | +0.020 |
years | +0.019 |
Neg logit contributions | |
its | -0.044 |
ower | -0.042 |
aged | -0.040 |
apy | -0.040 |
ikes | -0.040 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
its | +0.038 |
ower | +0.036 |
ikes | +0.036 |
isel | +0.035 |
aged | +0.034 |
Neg logit contributions | |
ranger | -0.027 |
years | -0.026 |
since | -0.026 |
Ms | -0.024 |
indeed | -0.023 |
Token | 's |
Token ID | 338 |
Feature activation | +6.02e-03 |
Pos logit contributions | |
its | +0.097 |
ower | +0.090 |
apy | +0.088 |
isel | +0.088 |
aged | +0.087 |
Neg logit contributions | |
ranger | -0.055 |
years | -0.052 |
clearing | -0.051 |
since | -0.051 |
café | -0.049 |
Token | face |
Token ID | 1986 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
ranger | +0.009 |
years | +0.009 |
since | +0.008 |
clearing | +0.008 |
Tooth | +0.008 |
Neg logit contributions | |
its | -0.012 |
ower | -0.011 |
ikes | -0.011 |
isel | -0.011 |
apy | -0.010 |
Token | sc |
Token ID | 629 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
its | +0.008 |
isel | +0.007 |
ower | +0.007 |
ikes | +0.007 |
utes | +0.007 |
Neg logit contributions | |
years | -0.004 |
ranger | -0.004 |
since | -0.004 |
café | -0.003 |
indeed | -0.003 |
Token | run |
Token ID | 5143 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
its | +0.096 |
ower | +0.088 |
isel | +0.087 |
aged | +0.085 |
apy | +0.085 |
Neg logit contributions | |
ranger | -0.071 |
years | -0.066 |
enclosure | -0.066 |
since | -0.065 |
grizz | -0.062 |
Token | ched |
Token ID | 1740 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
ower | +0.350 |
its | +0.339 |
isel | +0.331 |
utes | +0.306 |
iggle | +0.302 |
Neg logit contributions | |
� | -0.350 |
since | -0.345 |
years | -0.335 |
ranger | -0.332 |
Mrs | -0.301 |
Token | up |
Token ID | 510 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
its | +0.173 |
ower | +0.161 |
isel | +0.159 |
apy | +0.157 |
ikes | +0.154 |
Neg logit contributions | |
ranger | -0.104 |
years | -0.100 |
since | -0.098 |
clearing | -0.094 |
Prince | -0.092 |
Token | as |
Token ID | 355 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
ranger | +0.019 |
clearing | +0.018 |
Tooth | +0.018 |
café | +0.018 |
Fairy | +0.018 |
Neg logit contributions | |
its | -0.032 |
ower | -0.030 |
apy | -0.030 |
aged | -0.030 |
ikes | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
its | +0.153 |
ower | +0.143 |
ikes | +0.138 |
aged | +0.138 |
isel | +0.138 |
Neg logit contributions | |
ranger | -0.096 |
years | -0.091 |
since | -0.088 |
clearing | -0.087 |
Tooth | -0.085 |
Token | ate |
Token ID | 15063 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ranger | +0.006 |
years | +0.006 |
since | +0.005 |
clearing | +0.005 |
café | +0.005 |
Neg logit contributions | |
its | -0.008 |
ower | -0.008 |
apy | -0.007 |
isel | -0.007 |
ikes | -0.007 |
Token | temper |
Token ID | 4124 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
its | +0.073 |
apy | +0.072 |
ikes | +0.069 |
ower | +0.068 |
isel | +0.067 |
Neg logit contributions | |
ranger | -0.062 |
years | -0.061 |
cave | -0.056 |
dentist | -0.055 |
café | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
its | +0.083 |
ower | +0.078 |
apy | +0.077 |
isel | +0.077 |
ikes | +0.076 |
Neg logit contributions | |
ranger | -0.036 |
years | -0.034 |
since | -0.033 |
clearing | -0.031 |
café | -0.031 |
Token | often |
Token ID | 1690 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
its | +0.039 |
ower | +0.036 |
isel | +0.035 |
ikes | +0.035 |
apy | +0.035 |
Neg logit contributions | |
ranger | -0.023 |
years | -0.023 |
since | -0.022 |
clearing | -0.021 |
café | -0.021 |
Token | threw |
Token ID | 9617 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ranger | +0.007 |
years | +0.006 |
since | +0.006 |
clearing | +0.006 |
café | +0.006 |
Neg logit contributions | |
its | -0.010 |
ower | -0.009 |
ikes | -0.009 |
isel | -0.009 |
apy | -0.009 |
Token | temper |
Token ID | 4124 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
its | +0.041 |
ower | +0.039 |
apy | +0.037 |
ikes | +0.037 |
isel | +0.037 |
Neg logit contributions | |
years | -0.027 |
ranger | -0.026 |
since | -0.026 |
clearing | -0.025 |
Prince | -0.025 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
its | +0.070 |
ower | +0.066 |
apy | +0.064 |
isel | +0.064 |
ikes | +0.063 |
Neg logit contributions | |
ranger | -0.065 |
years | -0.064 |
since | -0.062 |
café | -0.058 |
clearing | -0.058 |
Token | rums |
Token ID | 45241 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
apy | +0.319 |
inters | +0.312 |
its | +0.309 |
ower | +0.303 |
isel | +0.288 |
Neg logit contributions | |
years | -0.402 |
mother | -0.356 |
since | -0.327 |
Fairy | -0.318 |
indeed | -0.316 |
Token | . |
Token ID | 13 |
Feature activation | +9.14e-03 |
Pos logit contributions | |
its | +0.099 |
isel | +0.093 |
apy | +0.090 |
ower | +0.090 |
aged | +0.087 |
Neg logit contributions | |
since | -0.038 |
years | -0.038 |
ranger | -0.037 |
Tooth | -0.032 |
Prince | -0.032 |
Token | One |
Token ID | 1881 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
ranger | +0.011 |
years | +0.010 |
clearing | +0.010 |
since | +0.010 |
Tooth | +0.009 |
Neg logit contributions | |
its | -0.021 |
ower | -0.019 |
apy | -0.019 |
isel | -0.019 |
ikes | -0.019 |
Token | day |
Token ID | 1110 |
Feature activation | -2.77e-04 |
Pos logit contributions | |
ranger | +0.014 |
years | +0.013 |
clearing | +0.013 |
since | +0.013 |
Tooth | +0.013 |
Neg logit contributions | |
its | -0.011 |
ower | -0.010 |
apy | -0.010 |
aged | -0.010 |
isel | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
its | +0.001 |
apy | +0.001 |
ower | +0.001 |
aged | +0.001 |
isel | +0.001 |
Neg logit contributions | |
ranger | -0.000 |
years | -0.000 |
clearing | -0.000 |
Tooth | -0.000 |
café | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
ranger | +0.017 |
years | +0.016 |
since | +0.016 |
Prince | +0.015 |
clearing | +0.014 |
Neg logit contributions | |
its | -0.039 |
ower | -0.038 |
ikes | -0.037 |
apy | -0.035 |
isel | -0.035 |
Token | feet |
Token ID | 3625 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
its | +0.070 |
isel | +0.063 |
apy | +0.063 |
ower | +0.063 |
ikes | +0.062 |
Neg logit contributions | |
ranger | -0.068 |
years | -0.064 |
enclosure | -0.060 |
clearing | -0.060 |
café | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
its | +0.143 |
ower | +0.135 |
apy | +0.133 |
isel | +0.132 |
aged | +0.131 |
Neg logit contributions | |
ranger | -0.052 |
years | -0.048 |
since | -0.047 |
clearing | -0.045 |
café | -0.044 |
Token | threw |
Token ID | 9617 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
ranger | +0.005 |
years | +0.004 |
clearing | +0.004 |
since | +0.004 |
Tooth | +0.004 |
Neg logit contributions | |
its | -0.005 |
apy | -0.005 |
aged | -0.005 |
ower | -0.005 |
isel | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
its | +0.048 |
ower | +0.047 |
ikes | +0.044 |
apy | +0.044 |
aged | +0.044 |
Neg logit contributions | |
ranger | -0.029 |
years | -0.027 |
clearing | -0.026 |
since | -0.026 |
Prince | -0.025 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
its | +0.040 |
ikes | +0.038 |
ower | +0.037 |
aged | +0.037 |
oving | +0.035 |
Neg logit contributions | |
ranger | -0.039 |
clearing | -0.036 |
café | -0.035 |
cafe | -0.033 |
Prince | -0.033 |
Token | rum |
Token ID | 6582 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
apy | +0.315 |
inters | +0.304 |
its | +0.291 |
ower | +0.290 |
isel | +0.278 |
Neg logit contributions | |
years | -0.391 |
mother | -0.353 |
ranger | -0.345 |
since | -0.327 |
Lion | -0.321 |
Token | . |
Token ID | 13 |
Feature activation | -8.34e-03 |
Pos logit contributions | |
its | +0.141 |
ower | +0.131 |
isel | +0.131 |
apy | +0.129 |
ikes | +0.127 |
Neg logit contributions | |
ranger | -0.057 |
years | -0.053 |
since | -0.051 |
clearing | -0.048 |
café | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -2.68e-04 |
Pos logit contributions | |
its | +0.019 |
apy | +0.018 |
ower | +0.017 |
aged | +0.017 |
isel | +0.017 |
Neg logit contributions | |
years | -0.010 |
ranger | -0.010 |
since | -0.009 |
clearing | -0.009 |
café | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
its | +0.001 |
ower | +0.001 |
aged | +0.001 |
isel | +0.001 |
apy | +0.001 |
Neg logit contributions | |
ranger | -0.000 |
years | -0.000 |
clearing | -0.000 |
since | -0.000 |
café | -0.000 |
Token | " |
Token ID | 1 |
Feature activation | -9.23e-03 |
Pos logit contributions | |
ranger | +0.015 |
banquet | +0.015 |
Fairy | +0.015 |
Tooth | +0.015 |
years | +0.015 |
Neg logit contributions | |
its | -0.020 |
apy | -0.019 |
ower | -0.018 |
aged | -0.018 |
isel | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
clearing | +0.024 |
ranger | +0.023 |
banquet | +0.022 |
grizz | +0.022 |
Tooth | +0.022 |
Neg logit contributions | |
its | -0.039 |
ower | -0.036 |
ikes | -0.036 |
iggle | -0.034 |
aged | -0.034 |
Token | they |
Token ID | 484 |
Feature activation | -9.78e-03 |
Pos logit contributions | |
its | +0.060 |
aged | +0.058 |
apy | +0.058 |
isel | +0.054 |
ower | +0.054 |
Neg logit contributions | |
clearing | -0.044 |
years | -0.044 |
ranger | -0.043 |
enclosure | -0.041 |
café | -0.041 |
Token | shared |
Token ID | 4888 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
its | +0.020 |
ower | +0.019 |
ikes | +0.018 |
apy | +0.018 |
isel | +0.018 |
Neg logit contributions | |
ranger | -0.014 |
years | -0.013 |
since | -0.013 |
clearing | -0.012 |
Tooth | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
its | +0.046 |
ower | +0.042 |
apy | +0.041 |
aged | +0.040 |
isel | +0.040 |
Neg logit contributions | |
ranger | -0.041 |
years | -0.039 |
clearing | -0.039 |
since | -0.038 |
café | -0.038 |
Token | cr |
Token ID | 1067 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
its | +0.122 |
ower | +0.111 |
apy | +0.110 |
isel | +0.109 |
aged | +0.109 |
Neg logit contributions | |
ranger | -0.103 |
years | -0.099 |
clearing | -0.097 |
Tooth | -0.096 |
since | -0.096 |
Token | ay |
Token ID | 323 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
its | +0.111 |
apy | +0.103 |
aged | +0.102 |
isel | +0.101 |
ower | +0.101 |
Neg logit contributions | |
ranger | -0.142 |
years | -0.142 |
since | -0.138 |
Fairy | -0.136 |
Tooth | -0.136 |
Token | ons |
Token ID | 684 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
its | +0.376 |
isel | +0.367 |
ower | +0.361 |
inters | +0.355 |
aged | +0.354 |
Neg logit contributions | |
years | -0.314 |
ranger | -0.300 |
mother | -0.290 |
Fairy | -0.282 |
Tooth | -0.277 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
its | +0.180 |
ower | +0.173 |
apy | +0.167 |
aged | +0.165 |
ikes | +0.163 |
Neg logit contributions | |
clearing | -0.142 |
grizz | -0.135 |
Tooth | -0.135 |
ranger | -0.133 |
café | -0.131 |
Token | They |
Token ID | 1119 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
its | +0.057 |
ower | +0.052 |
apy | +0.052 |
aged | +0.050 |
ikes | +0.049 |
Neg logit contributions | |
ranger | -0.043 |
years | -0.043 |
since | -0.042 |
clearing | -0.041 |
Fairy | -0.040 |
Token | drew |
Token ID | 9859 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
its | +0.030 |
ower | +0.028 |
apy | +0.027 |
isel | +0.027 |
aged | +0.027 |
Neg logit contributions | |
ranger | -0.024 |
years | -0.023 |
clearing | -0.022 |
since | -0.022 |
café | -0.022 |
Token | nice |
Token ID | 3621 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
its | +0.064 |
ower | +0.060 |
apy | +0.058 |
isel | +0.058 |
aged | +0.058 |
Neg logit contributions | |
ranger | -0.045 |
years | -0.042 |
clearing | -0.041 |
since | -0.041 |
café | -0.040 |
Token | paws |
Token ID | 49193 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
its | +0.062 |
isel | +0.057 |
ower | +0.056 |
ikes | +0.056 |
apy | +0.054 |
Neg logit contributions | |
years | -0.055 |
ranger | -0.055 |
Tooth | -0.051 |
clearing | -0.051 |
café | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
its | +0.122 |
isel | +0.112 |
ower | +0.112 |
apy | +0.112 |
ikes | +0.109 |
Neg logit contributions | |
ranger | -0.046 |
since | -0.046 |
years | -0.043 |
clearing | -0.039 |
café | -0.038 |
Token | So |
Token ID | 1406 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
ranger | +0.011 |
years | +0.011 |
since | +0.010 |
clearing | +0.010 |
Fairy | +0.010 |
Neg logit contributions | |
its | -0.018 |
ower | -0.017 |
ikes | -0.017 |
apy | -0.017 |
isel | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
ranger | +0.009 |
café | +0.008 |
cafe | +0.008 |
enclosure | +0.008 |
Tooth | +0.008 |
Neg logit contributions | |
apy | -0.010 |
aged | -0.010 |
isel | -0.010 |
its | -0.009 |
ower | -0.009 |
Token | sc |
Token ID | 629 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
its | +0.009 |
ower | +0.008 |
aged | +0.008 |
apy | +0.008 |
isel | +0.008 |
Neg logit contributions | |
ranger | -0.009 |
years | -0.009 |
clearing | -0.009 |
since | -0.009 |
Tooth | -0.008 |
Token | run |
Token ID | 5143 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
its | +0.096 |
ower | +0.090 |
ikes | +0.086 |
apy | +0.084 |
isel | +0.084 |
Neg logit contributions | |
ranger | -0.072 |
years | -0.066 |
since | -0.065 |
clearing | -0.064 |
enclosure | -0.063 |
Token | ched |
Token ID | 1740 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
ower | +0.359 |
its | +0.342 |
ikes | +0.315 |
isel | +0.310 |
apy | +0.304 |
Neg logit contributions | |
since | -0.354 |
years | -0.342 |
ranger | -0.338 |
clearing | -0.326 |
� | -0.325 |
Token | up |
Token ID | 510 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
its | +0.187 |
ower | +0.177 |
ikes | +0.170 |
apy | +0.167 |
isel | +0.166 |
Neg logit contributions | |
years | -0.074 |
since | -0.073 |
Prince | -0.072 |
ranger | -0.072 |
Tooth | -0.070 |
Token | his |
Token ID | 465 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
ranger | +0.028 |
clearing | +0.026 |
café | +0.026 |
years | +0.026 |
banquet | +0.025 |
Neg logit contributions | |
its | -0.048 |
aged | -0.045 |
ower | -0.045 |
apy | -0.045 |
isel | -0.044 |
Token | face |
Token ID | 1986 |
Feature activation | +7.62e-03 |
Pos logit contributions | |
its | +0.047 |
isel | +0.043 |
ikes | +0.041 |
ower | +0.041 |
apy | +0.040 |
Neg logit contributions | |
ranger | -0.035 |
years | -0.034 |
clearing | -0.033 |
since | -0.032 |
Tooth | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ranger | +0.007 |
years | +0.007 |
since | +0.007 |
clearing | +0.006 |
café | +0.006 |
Neg logit contributions | |
its | -0.019 |
ower | -0.018 |
apy | -0.017 |
isel | -0.017 |
aged | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
its | +0.063 |
ower | +0.059 |
apy | +0.058 |
aged | +0.057 |
isel | +0.057 |
Neg logit contributions | |
ranger | -0.030 |
years | -0.029 |
clearing | -0.028 |
since | -0.028 |
café | -0.027 |
Token | park |
Token ID | 3952 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ranger | +0.018 |
years | +0.017 |
since | +0.017 |
Tooth | +0.016 |
clearing | +0.016 |
Neg logit contributions | |
its | -0.027 |
ower | -0.025 |
apy | -0.025 |
aged | -0.024 |
isel | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
ranger | +0.047 |
years | +0.045 |
clearing | +0.044 |
Tooth | +0.044 |
since | +0.043 |
Neg logit contributions | |
its | -0.090 |
ower | -0.086 |
apy | -0.083 |
aged | -0.083 |
ikes | -0.082 |
Token | Julia |
Token ID | 22300 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
its | +0.030 |
ower | +0.028 |
apy | +0.028 |
isel | +0.027 |
aged | +0.027 |
Neg logit contributions | |
ranger | -0.024 |
years | -0.023 |
Tooth | -0.022 |
clearing | -0.022 |
since | -0.021 |
Token | sc |
Token ID | 629 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
ranger | +0.015 |
years | +0.014 |
clearing | +0.014 |
since | +0.014 |
Tooth | +0.014 |
Neg logit contributions | |
its | -0.021 |
ower | -0.020 |
apy | -0.020 |
aged | -0.019 |
isel | -0.019 |
Token | run |
Token ID | 5143 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
its | +0.105 |
ower | +0.095 |
ikes | +0.091 |
isel | +0.088 |
aged | +0.087 |
Neg logit contributions | |
ranger | -0.096 |
enclosure | -0.088 |
years | -0.088 |
since | -0.087 |
clearing | -0.084 |
Token | ched |
Token ID | 1740 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
ower | +0.374 |
its | +0.365 |
ikes | +0.334 |
isel | +0.330 |
aged | +0.329 |
Neg logit contributions | |
since | -0.329 |
years | -0.318 |
ranger | -0.310 |
clearing | -0.307 |
� | -0.305 |
Token | up |
Token ID | 510 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
its | +0.189 |
ower | +0.174 |
isel | +0.173 |
ikes | +0.169 |
apy | +0.167 |
Neg logit contributions | |
years | -0.084 |
ranger | -0.083 |
since | -0.082 |
Prince | -0.078 |
clearing | -0.078 |
Token | her |
Token ID | 607 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ranger | +0.019 |
clearing | +0.018 |
years | +0.018 |
Tooth | +0.017 |
since | +0.017 |
Neg logit contributions | |
its | -0.038 |
ower | -0.035 |
apy | -0.035 |
aged | -0.035 |
isel | -0.034 |
Token | face |
Token ID | 1986 |
Feature activation | +1.85e-03 |
Pos logit contributions | |
its | +0.040 |
isel | +0.036 |
ikes | +0.034 |
apy | +0.033 |
oving | +0.032 |
Neg logit contributions | |
ranger | -0.032 |
years | -0.031 |
since | -0.031 |
clearing | -0.029 |
front | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +2.73e-04 |
Pos logit contributions | |
ranger | +0.002 |
years | +0.002 |
clearing | +0.002 |
since | +0.002 |
café | +0.002 |
Neg logit contributions | |
its | -0.004 |
ower | -0.004 |
apy | -0.004 |
aged | -0.004 |
isel | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
years | +0.019 |
ranger | +0.018 |
since | +0.017 |
Tooth | +0.017 |
clearing | +0.017 |
Neg logit contributions | |
its | -0.029 |
ower | -0.027 |
isel | -0.027 |
ikes | -0.026 |
apy | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
its | +0.127 |
ower | +0.123 |
aged | +0.121 |
ikes | +0.117 |
apy | +0.116 |
Neg logit contributions | |
ranger | -0.097 |
clearing | -0.095 |
grizz | -0.092 |
Tooth | -0.092 |
café | -0.090 |
Token | never |
Token ID | 1239 |
Feature activation | -6.43e-04 |
Pos logit contributions | |
ranger | +0.011 |
years | +0.010 |
since | +0.010 |
clearing | +0.010 |
Tooth | +0.009 |
Neg logit contributions | |
its | -0.015 |
ower | -0.014 |
apy | -0.014 |
isel | -0.014 |
ikes | -0.014 |
Token | threw |
Token ID | 9617 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
its | +0.001 |
ower | +0.001 |
apy | +0.001 |
isel | +0.001 |
aged | +0.001 |
Neg logit contributions | |
ranger | -0.001 |
years | -0.001 |
clearing | -0.001 |
since | -0.001 |
café | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
its | +0.028 |
ower | +0.026 |
apy | +0.025 |
isel | +0.025 |
ikes | +0.025 |
Neg logit contributions | |
ranger | -0.027 |
years | -0.027 |
since | -0.026 |
clearing | -0.025 |
Prince | -0.025 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
its | +0.044 |
ower | +0.041 |
aged | +0.040 |
ikes | +0.040 |
apy | +0.039 |
Neg logit contributions | |
ranger | -0.043 |
years | -0.040 |
clearing | -0.040 |
since | -0.040 |
café | -0.039 |
Token | rum |
Token ID | 6582 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
apy | +0.310 |
inters | +0.305 |
ower | +0.286 |
its | +0.286 |
isel | +0.280 |
Neg logit contributions | |
years | -0.398 |
mother | -0.365 |
since | -0.324 |
ranger | -0.322 |
god | -0.319 |
Token | again |
Token ID | 757 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
its | +0.133 |
ower | +0.125 |
apy | +0.122 |
isel | +0.122 |
aged | +0.121 |
Neg logit contributions | |
ranger | -0.063 |
years | -0.059 |
since | -0.057 |
clearing | -0.057 |
café | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ranger | +0.067 |
years | +0.062 |
clearing | +0.061 |
since | +0.059 |
café | +0.059 |
Neg logit contributions | |
its | -0.137 |
ower | -0.129 |
apy | -0.126 |
aged | -0.125 |
isel | -0.124 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
its | +0.022 |
ower | +0.021 |
apy | +0.021 |
aged | +0.020 |
ikes | +0.020 |
Neg logit contributions | |
years | -0.016 |
ranger | -0.015 |
banquet | -0.015 |
clearing | -0.015 |
café | -0.014 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
ranger | +0.034 |
since | +0.032 |
years | +0.032 |
Tooth | +0.031 |
banquet | +0.031 |
Neg logit contributions | |
its | -0.055 |
ower | -0.049 |
apy | -0.048 |
ikes | -0.048 |
aged | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
clearing | +0.108 |
ranger | +0.105 |
Tooth | +0.100 |
years | +0.100 |
Fairy | +0.100 |
Neg logit contributions | |
its | -0.178 |
ower | -0.167 |
aged | -0.163 |
ikes | -0.160 |
apy | -0.159 |
Token | He |
Token ID | 679 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
its | +0.018 |
ower | +0.017 |
apy | +0.017 |
isel | +0.017 |
aged | +0.017 |
Neg logit contributions | |
ranger | -0.009 |
years | -0.009 |
clearing | -0.008 |
since | -0.008 |
café | -0.008 |
Token | kept |
Token ID | 4030 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
its | +0.018 |
aged | +0.017 |
apy | +0.016 |
ower | +0.015 |
isel | +0.015 |
Neg logit contributions | |
clearing | -0.019 |
ranger | -0.019 |
banquet | -0.019 |
Prince | -0.019 |
since | -0.019 |
Token | throwing |
Token ID | 9644 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
its | +0.051 |
ower | +0.049 |
apy | +0.047 |
ikes | +0.047 |
isel | +0.047 |
Neg logit contributions | |
ranger | -0.033 |
years | -0.031 |
clearing | -0.030 |
Tooth | -0.029 |
café | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
its | +0.092 |
ower | +0.087 |
apy | +0.084 |
isel | +0.083 |
ikes | +0.083 |
Neg logit contributions | |
ranger | -0.058 |
years | -0.055 |
since | -0.053 |
clearing | -0.052 |
Prince | -0.051 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
its | +0.045 |
ower | +0.041 |
aged | +0.041 |
ikes | +0.041 |
isel | +0.040 |
Neg logit contributions | |
ranger | -0.041 |
clearing | -0.039 |
café | -0.038 |
years | -0.037 |
Prince | -0.037 |
Token | rum |
Token ID | 6582 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
apy | +0.295 |
inters | +0.292 |
its | +0.283 |
ower | +0.277 |
ikes | +0.264 |
Neg logit contributions | |
years | -0.384 |
ranger | -0.359 |
mother | -0.348 |
since | -0.334 |
Fairy | -0.334 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
its | +0.128 |
ower | +0.121 |
aged | +0.118 |
apy | +0.118 |
ikes | +0.117 |
Neg logit contributions | |
ranger | -0.068 |
clearing | -0.065 |
years | -0.063 |
café | -0.063 |
Tooth | -0.062 |
Token | His |
Token ID | 2399 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
its | +0.008 |
ower | +0.008 |
apy | +0.008 |
isel | +0.007 |
aged | +0.007 |
Neg logit contributions | |
ranger | -0.004 |
years | -0.003 |
clearing | -0.003 |
since | -0.003 |
café | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
its | +0.064 |
ower | +0.059 |
isel | +0.057 |
apy | +0.057 |
ikes | +0.057 |
Neg logit contributions | |
ranger | -0.045 |
years | -0.042 |
clearing | -0.041 |
since | -0.040 |
café | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +5.79e-03 |
Pos logit contributions | |
ranger | +0.032 |
clearing | +0.032 |
banquet | +0.030 |
Prince | +0.030 |
Tooth | +0.030 |
Neg logit contributions | |
its | -0.041 |
aged | -0.038 |
ower | -0.037 |
apy | -0.037 |
isel | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
its | +0.024 |
ower | +0.023 |
apy | +0.022 |
aged | +0.022 |
isel | +0.022 |
Neg logit contributions | |
ranger | -0.015 |
years | -0.015 |
clearing | -0.014 |
since | -0.014 |
café | -0.014 |
Token | dirt |
Token ID | 13647 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
its | +0.021 |
ower | +0.019 |
isel | +0.019 |
apy | +0.019 |
aged | +0.019 |
Neg logit contributions | |
ranger | -0.017 |
years | -0.016 |
since | -0.016 |
clearing | -0.016 |
Tooth | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
its | +0.117 |
ower | +0.111 |
isel | +0.110 |
ikes | +0.109 |
apy | +0.109 |
Neg logit contributions | |
ranger | -0.049 |
years | -0.044 |
since | -0.043 |
clearing | -0.042 |
café | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
its | +0.008 |
ower | +0.008 |
apy | +0.008 |
isel | +0.008 |
aged | +0.008 |
Neg logit contributions | |
ranger | -0.005 |
years | -0.004 |
since | -0.004 |
clearing | -0.004 |
Tooth | -0.004 |
Token | sc |
Token ID | 629 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
its | +0.020 |
ower | +0.018 |
apy | +0.018 |
aged | +0.018 |
isel | +0.018 |
Neg logit contributions | |
ranger | -0.015 |
years | -0.014 |
clearing | -0.014 |
since | -0.014 |
café | -0.014 |
Token | run |
Token ID | 5143 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
its | +0.107 |
ower | +0.099 |
ikes | +0.096 |
apy | +0.092 |
aged | +0.090 |
Neg logit contributions | |
ranger | -0.074 |
enclosure | -0.071 |
years | -0.067 |
clearing | -0.066 |
since | -0.065 |
Token | ched |
Token ID | 1740 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
ower | +0.346 |
its | +0.327 |
ikes | +0.307 |
isel | +0.306 |
aged | +0.296 |
Neg logit contributions | |
since | -0.350 |
years | -0.336 |
ranger | -0.335 |
clearing | -0.329 |
� | -0.326 |
Token | up |
Token ID | 510 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
its | +0.181 |
ower | +0.172 |
isel | +0.164 |
ikes | +0.164 |
apy | +0.163 |
Neg logit contributions | |
ranger | -0.088 |
years | -0.084 |
since | -0.083 |
Prince | -0.081 |
clearing | -0.080 |
Token | his |
Token ID | 465 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
ranger | +0.022 |
Tooth | +0.021 |
clearing | +0.021 |
café | +0.021 |
years | +0.020 |
Neg logit contributions | |
its | -0.040 |
ower | -0.038 |
aged | -0.038 |
apy | -0.038 |
isel | -0.037 |
Token | face |
Token ID | 1986 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
its | +0.053 |
isel | +0.047 |
ower | +0.046 |
apy | +0.046 |
ikes | +0.046 |
Neg logit contributions | |
ranger | -0.049 |
years | -0.048 |
clearing | -0.046 |
since | -0.045 |
enclosure | -0.045 |
Token | as |
Token ID | 355 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
ranger | +0.001 |
years | +0.001 |
clearing | +0.001 |
since | +0.001 |
café | +0.001 |
Neg logit contributions | |
its | -0.003 |
ower | -0.003 |
apy | -0.003 |
aged | -0.003 |
ikes | -0.003 |
Token | laughed |
Token ID | 13818 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
its | +0.134 |
ower | +0.130 |
ikes | +0.125 |
isel | +0.120 |
apy | +0.119 |
Neg logit contributions | |
since | -0.073 |
ranger | -0.071 |
years | -0.071 |
clearing | -0.065 |
Fairy | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
its | +0.006 |
apy | +0.006 |
ower | +0.006 |
ikes | +0.006 |
aged | +0.006 |
Neg logit contributions | |
ranger | -0.005 |
café | -0.004 |
clearing | -0.004 |
Tooth | -0.004 |
enclosure | -0.004 |
Token | shared |
Token ID | 4888 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
its | +0.039 |
ower | +0.036 |
isel | +0.035 |
apy | +0.035 |
ikes | +0.035 |
Neg logit contributions | |
ranger | -0.025 |
years | -0.024 |
since | -0.023 |
clearing | -0.023 |
café | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
its | +0.031 |
ower | +0.028 |
apy | +0.028 |
aged | +0.028 |
isel | +0.027 |
Neg logit contributions | |
ranger | -0.022 |
years | -0.021 |
clearing | -0.021 |
since | -0.020 |
Tooth | -0.020 |
Token | cr |
Token ID | 1067 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
its | +0.104 |
ower | +0.097 |
apy | +0.093 |
ikes | +0.092 |
aged | +0.092 |
Neg logit contributions | |
ranger | -0.094 |
years | -0.089 |
since | -0.087 |
clearing | -0.087 |
café | -0.086 |
Token | ay |
Token ID | 323 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
its | +0.102 |
isel | +0.093 |
aged | +0.093 |
apy | +0.093 |
ower | +0.092 |
Neg logit contributions | |
ranger | -0.128 |
years | -0.126 |
since | -0.123 |
Fairy | -0.122 |
Tooth | -0.121 |
Token | ons |
Token ID | 684 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
its | +0.394 |
isel | +0.383 |
ower | +0.376 |
inters | +0.368 |
aged | +0.368 |
Neg logit contributions | |
years | -0.281 |
ranger | -0.271 |
Fairy | -0.252 |
mother | -0.250 |
since | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
its | +0.175 |
ower | +0.169 |
apy | +0.164 |
aged | +0.161 |
ikes | +0.159 |
Neg logit contributions | |
clearing | -0.127 |
ranger | -0.124 |
Tooth | -0.122 |
grizz | -0.120 |
dentist | -0.119 |
Token | |
Token ID | 220 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
its | +0.037 |
apy | +0.034 |
ower | +0.034 |
aged | +0.033 |
isel | +0.033 |
Neg logit contributions | |
ranger | -0.023 |
years | -0.021 |
clearing | -0.020 |
since | -0.020 |
Tooth | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
its | +0.155 |
isel | +0.153 |
ower | +0.149 |
aged | +0.147 |
apy | +0.147 |
Neg logit contributions | |
ranger | -0.021 |
clearing | -0.014 |
Ms | -0.014 |
since | -0.013 |
� | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +5.77e-03 |
Pos logit contributions | |
its | +0.012 |
ower | +0.012 |
isel | +0.011 |
aged | +0.011 |
apy | +0.011 |
Neg logit contributions | |
ranger | -0.003 |
clearing | -0.002 |
years | -0.002 |
since | -0.002 |
café | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ranger | +0.014 |
years | +0.014 |
since | +0.014 |
clearing | +0.012 |
café | +0.012 |
Neg logit contributions | |
its | -0.026 |
isel | -0.024 |
ower | -0.024 |
ikes | -0.023 |
apy | -0.023 |
Token | missing |
Token ID | 4814 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
its | +0.031 |
ower | +0.029 |
apy | +0.028 |
aged | +0.028 |
isel | +0.028 |
Neg logit contributions | |
ranger | -0.021 |
years | -0.020 |
clearing | -0.020 |
since | -0.019 |
café | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
its | +0.076 |
ower | +0.072 |
apy | +0.071 |
aged | +0.070 |
isel | +0.069 |
Neg logit contributions | |
ranger | -0.041 |
years | -0.038 |
clearing | -0.038 |
café | -0.037 |
Tooth | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
its | +0.021 |
ower | +0.020 |
apy | +0.019 |
isel | +0.019 |
ikes | +0.019 |
Neg logit contributions | |
ranger | -0.015 |
years | -0.015 |
clearing | -0.014 |
Tooth | -0.014 |
banquet | -0.014 |
Token | sc |
Token ID | 629 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
ranger | +0.033 |
café | +0.032 |
Tooth | +0.032 |
clearing | +0.031 |
cafe | +0.031 |
Neg logit contributions | |
its | -0.037 |
aged | -0.036 |
apy | -0.034 |
isel | -0.033 |
ower | -0.033 |
Token | run |
Token ID | 5143 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
its | +0.099 |
ower | +0.093 |
ikes | +0.089 |
apy | +0.087 |
isel | +0.087 |
Neg logit contributions | |
ranger | -0.079 |
years | -0.074 |
since | -0.072 |
enclosure | -0.070 |
clearing | -0.070 |
Token | ched |
Token ID | 1740 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
ower | +0.299 |
its | +0.292 |
ikes | +0.270 |
isel | +0.265 |
aged | +0.257 |
Neg logit contributions | |
since | -0.383 |
years | -0.371 |
ranger | -0.369 |
� | -0.365 |
clearing | -0.357 |
Token | up |
Token ID | 510 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
its | +0.154 |
ower | +0.144 |
apy | +0.139 |
ikes | +0.138 |
isel | +0.137 |
Neg logit contributions | |
ranger | -0.102 |
since | -0.099 |
years | -0.099 |
Prince | -0.095 |
clearing | -0.094 |
Token | her |
Token ID | 607 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
ranger | +0.022 |
clearing | +0.021 |
years | +0.021 |
café | +0.020 |
Tooth | +0.020 |
Neg logit contributions | |
its | -0.038 |
ower | -0.036 |
aged | -0.036 |
apy | -0.036 |
isel | -0.035 |
Token | face |
Token ID | 1986 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
its | +0.037 |
ower | +0.034 |
isel | +0.033 |
apy | +0.033 |
ikes | +0.033 |
Neg logit contributions | |
ranger | -0.030 |
years | -0.029 |
since | -0.028 |
clearing | -0.027 |
Tooth | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
ranger | +0.002 |
years | +0.002 |
clearing | +0.002 |
café | +0.002 |
since | +0.001 |
Neg logit contributions | |
its | -0.004 |
ower | -0.004 |
apy | -0.004 |
aged | -0.004 |
isel | -0.003 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ranger | +0.037 |
clearing | +0.035 |
years | +0.034 |
since | +0.033 |
café | +0.033 |
Neg logit contributions | |
its | -0.065 |
ower | -0.061 |
aged | -0.060 |
ikes | -0.059 |
apy | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
its | +0.018 |
ower | +0.017 |
ikes | +0.016 |
aged | +0.015 |
oom | +0.015 |
Neg logit contributions | |
clearing | -0.032 |
grizz | -0.031 |
ranger | -0.029 |
doorway | -0.029 |
café | -0.029 |
Token | share |
Token ID | 2648 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
its | +0.050 |
ower | +0.046 |
isel | +0.044 |
ikes | +0.044 |
apy | +0.043 |
Neg logit contributions | |
ranger | -0.047 |
years | -0.045 |
since | -0.044 |
Tooth | -0.042 |
clearing | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
clearing | +0.003 |
ranger | +0.003 |
grizz | +0.003 |
café | +0.003 |
banquet | +0.003 |
Neg logit contributions | |
its | -0.003 |
ower | -0.003 |
apy | -0.003 |
ikes | -0.003 |
aged | -0.003 |
Token | cr |
Token ID | 1067 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
its | +0.106 |
ower | +0.096 |
apy | +0.096 |
isel | +0.095 |
aged | +0.093 |
Neg logit contributions | |
ranger | -0.093 |
years | -0.090 |
clearing | -0.087 |
since | -0.087 |
Tooth | -0.086 |
Token | ay |
Token ID | 323 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
its | +0.104 |
apy | +0.099 |
aged | +0.098 |
isel | +0.096 |
ower | +0.093 |
Neg logit contributions | |
years | -0.131 |
ranger | -0.130 |
since | -0.127 |
Fairy | -0.125 |
Tooth | -0.124 |
Token | ons |
Token ID | 684 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
its | +0.355 |
isel | +0.350 |
apy | +0.333 |
inters | +0.332 |
aged | +0.332 |
Neg logit contributions | |
years | -0.321 |
ranger | -0.307 |
Fairy | -0.288 |
Tooth | -0.287 |
mother | -0.287 |
Token | and |
Token ID | 290 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
its | +0.148 |
ower | +0.145 |
ikes | +0.134 |
aged | +0.131 |
apy | +0.130 |
Neg logit contributions | |
clearing | -0.156 |
grizz | -0.146 |
café | -0.136 |
ranger | -0.134 |
awoke | -0.133 |
Token | the |
Token ID | 262 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
its | +0.065 |
apy | +0.059 |
ower | +0.059 |
aged | +0.058 |
isel | +0.058 |
Neg logit contributions | |
ranger | -0.065 |
clearing | -0.062 |
years | -0.062 |
café | -0.060 |
since | -0.060 |
Token | paper |
Token ID | 3348 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
its | +0.073 |
ower | +0.067 |
apy | +0.065 |
aged | +0.064 |
isel | +0.064 |
Neg logit contributions | |
ranger | -0.069 |
years | -0.066 |
clearing | -0.065 |
since | -0.065 |
café | -0.064 |
Token | ." |
Token ID | 526 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
its | +0.026 |
ower | +0.025 |
apy | +0.023 |
ikes | +0.023 |
aged | +0.023 |
Neg logit contributions | |
clearing | -0.022 |
café | -0.021 |
ranger | -0.021 |
years | -0.021 |
grizz | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
ranger | +0.060 |
years | +0.057 |
clearing | +0.055 |
since | +0.055 |
café | +0.054 |
Neg logit contributions | |
its | -0.084 |
ower | -0.078 |
apy | -0.076 |
isel | -0.076 |
ikes | -0.075 |
Token | candy |
Token ID | 18550 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
its | +0.056 |
ower | +0.052 |
apy | +0.051 |
isel | +0.051 |
aged | +0.050 |
Neg logit contributions | |
ranger | -0.037 |
years | -0.035 |
clearing | -0.034 |
since | -0.034 |
café | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ranger | +0.029 |
years | +0.027 |
clearing | +0.026 |
since | +0.026 |
café | +0.025 |
Neg logit contributions | |
its | -0.068 |
ower | -0.065 |
apy | -0.063 |
aged | -0.063 |
ikes | -0.062 |
Token | she |
Token ID | 673 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
its | +0.033 |
apy | +0.032 |
aged | +0.031 |
ower | +0.031 |
isel | +0.029 |
Neg logit contributions | |
ranger | -0.026 |
years | -0.024 |
enclosure | -0.023 |
café | -0.023 |
clearing | -0.023 |
Token | sc |
Token ID | 629 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
ranger | +0.057 |
clearing | +0.053 |
years | +0.052 |
Cave | +0.051 |
café | +0.051 |
Neg logit contributions | |
its | -0.058 |
aged | -0.054 |
apy | -0.053 |
isel | -0.051 |
ower | -0.050 |
Token | run |
Token ID | 5143 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
its | +0.083 |
ower | +0.077 |
ikes | +0.073 |
isel | +0.073 |
apy | +0.072 |
Neg logit contributions | |
ranger | -0.062 |
years | -0.057 |
since | -0.056 |
clearing | -0.056 |
café | -0.056 |
Token | ched |
Token ID | 1740 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
its | +0.321 |
ower | +0.311 |
isel | +0.285 |
ikes | +0.285 |
apy | +0.277 |
Neg logit contributions | |
ranger | -0.367 |
since | -0.361 |
years | -0.359 |
clearing | -0.350 |
Tooth | -0.340 |
Token | her |
Token ID | 607 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
its | +0.163 |
ower | +0.152 |
isel | +0.147 |
apy | +0.146 |
ikes | +0.146 |
Neg logit contributions | |
ranger | -0.096 |
since | -0.094 |
years | -0.093 |
Prince | -0.093 |
Tooth | -0.093 |
Token | eyes |
Token ID | 2951 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
its | +0.042 |
ower | +0.040 |
aged | +0.039 |
apy | +0.038 |
ikes | +0.038 |
Neg logit contributions | |
ranger | -0.035 |
clearing | -0.032 |
since | -0.032 |
years | -0.032 |
café | -0.031 |
Token | tight |
Token ID | 5381 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
its | +0.077 |
ower | +0.073 |
apy | +0.072 |
aged | +0.072 |
ikes | +0.070 |
Neg logit contributions | |
ranger | -0.042 |
years | -0.038 |
clearing | -0.038 |
café | -0.036 |
Prince | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
its | +0.061 |
ower | +0.058 |
aged | +0.058 |
ikes | +0.056 |
apy | +0.055 |
Neg logit contributions | |
ranger | -0.038 |
clearing | -0.035 |
years | -0.034 |
café | -0.034 |
banquet | -0.033 |
Token | listen |
Token ID | 6004 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
ranger | +0.029 |
years | +0.028 |
since | +0.028 |
café | +0.026 |
Tooth | +0.026 |
Neg logit contributions | |
its | -0.020 |
ower | -0.019 |
apy | -0.019 |
aged | -0.018 |
ikes | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
clearing | +0.107 |
ranger | +0.104 |
Tooth | +0.098 |
banquet | +0.098 |
enclosure | +0.097 |
Neg logit contributions | |
its | -0.167 |
ower | -0.157 |
aged | -0.155 |
ikes | -0.149 |
apy | -0.149 |
Token | She |
Token ID | 1375 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
its | +0.016 |
ower | +0.015 |
apy | +0.015 |
isel | +0.015 |
aged | +0.015 |
Neg logit contributions | |
ranger | -0.007 |
years | -0.007 |
since | -0.006 |
clearing | -0.006 |
Tooth | -0.006 |
Token | threw |
Token ID | 9617 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
clearing | +0.032 |
ranger | +0.030 |
banquet | +0.030 |
Prince | +0.030 |
Tooth | +0.030 |
Neg logit contributions | |
its | -0.030 |
aged | -0.026 |
apy | -0.024 |
ower | -0.024 |
isel | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
its | +0.056 |
ower | +0.054 |
isel | +0.051 |
apy | +0.051 |
ikes | +0.051 |
Neg logit contributions | |
ranger | -0.028 |
years | -0.026 |
since | -0.026 |
clearing | -0.025 |
Prince | -0.025 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
its | +0.023 |
ower | +0.020 |
ikes | +0.020 |
aged | +0.020 |
isel | +0.019 |
Neg logit contributions | |
ranger | -0.046 |
clearing | -0.043 |
years | -0.043 |
café | -0.043 |
since | -0.042 |
Token | rum |
Token ID | 6582 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
inters | +0.286 |
its | +0.280 |
apy | +0.275 |
ower | +0.274 |
ikes | +0.268 |
Neg logit contributions | |
years | -0.380 |
ranger | -0.342 |
mother | -0.342 |
since | -0.330 |
Fairy | -0.328 |
Token | in |
Token ID | 287 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
its | +0.125 |
ower | +0.119 |
aged | +0.116 |
apy | +0.116 |
ikes | +0.114 |
Neg logit contributions | |
ranger | -0.060 |
clearing | -0.056 |
years | -0.055 |
café | -0.054 |
Tooth | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
its | +0.043 |
ower | +0.042 |
ikes | +0.041 |
isel | +0.040 |
apy | +0.039 |
Neg logit contributions | |
years | -0.019 |
ranger | -0.019 |
since | -0.018 |
clearing | -0.017 |
café | -0.016 |
Token | store |
Token ID | 3650 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
since | +0.037 |
ranger | +0.036 |
Fairy | +0.036 |
Tooth | +0.035 |
years | +0.035 |
Neg logit contributions | |
its | -0.034 |
ower | -0.029 |
apy | -0.029 |
isel | -0.028 |
aged | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -8.25e-04 |
Pos logit contributions | |
clearing | +0.039 |
Tooth | +0.038 |
Fairy | +0.037 |
banquet | +0.037 |
ranger | +0.037 |
Neg logit contributions | |
its | -0.072 |
ower | -0.069 |
aged | -0.068 |
ikes | -0.065 |
apy | -0.064 |
Token | kept |
Token ID | 4030 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ranger | +0.033 |
clearing | +0.031 |
years | +0.030 |
banquet | +0.030 |
café | +0.030 |
Neg logit contributions | |
its | -0.035 |
aged | -0.032 |
ower | -0.031 |
apy | -0.031 |
isel | -0.030 |
Token | crying |
Token ID | 13774 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
its | +0.048 |
ower | +0.044 |
isel | +0.043 |
apy | +0.043 |
ikes | +0.043 |
Neg logit contributions | |
ranger | -0.033 |
years | -0.032 |
clearing | -0.030 |
since | -0.030 |
Tooth | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
its | +0.102 |
ower | +0.096 |
apy | +0.094 |
aged | +0.094 |
isel | +0.093 |
Neg logit contributions | |
ranger | -0.043 |
years | -0.039 |
clearing | -0.039 |
since | -0.038 |
café | -0.038 |
Token | throwing |
Token ID | 9644 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
ranger | +0.012 |
years | +0.012 |
since | +0.012 |
clearing | +0.011 |
Tooth | +0.011 |
Neg logit contributions | |
its | -0.019 |
ower | -0.018 |
ikes | -0.018 |
isel | -0.018 |
apy | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
its | +0.089 |
ower | +0.088 |
ikes | +0.085 |
isel | +0.084 |
apy | +0.081 |
Neg logit contributions | |
years | -0.048 |
ranger | -0.048 |
since | -0.046 |
clearing | -0.044 |
Prince | -0.044 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
its | +0.028 |
ikes | +0.026 |
ower | +0.025 |
isel | +0.024 |
aged | +0.024 |
Neg logit contributions | |
ranger | -0.038 |
clearing | -0.036 |
café | -0.036 |
years | -0.035 |
since | -0.035 |
Token | rum |
Token ID | 6582 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
inters | +0.284 |
its | +0.281 |
ower | +0.278 |
apy | +0.274 |
ikes | +0.273 |
Neg logit contributions | |
years | -0.377 |
mother | -0.345 |
since | -0.334 |
Fairy | -0.332 |
ranger | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | -4.33e-03 |
Pos logit contributions | |
its | +0.122 |
ower | +0.114 |
apy | +0.112 |
isel | +0.112 |
aged | +0.111 |
Neg logit contributions | |
ranger | -0.057 |
years | -0.054 |
since | -0.052 |
clearing | -0.051 |
café | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
its | +0.011 |
isel | +0.010 |
ower | +0.010 |
ikes | +0.010 |
apy | +0.010 |
Neg logit contributions | |
ranger | -0.004 |
since | -0.004 |
years | -0.004 |
clearing | -0.004 |
café | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ranger | +0.003 |
years | +0.003 |
since | +0.003 |
clearing | +0.003 |
Mrs | +0.003 |
Neg logit contributions | |
its | -0.018 |
isel | -0.017 |
ower | -0.017 |
aged | -0.017 |
ikes | -0.017 |
Token | Finally |
Token ID | 11158 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
ranger | +0.019 |
years | +0.018 |
since | +0.018 |
clearing | +0.017 |
café | +0.016 |
Neg logit contributions | |
its | -0.036 |
isel | -0.033 |
ower | -0.033 |
apy | -0.033 |
ikes | -0.032 |
Token | sad |
Token ID | 6507 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
ranger | +0.002 |
since | +0.002 |
years | +0.002 |
café | +0.002 |
Prince | +0.002 |
Neg logit contributions | |
its | -0.003 |
ower | -0.003 |
ikes | -0.003 |
isel | -0.003 |
apy | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
its | +0.127 |
ower | +0.120 |
apy | +0.117 |
aged | +0.117 |
ikes | +0.116 |
Neg logit contributions | |
ranger | -0.063 |
years | -0.059 |
clearing | -0.059 |
café | -0.057 |
since | -0.056 |
Token | She |
Token ID | 1375 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
its | +0.026 |
ower | +0.025 |
isel | +0.024 |
apy | +0.024 |
aged | +0.024 |
Neg logit contributions | |
ranger | -0.011 |
years | -0.010 |
since | -0.010 |
clearing | -0.010 |
café | -0.010 |
Token | threw |
Token ID | 9617 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
ranger | +0.028 |
clearing | +0.027 |
years | +0.026 |
café | +0.026 |
banquet | +0.026 |
Neg logit contributions | |
its | -0.027 |
aged | -0.024 |
ower | -0.024 |
apy | -0.023 |
isel | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
its | +0.065 |
ower | +0.063 |
ikes | +0.060 |
apy | +0.059 |
isel | +0.059 |
Neg logit contributions | |
ranger | -0.026 |
years | -0.024 |
since | -0.024 |
clearing | -0.023 |
Prince | -0.023 |
Token | tant |
Token ID | 24246 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
its | +0.026 |
ikes | +0.024 |
ower | +0.023 |
aged | +0.023 |
oving | +0.022 |
Neg logit contributions | |
ranger | -0.039 |
clearing | -0.037 |
café | -0.036 |
since | -0.035 |
years | -0.035 |
Token | rum |
Token ID | 6582 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
its | +0.281 |
inters | +0.274 |
ower | +0.268 |
apy | +0.267 |
ikes | +0.262 |
Neg logit contributions | |
years | -0.388 |
mother | -0.353 |
since | -0.347 |
Fairy | -0.345 |
ranger | -0.345 |
Token | and |
Token ID | 290 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
its | +0.130 |
ower | +0.122 |
isel | +0.120 |
apy | +0.119 |
ikes | +0.118 |
Neg logit contributions | |
ranger | -0.055 |
years | -0.052 |
since | -0.050 |
clearing | -0.049 |
café | -0.047 |
Token | cried |
Token ID | 16896 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
ranger | +0.003 |
years | +0.003 |
since | +0.003 |
clearing | +0.003 |
Tooth | +0.003 |
Neg logit contributions | |
its | -0.004 |
ower | -0.004 |
isel | -0.004 |
ikes | -0.004 |
apy | -0.004 |
Token | loudly |
Token ID | 23112 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
its | +0.042 |
isel | +0.039 |
ower | +0.038 |
ikes | +0.038 |
apy | +0.037 |
Neg logit contributions | |
since | -0.015 |
years | -0.014 |
ranger | -0.014 |
Prince | -0.013 |
again | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +9.53e-04 |
Pos logit contributions | |
ranger | +0.032 |
clearing | +0.031 |
years | +0.031 |
café | +0.029 |
Tooth | +0.029 |
Neg logit contributions | |
its | -0.056 |
ower | -0.054 |
aged | -0.053 |
apy | -0.052 |
ikes | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
ranger | +0.003 |
clearing | +0.002 |
years | +0.002 |
Tooth | +0.002 |
since | +0.002 |
Neg logit contributions | |
its | -0.005 |
ower | -0.005 |
aged | -0.005 |
apy | -0.005 |
ikes | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
its | +0.002 |
ower | +0.002 |
apy | +0.002 |
ikes | +0.002 |
isel | +0.002 |
Neg logit contributions | |
ranger | -0.002 |
years | -0.002 |
since | -0.002 |
clearing | -0.002 |
Tooth | -0.002 |
Token | share |
Token ID | 2648 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
its | +0.070 |
ower | +0.068 |
apy | +0.066 |
isel | +0.066 |
ikes | +0.065 |
Neg logit contributions | |
ranger | -0.033 |
years | -0.033 |
since | -0.030 |
Prince | -0.030 |
Tooth | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
clearing | +0.017 |
ranger | +0.017 |
Fairy | +0.016 |
grizz | +0.016 |
café | +0.016 |
Neg logit contributions | |
its | -0.024 |
ower | -0.021 |
ikes | -0.021 |
apy | -0.021 |
aged | -0.021 |
Token | cr |
Token ID | 1067 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
its | +0.112 |
ower | +0.103 |
apy | +0.100 |
aged | +0.099 |
isel | +0.099 |
Neg logit contributions | |
ranger | -0.095 |
years | -0.091 |
clearing | -0.089 |
since | -0.089 |
café | -0.087 |
Token | ay |
Token ID | 323 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
its | +0.097 |
apy | +0.089 |
aged | +0.087 |
isel | +0.087 |
ower | +0.087 |
Neg logit contributions | |
ranger | -0.135 |
years | -0.132 |
since | -0.129 |
Tooth | -0.127 |
clearing | -0.126 |
Token | ons |
Token ID | 684 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
its | +0.328 |
isel | +0.308 |
apy | +0.303 |
ower | +0.302 |
aged | +0.295 |
Neg logit contributions | |
ranger | -0.349 |
years | -0.346 |
Tooth | -0.321 |
since | -0.320 |
Fairy | -0.320 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
its | +0.164 |
ower | +0.155 |
ikes | +0.147 |
aged | +0.147 |
apy | +0.145 |
Neg logit contributions | |
clearing | -0.129 |
grizz | -0.120 |
ranger | -0.120 |
café | -0.115 |
banquet | -0.112 |
Token | You |
Token ID | 921 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
its | +0.046 |
ikes | +0.044 |
ower | +0.043 |
apy | +0.042 |
aged | +0.040 |
Neg logit contributions | |
ranger | -0.040 |
clearing | -0.040 |
years | -0.039 |
banquet | -0.038 |
café | -0.038 |
Token | can |
Token ID | 460 |
Feature activation | +2.46e-03 |
Pos logit contributions | |
its | +0.033 |
ower | +0.031 |
apy | +0.030 |
aged | +0.030 |
isel | +0.030 |
Neg logit contributions | |
ranger | -0.031 |
years | -0.030 |
since | -0.029 |
clearing | -0.028 |
Tooth | -0.028 |
Token | show |
Token ID | 905 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
ranger | +0.004 |
years | +0.004 |
clearing | +0.004 |
since | +0.004 |
café | +0.004 |
Neg logit contributions | |
its | -0.004 |
ower | -0.004 |
apy | -0.004 |
isel | -0.004 |
ikes | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
its | +0.060 |
ower | +0.058 |
isel | +0.057 |
aged | +0.057 |
apy | +0.056 |
Neg logit contributions | |
ranger | -0.018 |
years | -0.015 |
clearing | -0.015 |
since | -0.014 |
Tooth | -0.013 |
Token | They |
Token ID | 2990 |
Feature activation | -7.81e-04 |
Pos logit contributions | |
its | +0.017 |
apy | +0.016 |
ower | +0.016 |
ikes | +0.015 |
aged | +0.015 |
Neg logit contributions | |
Prince | -0.015 |
banquet | -0.015 |
Tooth | -0.015 |
Fairy | -0.015 |
since | -0.015 |
Token | share |
Token ID | 2648 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
its | +0.001 |
ower | +0.001 |
apy | +0.001 |
ikes | +0.001 |
aged | +0.001 |
Neg logit contributions | |
ranger | -0.001 |
years | -0.001 |
since | -0.001 |
clearing | -0.001 |
Prince | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
ranger | +0.007 |
clearing | +0.007 |
years | +0.006 |
Fairy | +0.006 |
Tooth | +0.006 |
Neg logit contributions | |
its | -0.010 |
apy | -0.009 |
aged | -0.009 |
ower | -0.009 |
ikes | -0.008 |
Token | cr |
Token ID | 1067 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
its | +0.119 |
ower | +0.110 |
apy | +0.107 |
aged | +0.106 |
ikes | +0.106 |
Neg logit contributions | |
ranger | -0.087 |
years | -0.084 |
since | -0.082 |
clearing | -0.081 |
café | -0.079 |
Token | ay |
Token ID | 323 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
its | +0.101 |
apy | +0.097 |
aged | +0.096 |
isel | +0.095 |
ower | +0.095 |
Neg logit contributions | |
ranger | -0.121 |
years | -0.119 |
Tooth | -0.116 |
since | -0.116 |
Fairy | -0.114 |
Token | ons |
Token ID | 684 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
its | +0.378 |
isel | +0.370 |
ower | +0.368 |
apy | +0.361 |
aged | +0.360 |
Neg logit contributions | |
ranger | -0.279 |
years | -0.276 |
Tooth | -0.251 |
dentist | -0.250 |
Prince | -0.248 |
Token | and |
Token ID | 290 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
its | +0.197 |
ower | +0.186 |
apy | +0.181 |
aged | +0.181 |
ikes | +0.176 |
Neg logit contributions | |
ranger | -0.099 |
clearing | -0.098 |
Tooth | -0.095 |
years | -0.094 |
café | -0.092 |
Token | print |
Token ID | 3601 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
its | +0.062 |
apy | +0.056 |
ower | +0.055 |
aged | +0.055 |
isel | +0.055 |
Neg logit contributions | |
ranger | -0.070 |
clearing | -0.068 |
years | -0.068 |
since | -0.066 |
Tooth | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ranger | +0.011 |
years | +0.010 |
clearing | +0.010 |
since | +0.010 |
Prince | +0.010 |
Neg logit contributions | |
its | -0.017 |
ower | -0.017 |
isel | -0.016 |
apy | -0.016 |
aged | -0.016 |
Token | plate |
Token ID | 7480 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
its | +0.058 |
ower | +0.053 |
apy | +0.051 |
ikes | +0.051 |
aged | +0.050 |
Neg logit contributions | |
ranger | -0.049 |
years | -0.047 |
since | -0.046 |
clearing | -0.046 |
café | -0.045 |
Token | ste |
Token ID | 2876 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
its | +0.034 |
apy | +0.031 |
ower | +0.031 |
isel | +0.030 |
aged | +0.030 |
Neg logit contributions | |
ranger | -0.034 |
years | -0.033 |
since | -0.032 |
enclosure | -0.032 |
clearing | -0.032 |
Token | aming |
Token ID | 3723 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ranger | +0.013 |
since | +0.012 |
café | +0.012 |
Prince | +0.012 |
Tooth | +0.012 |
Neg logit contributions | |
its | -0.015 |
ower | -0.014 |
aged | -0.013 |
apy | -0.013 |
isel | -0.013 |
Token | pie |
Token ID | 2508 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
years | +0.029 |
ranger | +0.028 |
since | +0.028 |
Prince | +0.028 |
clearing | +0.027 |
Neg logit contributions | |
ower | -0.027 |
its | -0.027 |
apy | -0.026 |
aged | -0.025 |
isel | -0.024 |
Token | appeared |
Token ID | 4120 |
Feature activation | +2.61e-04 |
Pos logit contributions | |
ranger | +0.062 |
years | +0.060 |
clearing | +0.057 |
Tooth | +0.057 |
café | +0.056 |
Neg logit contributions | |
its | -0.117 |
ower | -0.111 |
apy | -0.109 |
aged | -0.108 |
ikes | -0.105 |
Token | in |
Token ID | 287 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
ranger | +0.000 |
café | +0.000 |
years | +0.000 |
Tooth | +0.000 |
dentist | +0.000 |
Neg logit contributions | |
its | -0.000 |
ower | -0.000 |
aged | -0.000 |
ikes | -0.000 |
apy | -0.000 |
Token | front |
Token ID | 2166 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ranger | +0.032 |
enclosure | +0.029 |
café | +0.028 |
dentist | +0.028 |
banquet | +0.028 |
Neg logit contributions | |
its | -0.043 |
apy | -0.038 |
isel | -0.037 |
aged | -0.036 |
ower | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
Tooth | +0.197 |
Prince | +0.197 |
ranger | +0.187 |
Princess | +0.186 |
Fairy | +0.186 |
Neg logit contributions | |
its | -0.148 |
apy | -0.124 |
ower | -0.120 |
isel | -0.120 |
aged | -0.117 |
Token | her |
Token ID | 607 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ranger | +0.023 |
years | +0.022 |
since | +0.021 |
clearing | +0.021 |
café | +0.021 |
Neg logit contributions | |
its | -0.028 |
ower | -0.025 |
apy | -0.025 |
aged | -0.025 |
isel | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-03 |
Pos logit contributions | |
ranger | +0.024 |
clearing | +0.022 |
café | +0.022 |
since | +0.022 |
Tooth | +0.021 |
Neg logit contributions | |
its | -0.041 |
ower | -0.040 |
aged | -0.038 |
apy | -0.038 |
ikes | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
apy | +0.002 |
its | +0.002 |
aged | +0.002 |
ower | +0.002 |
isel | +0.002 |
Neg logit contributions | |
years | -0.002 |
ranger | -0.002 |
tale | -0.002 |
banquet | -0.002 |
clearing | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -4.24e-03 |
Pos logit contributions | |
ranger | +0.039 |
clearing | +0.036 |
café | +0.036 |
Tooth | +0.036 |
years | +0.036 |
Neg logit contributions | |
its | -0.046 |
apy | -0.043 |
aged | -0.043 |
ower | -0.040 |
isel | -0.040 |
Token | They |
Token ID | 1119 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
ranger | +0.034 |
years | +0.033 |
clearing | +0.032 |
Tooth | +0.032 |
since | +0.032 |
Neg logit contributions | |
its | -0.054 |
ower | -0.050 |
apy | -0.049 |
ikes | -0.049 |
isel | -0.049 |
Token | pretend |
Token ID | 16614 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
ranger | +0.038 |
since | +0.036 |
years | +0.035 |
Prince | +0.034 |
clearing | +0.034 |
Neg logit contributions | |
its | -0.043 |
ower | -0.041 |
aged | -0.039 |
apy | -0.039 |
ikes | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
clearing | +0.047 |
ranger | +0.047 |
Tooth | +0.045 |
years | +0.045 |
since | +0.044 |
Neg logit contributions | |
its | -0.061 |
apy | -0.057 |
ower | -0.057 |
aged | -0.055 |
ikes | -0.055 |
Token | be |
Token ID | 307 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
its | +0.004 |
ower | +0.004 |
apy | +0.004 |
aged | +0.004 |
isel | +0.004 |
Neg logit contributions | |
ranger | -0.004 |
clearing | -0.003 |
years | -0.003 |
enclosure | -0.003 |
Lion | -0.003 |
Token | cow |
Token ID | 9875 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
ranger | +0.027 |
years | +0.026 |
clearing | +0.025 |
since | +0.025 |
café | +0.024 |
Neg logit contributions | |
its | -0.040 |
ower | -0.037 |
apy | -0.036 |
aged | -0.036 |
isel | -0.036 |
Token | boys |
Token ID | 13202 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
clearing | +0.116 |
Tooth | +0.106 |
doorway | +0.102 |
awoke | +0.101 |
nowhere | +0.101 |
Neg logit contributions | |
ower | -0.117 |
its | -0.115 |
ikes | -0.113 |
aged | -0.108 |
iggle | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e-04 |
Pos logit contributions | |
clearing | +0.135 |
ranger | +0.128 |
years | +0.125 |
Tooth | +0.123 |
banquet | +0.120 |
Neg logit contributions | |
its | -0.204 |
ikes | -0.200 |
ower | -0.200 |
aged | -0.188 |
iggle | -0.184 |
Token | robbers |
Token ID | 46988 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
its | +0.001 |
ower | +0.001 |
apy | +0.001 |
isel | +0.001 |
aged | +0.001 |
Neg logit contributions | |
ranger | -0.000 |
years | -0.000 |
clearing | -0.000 |
since | -0.000 |
café | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
its | +0.010 |
ower | +0.009 |
aged | +0.009 |
ikes | +0.009 |
apy | +0.009 |
Neg logit contributions | |
ranger | -0.006 |
Tooth | -0.006 |
clearing | -0.006 |
years | -0.006 |
since | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
ranger | +0.019 |
years | +0.018 |
clearing | +0.018 |
since | +0.017 |
Tooth | +0.017 |
Neg logit contributions | |
its | -0.032 |
ower | -0.030 |
apy | -0.029 |
ikes | -0.029 |
isel | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
ranger | +0.012 |
years | +0.012 |
clearing | +0.012 |
since | +0.011 |
Tooth | +0.011 |
Neg logit contributions | |
its | -0.011 |
ower | -0.010 |
apy | -0.009 |
aged | -0.009 |
isel | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -7.02e-03 |
Pos logit contributions | |
its | +0.035 |
ower | +0.033 |
ikes | +0.033 |
aged | +0.033 |
apy | +0.033 |
Neg logit contributions | |
years | -0.020 |
ranger | -0.020 |
clearing | -0.019 |
banquet | -0.019 |
café | -0.018 |
Token | pretended |
Token ID | 36766 |
Feature activation | +6.31e-03 |
Pos logit contributions | |
its | +0.012 |
aged | +0.011 |
isel | +0.011 |
apy | +0.010 |
ower | +0.010 |
Neg logit contributions | |
years | -0.012 |
clearing | -0.011 |
ranger | -0.011 |
cafe | -0.011 |
café | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -5.86e-03 |
Pos logit contributions | |
clearing | +0.008 |
years | +0.008 |
ranger | +0.008 |
Tooth | +0.008 |
café | +0.008 |
Neg logit contributions | |
its | -0.012 |
aged | -0.012 |
ower | -0.012 |
apy | -0.012 |
ikes | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
its | +0.011 |
ower | +0.010 |
apy | +0.010 |
aged | +0.010 |
isel | +0.010 |
Neg logit contributions | |
ranger | -0.010 |
years | -0.009 |
since | -0.009 |
clearing | -0.009 |
dentist | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
ranger | +0.016 |
years | +0.015 |
clearing | +0.015 |
since | +0.015 |
café | +0.014 |
Neg logit contributions | |
its | -0.027 |
ower | -0.025 |
apy | -0.025 |
aged | -0.024 |
isel | -0.024 |
Token | doctor |
Token ID | 6253 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
years | +0.012 |
ranger | +0.012 |
since | +0.012 |
café | +0.011 |
clearing | +0.011 |
Neg logit contributions | |
its | -0.017 |
ower | -0.016 |
isel | -0.015 |
apy | -0.015 |
aged | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
clearing | +0.127 |
years | +0.118 |
café | +0.118 |
banquet | +0.117 |
Tooth | +0.117 |
Neg logit contributions | |
aged | -0.187 |
its | -0.187 |
ower | -0.187 |
ikes | -0.180 |
ged | -0.171 |
Token | fixed |
Token ID | 5969 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
ranger | +0.011 |
years | +0.010 |
clearing | +0.010 |
since | +0.010 |
café | +0.010 |
Neg logit contributions | |
its | -0.016 |
ower | -0.015 |
apy | -0.015 |
aged | -0.015 |
isel | -0.015 |
Token | Billy |
Token ID | 15890 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
its | +0.048 |
ower | +0.046 |
apy | +0.044 |
isel | +0.044 |
aged | +0.043 |
Neg logit contributions | |
ranger | -0.025 |
years | -0.023 |
since | -0.023 |
clearing | -0.022 |
Prince | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
its | +0.246 |
ower | +0.234 |
apy | +0.232 |
isel | +0.231 |
aged | +0.226 |
Neg logit contributions | |
ranger | -0.049 |
years | -0.044 |
since | -0.043 |
clearing | -0.039 |
café | -0.036 |
Token | broken |
Token ID | 5445 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ranger | +0.035 |
dentist | +0.034 |
cave | +0.033 |
chest | +0.033 |
years | +0.033 |
Neg logit contributions | |
its | -0.044 |
apy | -0.040 |
ikes | -0.038 |
ower | -0.037 |
isel | -0.037 |
Token | " |
Token ID | 366 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
its | +0.028 |
ower | +0.027 |
apy | +0.027 |
aged | +0.026 |
isel | +0.026 |
Neg logit contributions | |
ranger | -0.019 |
years | -0.018 |
since | -0.017 |
café | -0.017 |
Tooth | -0.017 |
Token | So |
Token ID | 2396 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
its | +0.082 |
ower | +0.077 |
apy | +0.075 |
isel | +0.075 |
aged | +0.074 |
Neg logit contributions | |
ranger | -0.046 |
years | -0.043 |
clearing | -0.042 |
since | -0.042 |
café | -0.041 |
Token | when |
Token ID | 618 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
ranger | +0.001 |
years | +0.001 |
clearing | +0.001 |
café | +0.001 |
Tooth | +0.001 |
Neg logit contributions | |
its | -0.002 |
apy | -0.002 |
ower | -0.002 |
isel | -0.002 |
aged | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
its | +0.036 |
ower | +0.034 |
apy | +0.034 |
isel | +0.033 |
aged | +0.033 |
Neg logit contributions | |
ranger | -0.023 |
years | -0.021 |
clearing | -0.021 |
café | -0.021 |
since | -0.021 |
Token | sky |
Token ID | 6766 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
ranger | +0.027 |
since | +0.026 |
years | +0.025 |
café | +0.024 |
Prince | +0.024 |
Neg logit contributions | |
its | -0.037 |
ower | -0.036 |
apy | -0.034 |
aged | -0.033 |
isel | -0.033 |
Token | closes |
Token ID | 20612 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
ranger | +0.049 |
years | +0.046 |
clearing | +0.045 |
since | +0.045 |
Tooth | +0.044 |
Neg logit contributions | |
its | -0.068 |
ower | -0.062 |
apy | -0.061 |
aged | -0.060 |
isel | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
ranger | +0.129 |
years | +0.117 |
clearing | +0.114 |
café | +0.114 |
Tooth | +0.113 |
Neg logit contributions | |
its | -0.207 |
ower | -0.194 |
apy | -0.191 |
aged | -0.187 |
isel | -0.187 |
Token | I |
Token ID | 314 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
its | +0.010 |
ower | +0.009 |
apy | +0.009 |
isel | +0.009 |
aged | +0.009 |
Neg logit contributions | |
ranger | -0.007 |
years | -0.006 |
clearing | -0.006 |
café | -0.006 |
since | -0.006 |
Token | won |
Token ID | 1839 |
Feature activation | -4.50e-03 |
Pos logit contributions | |
ranger | +0.044 |
years | +0.043 |
clearing | +0.042 |
since | +0.042 |
Fairy | +0.041 |
Neg logit contributions | |
its | -0.046 |
ower | -0.043 |
ikes | -0.042 |
apy | -0.041 |
aged | -0.041 |
Token | 't |
Token ID | 470 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
its | +0.009 |
ower | +0.009 |
isel | +0.008 |
apy | +0.008 |
aged | +0.008 |
Neg logit contributions | |
ranger | -0.006 |
years | -0.006 |
since | -0.006 |
clearing | -0.006 |
Fairy | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | +6.82e-03 |
Pos logit contributions | |
ranger | +0.005 |
years | +0.005 |
since | +0.005 |
clearing | +0.005 |
Tooth | +0.005 |
Neg logit contributions | |
its | -0.005 |
ower | -0.004 |
apy | -0.004 |
aged | -0.004 |
ikes | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
its | +0.020 |
ower | +0.018 |
apy | +0.018 |
isel | +0.018 |
aged | +0.018 |
Neg logit contributions | |
ranger | -0.007 |
years | -0.006 |
since | -0.006 |
clearing | -0.006 |
café | -0.006 |
Token | there |
Token ID | 612 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ranger | +0.041 |
clearing | +0.039 |
since | +0.039 |
years | +0.037 |
nowhere | +0.036 |
Neg logit contributions | |
its | -0.142 |
ower | -0.133 |
isel | -0.131 |
ikes | -0.130 |
aged | -0.129 |
Token | was |
Token ID | 373 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
its | +0.030 |
ower | +0.029 |
isel | +0.029 |
ikes | +0.028 |
aged | +0.028 |
Neg logit contributions | |
ranger | -0.010 |
years | -0.010 |
clearing | -0.010 |
since | -0.009 |
café | -0.009 |
Token | an |
Token ID | 281 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
ranger | +0.078 |
years | +0.068 |
since | +0.068 |
café | +0.067 |
clearing | +0.066 |
Neg logit contributions | |
its | -0.111 |
apy | -0.107 |
ower | -0.104 |
aged | -0.101 |
ikes | -0.101 |
Token | old |
Token ID | 1468 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ranger | +0.081 |
clearing | +0.076 |
since | +0.075 |
years | +0.075 |
café | +0.073 |
Neg logit contributions | |
its | -0.095 |
ower | -0.090 |
isel | -0.085 |
aged | -0.085 |
apy | -0.085 |
Token | lady |
Token ID | 10846 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
years | +0.040 |
since | +0.040 |
ranger | +0.038 |
clearing | +0.037 |
THE | +0.036 |
Neg logit contributions | |
ower | -0.059 |
its | -0.055 |
apy | -0.054 |
aged | -0.053 |
ikes | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
ranger | +0.142 |
clearing | +0.137 |
grizz | +0.137 |
Prince | +0.135 |
Tooth | +0.134 |
Neg logit contributions | |
its | -0.192 |
aged | -0.191 |
ower | -0.190 |
ot | -0.178 |
iggle | -0.174 |
Token | She |
Token ID | 1375 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
ranger | +0.053 |
years | +0.051 |
clearing | +0.050 |
Tooth | +0.049 |
since | +0.049 |
Neg logit contributions | |
its | -0.072 |
ower | -0.068 |
apy | -0.068 |
aged | -0.066 |
ikes | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
clearing | +0.082 |
ranger | +0.082 |
enclosure | +0.081 |
since | +0.078 |
Prince | +0.078 |
Neg logit contributions | |
its | -0.079 |
ower | -0.075 |
aged | -0.075 |
apy | -0.073 |
ikes | -0.068 |
Token | very |
Token ID | 845 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
ranger | +0.018 |
years | +0.017 |
since | +0.017 |
clearing | +0.016 |
café | +0.016 |
Neg logit contributions | |
its | -0.026 |
ower | -0.024 |
aged | -0.024 |
apy | -0.024 |
isel | -0.023 |
Token | old |
Token ID | 1468 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ranger | +0.035 |
years | +0.033 |
café | +0.030 |
Princess | +0.030 |
Prince | +0.030 |
Neg logit contributions | |
its | -0.054 |
ikes | -0.051 |
isel | -0.051 |
ower | -0.048 |
apy | -0.048 |
Token | So |
Token ID | 1406 |
Feature activation | -9.99e-03 |
Pos logit contributions | |
ranger | +0.018 |
clearing | +0.017 |
years | +0.017 |
banquet | +0.016 |
enclosure | +0.016 |
Neg logit contributions | |
its | -0.026 |
apy | -0.025 |
aged | -0.025 |
ower | -0.025 |
ikes | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
apy | +0.020 |
aged | +0.019 |
its | +0.019 |
ower | +0.018 |
iggle | +0.017 |
Neg logit contributions | |
ranger | -0.015 |
clearing | -0.014 |
enclosure | -0.014 |
dentist | -0.013 |
café | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
apy | +0.050 |
its | +0.048 |
aged | +0.047 |
ower | +0.045 |
ikes | +0.044 |
Neg logit contributions | |
ranger | -0.053 |
clearing | -0.051 |
enclosure | -0.050 |
years | -0.050 |
banquet | -0.048 |
Token | looked |
Token ID | 3114 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
ranger | +0.021 |
years | +0.020 |
since | +0.020 |
clearing | +0.020 |
café | +0.019 |
Neg logit contributions | |
its | -0.028 |
ower | -0.026 |
apy | -0.025 |
ikes | -0.025 |
isel | -0.025 |
Token | around |
Token ID | 1088 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
its | +0.005 |
isel | +0.005 |
aged | +0.005 |
apy | +0.005 |
ower | +0.005 |
Neg logit contributions | |
ranger | -0.005 |
Tooth | -0.005 |
café | -0.005 |
dentist | -0.005 |
years | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
its | +0.074 |
apy | +0.070 |
ower | +0.070 |
aged | +0.070 |
ged | +0.069 |
Neg logit contributions | |
ranger | -0.053 |
Tooth | -0.049 |
enclosure | -0.049 |
café | -0.049 |
banquet | -0.048 |
Token | found |
Token ID | 1043 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
ranger | +0.019 |
years | +0.018 |
clearing | +0.017 |
café | +0.017 |
Tooth | +0.017 |
Neg logit contributions | |
its | -0.028 |
ower | -0.026 |
apy | -0.026 |
aged | -0.026 |
isel | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
its | +0.099 |
ower | +0.096 |
ikes | +0.091 |
isel | +0.091 |
aged | +0.089 |
Neg logit contributions | |
ranger | -0.037 |
clearing | -0.034 |
years | -0.033 |
since | -0.033 |
Prince | -0.033 |
Token | new |
Token ID | 649 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
ranger | +0.027 |
years | +0.027 |
since | +0.026 |
clearing | +0.025 |
café | +0.025 |
Neg logit contributions | |
its | -0.026 |
ower | -0.024 |
apy | -0.024 |
isel | -0.023 |
aged | -0.023 |
Token | spoon |
Token ID | 24556 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ranger | +0.095 |
years | +0.091 |
since | +0.087 |
clearing | +0.086 |
Prince | +0.085 |
Neg logit contributions | |
its | -0.102 |
ower | -0.095 |
apy | -0.093 |
isel | -0.091 |
aged | -0.090 |
Token | that |
Token ID | 326 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
its | +0.043 |
ower | +0.041 |
aged | +0.040 |
apy | +0.040 |
ikes | +0.039 |
Neg logit contributions | |
ranger | -0.025 |
years | -0.024 |
clearing | -0.023 |
Tooth | -0.023 |
café | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | -7.44e-03 |
Pos logit contributions | |
ranger | +0.013 |
years | +0.012 |
clearing | +0.012 |
since | +0.012 |
café | +0.011 |
Neg logit contributions | |
its | -0.019 |
ower | -0.018 |
apy | -0.018 |
isel | -0.017 |
aged | -0.017 |
Token | Hello |
Token ID | 15496 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
its | +0.019 |
ower | +0.018 |
apy | +0.017 |
ikes | +0.017 |
aged | +0.017 |
Neg logit contributions | |
ranger | -0.007 |
years | -0.006 |
clearing | -0.006 |
since | -0.006 |
café | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ranger | +0.056 |
years | +0.052 |
clearing | +0.051 |
Tooth | +0.050 |
dentist | +0.050 |
Neg logit contributions | |
its | -0.076 |
ower | -0.073 |
ikes | -0.069 |
apy | -0.068 |
aged | -0.066 |
Token | c |
Token ID | 269 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ranger | +0.024 |
years | +0.023 |
clearing | +0.022 |
since | +0.022 |
café | +0.021 |
Neg logit contributions | |
its | -0.029 |
ower | -0.027 |
apy | -0.026 |
ikes | -0.025 |
isel | -0.025 |
Token | actus |
Token ID | 34144 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
ranger | +0.048 |
years | +0.046 |
clearing | +0.044 |
since | +0.043 |
café | +0.043 |
Neg logit contributions | |
its | -0.097 |
apy | -0.090 |
ower | -0.090 |
isel | -0.090 |
aged | -0.089 |
Token | ! |
Token ID | 0 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
clearing | +0.021 |
amusement | +0.021 |
Tooth | +0.021 |
dentist | +0.021 |
ranger | +0.021 |
Neg logit contributions | |
its | -0.027 |
ower | -0.026 |
iggle | -0.024 |
apy | -0.023 |
ikes | -0.023 |
Token | Can |
Token ID | 1680 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
apy | +0.009 |
its | +0.009 |
ower | +0.008 |
ikes | +0.008 |
isel | +0.008 |
Neg logit contributions | |
years | -0.007 |
ranger | -0.007 |
dentist | -0.007 |
clearing | -0.006 |
café | -0.006 |
Token | I |
Token ID | 314 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
ranger | +0.026 |
clearing | +0.025 |
café | +0.025 |
years | +0.024 |
cafe | +0.024 |
Neg logit contributions | |
its | -0.033 |
apy | -0.032 |
ower | -0.030 |
ikes | -0.030 |
aged | -0.030 |
Token | sit |
Token ID | 1650 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
ranger | +0.061 |
years | +0.059 |
clearing | +0.058 |
since | +0.057 |
café | +0.057 |
Neg logit contributions | |
its | -0.051 |
ower | -0.046 |
apy | -0.045 |
isel | -0.044 |
aged | -0.043 |
Token | on |
Token ID | 319 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
ranger | +0.058 |
clearing | +0.053 |
café | +0.052 |
dentist | +0.052 |
Tooth | +0.052 |
Neg logit contributions | |
its | -0.059 |
ower | -0.059 |
aged | -0.055 |
apy | -0.054 |
ikes | -0.054 |
Token | you |
Token ID | 345 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
its | +0.036 |
apy | +0.035 |
ower | +0.033 |
ikes | +0.032 |
iggle | +0.031 |
Neg logit contributions | |
ranger | -0.031 |
clearing | -0.027 |
café | -0.027 |
since | -0.026 |
banquet | -0.026 |
Token | by |
Token ID | 416 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
its | +0.080 |
ower | +0.073 |
aged | +0.073 |
apy | +0.071 |
ikes | +0.070 |
Neg logit contributions | |
Tooth | -0.066 |
ranger | -0.063 |
years | -0.063 |
clearing | -0.062 |
Fairy | -0.062 |
Token | heard |
Token ID | 2982 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
ranger | +0.031 |
years | +0.029 |
clearing | +0.029 |
since | +0.029 |
Tooth | +0.029 |
Neg logit contributions | |
its | -0.055 |
ower | -0.051 |
apy | -0.050 |
aged | -0.050 |
isel | -0.049 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
ranger | +0.070 |
clearing | +0.069 |
years | +0.066 |
since | +0.066 |
Tooth | +0.066 |
Neg logit contributions | |
its | -0.089 |
apy | -0.078 |
ower | -0.076 |
ikes | -0.075 |
aged | -0.075 |
Token | 's |
Token ID | 338 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
ranger | +0.013 |
years | +0.012 |
since | +0.011 |
clearing | +0.011 |
café | +0.010 |
Neg logit contributions | |
its | -0.041 |
ower | -0.039 |
apy | -0.039 |
isel | -0.039 |
aged | -0.038 |
Token | cries |
Token ID | 24691 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ranger | +0.075 |
years | +0.070 |
clearing | +0.067 |
since | +0.066 |
café | +0.066 |
Neg logit contributions | |
its | -0.121 |
ower | -0.113 |
apy | -0.111 |
isel | -0.110 |
aged | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
ranger | +0.019 |
years | +0.018 |
clearing | +0.017 |
since | +0.017 |
café | +0.016 |
Neg logit contributions | |
its | -0.041 |
ower | -0.038 |
apy | -0.038 |
isel | -0.037 |
aged | -0.037 |
Token | He |
Token ID | 679 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
years | +0.007 |
tale | +0.007 |
Tooth | +0.007 |
banquet | +0.007 |
clearing | +0.007 |
Neg logit contributions | |
its | -0.009 |
apy | -0.008 |
ower | -0.008 |
aged | -0.008 |
isel | -0.008 |
Token | came |
Token ID | 1625 |
Feature activation | -3.51e-03 |
Pos logit contributions | |
since | +0.005 |
Tooth | +0.005 |
ranger | +0.005 |
years | +0.005 |
Prince | +0.005 |
Neg logit contributions | |
its | -0.005 |
aged | -0.005 |
apy | -0.005 |
isel | -0.004 |
ower | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
its | +0.007 |
ower | +0.007 |
apy | +0.006 |
isel | +0.006 |
aged | +0.006 |
Neg logit contributions | |
ranger | -0.005 |
years | -0.005 |
clearing | -0.005 |
since | -0.005 |
café | -0.005 |
Token | see |
Token ID | 766 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
ranger | +0.060 |
years | +0.058 |
since | +0.056 |
clearing | +0.056 |
café | +0.055 |
Neg logit contributions | |
its | -0.080 |
ower | -0.073 |
apy | -0.073 |
isel | -0.072 |
aged | -0.071 |
Token | what |
Token ID | 644 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ranger | +0.078 |
years | +0.075 |
clearing | +0.074 |
since | +0.072 |
café | +0.072 |
Neg logit contributions | |
its | -0.104 |
apy | -0.093 |
ower | -0.092 |
isel | -0.091 |
aged | -0.091 |
Token | with |
Token ID | 351 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Tooth | +0.012 |
ranger | +0.012 |
dentist | +0.012 |
Fairy | +0.011 |
Prince | +0.011 |
Neg logit contributions | |
its | -0.015 |
ower | -0.014 |
apy | -0.014 |
ikes | -0.014 |
iggle | -0.013 |
Token | Be |
Token ID | 1355 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ranger | +0.026 |
years | +0.025 |
clearing | +0.024 |
since | +0.024 |
café | +0.023 |
Neg logit contributions | |
its | -0.033 |
ower | -0.031 |
apy | -0.030 |
isel | -0.030 |
aged | -0.030 |
Token | cca |
Token ID | 13227 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
years | +0.055 |
ranger | +0.053 |
since | +0.050 |
clearing | +0.050 |
café | +0.048 |
Neg logit contributions | |
its | -0.065 |
apy | -0.060 |
ower | -0.059 |
isel | -0.059 |
ikes | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -9.34e-03 |
Pos logit contributions | |
ranger | +0.008 |
Tooth | +0.008 |
clearing | +0.008 |
years | +0.007 |
café | +0.007 |
Neg logit contributions | |
its | -0.013 |
ower | -0.013 |
aged | -0.013 |
apy | -0.012 |
ikes | -0.012 |
Token | but |
Token ID | 475 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
its | +0.018 |
aged | +0.018 |
ower | +0.018 |
apy | +0.017 |
ikes | +0.017 |
Neg logit contributions | |
ranger | -0.012 |
years | -0.011 |
banquet | -0.011 |
Tooth | -0.011 |
clearing | -0.011 |
Token | Be |
Token ID | 1355 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
café | +0.026 |
years | +0.025 |
ranger | +0.025 |
banquet | +0.025 |
Tooth | +0.025 |
Neg logit contributions | |
aged | -0.036 |
apy | -0.036 |
its | -0.035 |
ower | -0.034 |
isel | -0.033 |
Token | cca |
Token ID | 13227 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
ranger | +0.051 |
years | +0.051 |
since | +0.048 |
clearing | +0.048 |
café | +0.046 |
Neg logit contributions | |
its | -0.061 |
ower | -0.056 |
apy | -0.055 |
ikes | -0.055 |
isel | -0.054 |
Token | was |
Token ID | 373 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
ranger | +0.015 |
clearing | +0.014 |
years | +0.014 |
Tooth | +0.014 |
since | +0.013 |
Neg logit contributions | |
its | -0.022 |
ower | -0.021 |
apy | -0.020 |
aged | -0.020 |
isel | -0.020 |
Token | scared |
Token ID | 12008 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ranger | +0.002 |
café | +0.002 |
Tooth | +0.002 |
Prince | +0.002 |
since | +0.002 |
Neg logit contributions | |
its | -0.003 |
aged | -0.003 |
apy | -0.003 |
ower | -0.003 |
isel | -0.003 |
Token | so |
Token ID | 523 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
ranger | +0.035 |
clearing | +0.033 |
Tooth | +0.033 |
café | +0.032 |
years | +0.032 |
Neg logit contributions | |
its | -0.050 |
ower | -0.047 |
apy | -0.045 |
aged | -0.045 |
ikes | -0.045 |
Token | Joe |
Token ID | 5689 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
its | +0.092 |
ower | +0.087 |
isel | +0.085 |
ikes | +0.084 |
aged | +0.084 |
Neg logit contributions | |
ranger | -0.046 |
years | -0.043 |
since | -0.041 |
clearing | -0.040 |
café | -0.039 |
Token | very |
Token ID | 845 |
Feature activation | -6.58e-03 |
Pos logit contributions | |
its | +0.030 |
isel | +0.028 |
ower | +0.028 |
ikes | +0.027 |
apy | +0.026 |
Neg logit contributions | |
ranger | -0.023 |
years | -0.022 |
since | -0.022 |
� | -0.021 |
café | -0.021 |
Token | scared |
Token ID | 12008 |
Feature activation | -7.85e-04 |
Pos logit contributions | |
ikes | +0.013 |
isel | +0.013 |
ower | +0.013 |
its | +0.013 |
ged | +0.013 |
Neg logit contributions | |
years | -0.008 |
ranger | -0.008 |
� | -0.007 |
more | -0.007 |
too | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +9.25e-03 |
Pos logit contributions | |
its | +0.002 |
ower | +0.002 |
aged | +0.002 |
ikes | +0.002 |
apy | +0.002 |
Neg logit contributions | |
ranger | -0.001 |
clearing | -0.001 |
Tooth | -0.001 |
café | -0.001 |
banquet | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ranger | +0.013 |
years | +0.012 |
since | +0.012 |
Prince | +0.011 |
Tooth | +0.011 |
Neg logit contributions | |
its | -0.020 |
ower | -0.019 |
ikes | -0.018 |
isel | -0.018 |
apy | -0.017 |
Token | started |
Token ID | 2067 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ranger | +0.044 |
years | +0.041 |
since | +0.040 |
clearing | +0.040 |
café | +0.039 |
Neg logit contributions | |
its | -0.052 |
ower | -0.048 |
isel | -0.046 |
ikes | -0.046 |
apy | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
its | +0.023 |
ower | +0.022 |
apy | +0.021 |
aged | +0.021 |
isel | +0.021 |
Neg logit contributions | |
ranger | -0.012 |
years | -0.011 |
clearing | -0.011 |
since | -0.011 |
Tooth | -0.011 |
Token | cry |
Token ID | 3960 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
ranger | +0.006 |
years | +0.006 |
café | +0.006 |
clearing | +0.006 |
since | +0.006 |
Neg logit contributions | |
its | -0.005 |
ower | -0.005 |
apy | -0.005 |
ikes | -0.005 |
isel | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.97e-04 |
Pos logit contributions | |
ranger | +0.023 |
years | +0.021 |
since | +0.021 |
clearing | +0.020 |
Tooth | +0.019 |
Neg logit contributions | |
its | -0.059 |
ower | -0.055 |
isel | -0.055 |
apy | -0.054 |
aged | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +6.98e-03 |
Pos logit contributions | |
its | +0.001 |
ower | +0.001 |
apy | +0.001 |
isel | +0.001 |
aged | +0.001 |
Neg logit contributions | |
ranger | -0.000 |
years | -0.000 |
since | -0.000 |
clearing | -0.000 |
café | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ranger | +0.005 |
years | +0.004 |
since | +0.004 |
clearing | +0.004 |
café | +0.004 |
Neg logit contributions | |
its | -0.019 |
ower | -0.019 |
isel | -0.018 |
apy | -0.018 |
aged | -0.018 |
Token | Her |
Token ID | 9360 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
ranger | +0.019 |
years | +0.018 |
since | +0.018 |
clearing | +0.017 |
café | +0.017 |
Neg logit contributions | |
its | -0.036 |
ower | -0.034 |
apy | -0.033 |
isel | -0.033 |
aged | -0.033 |
Token | come |
Token ID | 1282 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
ranger | +0.032 |
since | +0.031 |
clearing | +0.031 |
years | +0.030 |
Fairy | +0.030 |
Neg logit contributions | |
its | -0.047 |
aged | -0.044 |
apy | -0.044 |
ower | -0.043 |
isel | -0.043 |
Token | home |
Token ID | 1363 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
ranger | +0.012 |
years | +0.012 |
clearing | +0.012 |
Tooth | +0.011 |
since | +0.011 |
Neg logit contributions | |
its | -0.018 |
ower | -0.017 |
apy | -0.017 |
aged | -0.017 |
isel | -0.017 |
Token | early |
Token ID | 1903 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
clearing | +0.039 |
ranger | +0.038 |
Prince | +0.038 |
Tooth | +0.037 |
Fairy | +0.037 |
Neg logit contributions | |
its | -0.057 |
ower | -0.054 |
aged | -0.053 |
apy | -0.051 |
iggle | -0.049 |
Token | from |
Token ID | 422 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
Fairy | +0.165 |
clearing | +0.165 |
Prince | +0.162 |
ranger | +0.162 |
Tooth | +0.161 |
Neg logit contributions | |
its | -0.192 |
ower | -0.186 |
aged | -0.177 |
ikes | -0.170 |
ged | -0.170 |
Token | work |
Token ID | 670 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
ranger | +0.039 |
years | +0.037 |
clearing | +0.036 |
since | +0.035 |
café | +0.034 |
Neg logit contributions | |
its | -0.062 |
ower | -0.058 |
apy | -0.057 |
ikes | -0.056 |
isel | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ranger | +0.006 |
years | +0.006 |
clearing | +0.006 |
since | +0.006 |
café | +0.006 |
Neg logit contributions | |
its | -0.013 |
ower | -0.012 |
apy | -0.012 |
aged | -0.012 |
isel | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
its | +0.029 |
ower | +0.027 |
apy | +0.027 |
isel | +0.026 |
aged | +0.026 |
Neg logit contributions | |
years | -0.017 |
ranger | -0.016 |
since | -0.016 |
clearing | -0.016 |
banquet | -0.015 |
Token | sees |
Token ID | 7224 |
Feature activation | +3.25e-03 |
Pos logit contributions | |
its | +0.015 |
exc | +0.011 |
aged | +0.011 |
apy | +0.011 |
isel | +0.010 |
Neg logit contributions | |
since | -0.016 |
ranger | -0.015 |
clearing | -0.015 |
Tooth | -0.015 |
THE | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
ranger | +0.004 |
years | +0.004 |
since | +0.003 |
clearing | +0.003 |
café | +0.003 |
Neg logit contributions | |
its | -0.007 |
ower | -0.007 |
apy | -0.007 |
isel | -0.007 |
aged | -0.007 |
Token | smoke |
Token ID | 7523 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
ranger | +0.035 |
since | +0.033 |
years | +0.032 |
clearing | +0.032 |
café | +0.031 |
Neg logit contributions | |
its | -0.064 |
ower | -0.059 |
apy | -0.057 |
aged | -0.057 |
isel | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
ranger | +0.061 |
years | +0.058 |
clearing | +0.057 |
since | +0.057 |
Tooth | +0.057 |
Neg logit contributions | |
its | -0.121 |
ower | -0.111 |
apy | -0.109 |
aged | -0.107 |
isel | -0.106 |
Token | true |
Token ID | 2081 |
Feature activation | +8.80e-03 |
Pos logit contributions | |
ranger | +0.003 |
since | +0.003 |
years | +0.003 |
clearing | +0.003 |
Prince | +0.002 |
Neg logit contributions | |
its | -0.006 |
ower | -0.005 |
isel | -0.005 |
apy | -0.005 |
aged | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
ranger | +0.011 |
clearing | +0.011 |
café | +0.010 |
Tooth | +0.010 |
grizz | +0.010 |
Neg logit contributions | |
its | -0.018 |
ower | -0.017 |
ikes | -0.017 |
aged | -0.017 |
isel | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
ranger | +0.024 |
years | +0.022 |
since | +0.022 |
clearing | +0.022 |
café | +0.021 |
Neg logit contributions | |
its | -0.038 |
ower | -0.036 |
apy | -0.034 |
isel | -0.034 |
aged | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
ranger | +0.003 |
clearing | +0.002 |
years | +0.002 |
Tooth | +0.002 |
café | +0.002 |
Neg logit contributions | |
its | -0.004 |
ower | -0.003 |
apy | -0.003 |
aged | -0.003 |
isel | -0.003 |
Token | playing |
Token ID | 2712 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
its | +0.036 |
aged | +0.034 |
apy | +0.033 |
ower | +0.033 |
isel | +0.033 |
Neg logit contributions | |
ranger | -0.028 |
clearing | -0.027 |
café | -0.027 |
Tooth | -0.026 |
years | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
its | +0.134 |
ower | +0.124 |
apy | +0.122 |
aged | +0.121 |
isel | +0.120 |
Neg logit contributions | |
ranger | -0.082 |
years | -0.077 |
clearing | -0.075 |
since | -0.075 |
Tooth | -0.074 |
Token | best |
Token ID | 1266 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
its | +0.042 |
isel | +0.039 |
apy | +0.039 |
ower | +0.038 |
aged | +0.038 |
Neg logit contributions | |
ranger | -0.033 |
clearing | -0.031 |
since | -0.031 |
years | -0.031 |
café | -0.030 |
Token | soccer |
Token ID | 11783 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
its | +0.056 |
ower | +0.054 |
aged | +0.053 |
isel | +0.053 |
apy | +0.052 |
Neg logit contributions | |
ranger | -0.041 |
since | -0.038 |
years | -0.037 |
café | -0.035 |
again | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
its | +0.108 |
ower | +0.101 |
apy | +0.098 |
aged | +0.096 |
ikes | +0.096 |
Neg logit contributions | |
ranger | -0.088 |
years | -0.086 |
Tooth | -0.085 |
clearing | -0.085 |
café | -0.084 |
Token | his |
Token ID | 465 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
its | +0.206 |
ower | +0.203 |
ikes | +0.190 |
isel | +0.190 |
apy | +0.189 |
Neg logit contributions | |
ranger | -0.107 |
years | -0.104 |
nowhere | -0.092 |
clearing | -0.092 |
since | -0.091 |
Token | life |
Token ID | 1204 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
its | +0.133 |
isel | +0.122 |
ower | +0.120 |
apy | +0.119 |
aged | +0.118 |
Neg logit contributions | |
ranger | -0.115 |
years | -0.111 |
since | -0.104 |
clearing | -0.102 |
café | -0.102 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
its | +0.015 |
ower | +0.014 |
apy | +0.014 |
isel | +0.014 |
ikes | +0.014 |
Neg logit contributions | |
ranger | -0.009 |
years | -0.008 |
since | -0.008 |
clearing | -0.008 |
café | -0.008 |
Token | off |
Token ID | 572 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
its | +0.069 |
ower | +0.064 |
apy | +0.064 |
aged | +0.064 |
isel | +0.063 |
Neg logit contributions | |
ranger | -0.058 |
years | -0.056 |
Tooth | -0.055 |
clearing | -0.054 |
since | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
its | +0.073 |
apy | +0.069 |
ower | +0.069 |
aged | +0.069 |
isel | +0.066 |
Neg logit contributions | |
ranger | -0.047 |
years | -0.046 |
Tooth | -0.045 |
clearing | -0.044 |
café | -0.044 |
Token | play |
Token ID | 711 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
its | +0.033 |
ower | +0.031 |
ikes | +0.030 |
aged | +0.029 |
isel | +0.029 |
Neg logit contributions | |
ranger | -0.022 |
clearing | -0.021 |
years | -0.021 |
Tooth | -0.020 |
since | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
its | +0.066 |
apy | +0.063 |
ower | +0.063 |
aged | +0.061 |
isel | +0.060 |
Neg logit contributions | |
ranger | -0.042 |
years | -0.039 |
since | -0.039 |
Tooth | -0.039 |
café | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
its | +0.040 |
ower | +0.037 |
apy | +0.037 |
isel | +0.036 |
aged | +0.036 |
Neg logit contributions | |
ranger | -0.019 |
years | -0.018 |
since | -0.017 |
clearing | -0.017 |
café | -0.017 |
Token | never |
Token ID | 1239 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
its | +0.038 |
ower | +0.035 |
apy | +0.034 |
aged | +0.034 |
isel | +0.034 |
Neg logit contributions | |
ranger | -0.025 |
years | -0.024 |
clearing | -0.023 |
since | -0.023 |
café | -0.023 |
Token | let |
Token ID | 1309 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
its | +0.018 |
ower | +0.017 |
aged | +0.017 |
apy | +0.017 |
isel | +0.017 |
Neg logit contributions | |
ranger | -0.016 |
years | -0.016 |
clearing | -0.016 |
Tooth | -0.015 |
café | -0.015 |
Token | go |
Token ID | 467 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
its | +0.049 |
ower | +0.048 |
apy | +0.045 |
ikes | +0.045 |
aged | +0.044 |
Neg logit contributions | |
ranger | -0.022 |
since | -0.021 |
Prince | -0.021 |
dentist | -0.021 |
Tooth | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
its | +0.061 |
ower | +0.057 |
apy | +0.056 |
isel | +0.055 |
aged | +0.055 |
Neg logit contributions | |
ranger | -0.034 |
years | -0.032 |
clearing | -0.032 |
since | -0.031 |
café | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
its | +0.051 |
ower | +0.049 |
ikes | +0.047 |
isel | +0.046 |
aged | +0.046 |
Neg logit contributions | |
years | -0.020 |
ranger | -0.020 |
Tooth | -0.019 |
clearing | -0.019 |
since | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
its | +0.148 |
isel | +0.138 |
ower | +0.137 |
apy | +0.132 |
ikes | +0.131 |
Neg logit contributions | |
ranger | -0.093 |
years | -0.089 |
clearing | -0.086 |
since | -0.083 |
café | -0.080 |
Token | The |
Token ID | 383 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
its | +0.029 |
ower | +0.027 |
apy | +0.027 |
aged | +0.027 |
isel | +0.027 |
Neg logit contributions | |
ranger | -0.020 |
years | -0.019 |
clearing | -0.018 |
since | -0.018 |
Tooth | -0.018 |
Token | people |
Token ID | 661 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
ranger | +0.002 |
since | +0.002 |
years | +0.002 |
Tooth | +0.002 |
clearing | +0.002 |
Neg logit contributions | |
its | -0.003 |
ower | -0.003 |
aged | -0.003 |
apy | -0.003 |
ikes | -0.003 |
Token | wore |
Token ID | 12408 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
its | +0.020 |
ower | +0.019 |
ikes | +0.018 |
isel | +0.018 |
inters | +0.017 |
Neg logit contributions | |
since | -0.011 |
years | -0.011 |
ranger | -0.011 |
clearing | -0.010 |
café | -0.010 |
Token | bright |
Token ID | 6016 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
its | +0.112 |
ower | +0.104 |
isel | +0.101 |
apy | +0.100 |
ikes | +0.099 |
Neg logit contributions | |
ranger | -0.083 |
years | -0.079 |
clearing | -0.077 |
since | -0.076 |
café | -0.075 |
Token | colours |
Token ID | 18915 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
its | +0.034 |
ower | +0.031 |
ikes | +0.030 |
isel | +0.030 |
aged | +0.030 |
Neg logit contributions | |
years | -0.028 |
ranger | -0.028 |
clearing | -0.027 |
since | -0.026 |
café | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
its | +0.146 |
ower | +0.137 |
apy | +0.137 |
aged | +0.135 |
isel | +0.133 |
Neg logit contributions | |
ranger | -0.072 |
Tooth | -0.067 |
years | -0.067 |
clearing | -0.066 |
café | -0.064 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
its | +0.092 |
ower | +0.085 |
ikes | +0.083 |
isel | +0.083 |
aged | +0.079 |
Neg logit contributions | |
ranger | -0.053 |
years | -0.050 |
since | -0.049 |
café | -0.046 |
clearing | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
its | +0.073 |
ower | +0.068 |
isel | +0.067 |
apy | +0.066 |
ikes | +0.066 |
Neg logit contributions | |
ranger | -0.044 |
years | -0.042 |
since | -0.040 |
clearing | -0.039 |
café | -0.038 |
Token | dance |
Token ID | 9280 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
its | +0.056 |
ower | +0.054 |
ikes | +0.052 |
aged | +0.051 |
isel | +0.050 |
Neg logit contributions | |
ranger | -0.044 |
years | -0.042 |
clearing | -0.041 |
café | -0.040 |
cafe | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ranger | +0.049 |
clearing | +0.046 |
years | +0.046 |
Tooth | +0.045 |
since | +0.044 |
Neg logit contributions | |
its | -0.077 |
ower | -0.073 |
apy | -0.072 |
aged | -0.071 |
ikes | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
its | +0.050 |
ower | +0.046 |
apy | +0.046 |
isel | +0.045 |
aged | +0.045 |
Neg logit contributions | |
ranger | -0.027 |
years | -0.025 |
clearing | -0.024 |
since | -0.024 |
café | -0.024 |
Token | air |
Token ID | 1633 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ranger | +0.017 |
since | +0.017 |
years | +0.016 |
grizz | +0.015 |
Tooth | +0.015 |
Neg logit contributions | |
its | -0.021 |
apy | -0.019 |
isel | -0.019 |
ower | -0.018 |
aged | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
ranger | +0.017 |
years | +0.016 |
clearing | +0.016 |
Tooth | +0.015 |
café | +0.015 |
Neg logit contributions | |
its | -0.030 |
ower | -0.028 |
aged | -0.027 |
apy | -0.027 |
isel | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
its | +0.024 |
ower | +0.023 |
isel | +0.022 |
ikes | +0.022 |
aged | +0.022 |
Neg logit contributions | |
ranger | -0.008 |
Prince | -0.007 |
Tooth | -0.007 |
since | -0.007 |
clearing | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
ranger | +0.025 |
years | +0.024 |
clearing | +0.024 |
since | +0.024 |
café | +0.023 |
Neg logit contributions | |
its | -0.028 |
apy | -0.026 |
ower | -0.026 |
aged | -0.025 |
isel | -0.025 |
Token | " |
Token ID | 366 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ranger | +0.008 |
years | +0.007 |
since | +0.007 |
Prince | +0.007 |
Tooth | +0.007 |
Neg logit contributions | |
its | -0.016 |
ower | -0.015 |
ikes | -0.015 |
isel | -0.015 |
aged | -0.015 |
Token | Y |
Token ID | 56 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
its | +0.044 |
isel | +0.043 |
ower | +0.042 |
aged | +0.042 |
apy | +0.042 |
Neg logit contributions | |
ranger | -0.023 |
years | -0.021 |
since | -0.021 |
clearing | -0.021 |
Tooth | -0.021 |
Token | ay |
Token ID | 323 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
its | +0.027 |
isel | +0.026 |
aged | +0.026 |
ower | +0.026 |
apy | +0.025 |
Neg logit contributions | |
ranger | -0.035 |
years | -0.034 |
since | -0.033 |
café | -0.033 |
clearing | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
its | +0.272 |
ower | +0.256 |
apy | +0.252 |
aged | +0.249 |
ikes | +0.248 |
Neg logit contributions | |
ranger | -0.115 |
years | -0.106 |
clearing | -0.105 |
since | -0.103 |
café | -0.100 |
Token | this |
Token ID | 428 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
its | +0.009 |
apy | +0.008 |
ower | +0.008 |
isel | +0.008 |
ikes | +0.008 |
Neg logit contributions | |
ranger | -0.006 |
clearing | -0.006 |
years | -0.006 |
café | -0.006 |
since | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
its | +0.032 |
ower | +0.030 |
isel | +0.030 |
aged | +0.030 |
apy | +0.030 |
Neg logit contributions | |
ranger | -0.016 |
clearing | -0.015 |
years | -0.015 |
since | -0.015 |
café | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
its | +0.014 |
ower | +0.013 |
apy | +0.013 |
aged | +0.013 |
isel | +0.013 |
Neg logit contributions | |
ranger | -0.007 |
years | -0.007 |
clearing | -0.007 |
since | -0.007 |
café | -0.006 |
Token | colour |
Token ID | 9568 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
its | +0.010 |
ower | +0.009 |
aged | +0.009 |
isel | +0.008 |
ikes | +0.008 |
Neg logit contributions | |
café | -0.007 |
ranger | -0.007 |
years | -0.007 |
banquet | -0.007 |
cafe | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
years | +0.022 |
ranger | +0.022 |
since | +0.021 |
café | +0.020 |
clearing | +0.020 |
Neg logit contributions | |
its | -0.044 |
isel | -0.041 |
ower | -0.041 |
aged | -0.040 |
apy | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
years | +0.019 |
Prince | +0.018 |
Tooth | +0.018 |
since | +0.017 |
café | +0.017 |
Neg logit contributions | |
its | -0.028 |
ower | -0.027 |
ikes | -0.025 |
isel | -0.025 |
aged | -0.025 |
Token | cr |
Token ID | 1067 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
its | +0.009 |
ower | +0.008 |
isel | +0.008 |
apy | +0.008 |
aged | +0.008 |
Neg logit contributions | |
ranger | -0.008 |
years | -0.007 |
clearing | -0.007 |
since | -0.007 |
Tooth | -0.007 |
Token | ay |
Token ID | 323 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
years | +0.017 |
ranger | +0.016 |
since | +0.016 |
Tooth | +0.016 |
Fairy | +0.016 |
Neg logit contributions | |
its | -0.013 |
apy | -0.012 |
isel | -0.012 |
ower | -0.012 |
aged | -0.012 |
Token | ons |
Token ID | 684 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
its | +0.224 |
ower | +0.211 |
isel | +0.207 |
apy | +0.203 |
aged | +0.198 |
Neg logit contributions | |
years | -0.206 |
mother | -0.184 |
Tooth | -0.184 |
since | -0.182 |
Fairy | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
its | +0.043 |
ower | +0.042 |
aged | +0.040 |
ikes | +0.039 |
apy | +0.038 |
Neg logit contributions | |
ranger | -0.036 |
clearing | -0.034 |
grizz | -0.033 |
café | -0.033 |
banquet | -0.032 |
Token | She |
Token ID | 1375 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
ranger | +0.013 |
years | +0.012 |
clearing | +0.012 |
since | +0.012 |
café | +0.011 |
Neg logit contributions | |
its | -0.027 |
ower | -0.025 |
apy | -0.025 |
isel | -0.025 |
aged | -0.025 |
Token | used |
Token ID | 973 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
years | +0.040 |
ranger | +0.040 |
since | +0.039 |
Tooth | +0.037 |
clearing | +0.037 |
Neg logit contributions | |
its | -0.058 |
ower | -0.054 |
ikes | -0.053 |
isel | -0.052 |
apy | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
nowhere | +0.011 |
years | +0.011 |
since | +0.011 |
front | +0.011 |
more | +0.010 |
Neg logit contributions | |
ower | -0.023 |
its | -0.022 |
ikes | -0.022 |
oving | -0.021 |
isel | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
its | +0.015 |
ower | +0.014 |
isel | +0.014 |
apy | +0.014 |
aged | +0.014 |
Neg logit contributions | |
ranger | -0.006 |
years | -0.006 |
since | -0.006 |
clearing | -0.006 |
café | -0.005 |
Token | |
Token ID | 220 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
its | +0.047 |
ower | +0.044 |
apy | +0.043 |
aged | +0.043 |
isel | +0.042 |
Neg logit contributions | |
ranger | -0.024 |
years | -0.023 |
clearing | -0.022 |
since | -0.022 |
café | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -8.24e-03 |
Pos logit contributions | |
its | +0.149 |
isel | +0.148 |
ower | +0.140 |
apy | +0.139 |
aged | +0.137 |
Neg logit contributions | |
ranger | -0.021 |
Ms | -0.017 |
clearing | -0.017 |
Mrs | -0.016 |
� | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
its | +0.023 |
isel | +0.022 |
ower | +0.022 |
aged | +0.022 |
apy | +0.021 |
Neg logit contributions | |
ranger | -0.005 |
clearing | -0.005 |
years | -0.004 |
since | -0.004 |
café | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ranger | +0.003 |
years | +0.002 |
clearing | +0.002 |
since | +0.002 |
café | +0.002 |
Neg logit contributions | |
its | -0.005 |
ower | -0.005 |
apy | -0.005 |
aged | -0.005 |
ikes | -0.005 |
Token | little |
Token ID | 1310 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ranger | +0.029 |
clearing | +0.027 |
since | +0.027 |
years | +0.027 |
enclosure | +0.026 |
Neg logit contributions | |
its | -0.044 |
ower | -0.041 |
apy | -0.040 |
aged | -0.040 |
ikes | -0.039 |
Token | girl |
Token ID | 2576 |
Feature activation | -8.47e-03 |
Pos logit contributions | |
its | +0.177 |
ower | +0.165 |
aged | +0.162 |
apy | +0.160 |
isel | +0.159 |
Neg logit contributions | |
ranger | -0.185 |
enclosure | -0.178 |
years | -0.176 |
clearing | -0.174 |
grizz | -0.172 |
Token | was |
Token ID | 373 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
its | +0.015 |
aged | +0.015 |
apy | +0.014 |
iggle | +0.013 |
ower | +0.013 |
Neg logit contributions | |
clearing | -0.013 |
ranger | -0.013 |
Tooth | -0.013 |
Prince | -0.012 |
banquet | -0.012 |
Token | so |
Token ID | 523 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
aged | +0.035 |
its | +0.034 |
apy | +0.033 |
ower | +0.032 |
iggle | +0.030 |
Neg logit contributions | |
ranger | -0.036 |
clearing | -0.035 |
enclosure | -0.035 |
Tooth | -0.035 |
café | -0.034 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
its | +0.120 |
ikes | +0.116 |
isel | +0.112 |
ower | +0.110 |
inters | +0.109 |
Neg logit contributions | |
years | -0.064 |
ranger | -0.062 |
� | -0.061 |
since | -0.059 |
cal | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
aged | +0.042 |
ower | +0.042 |
its | +0.042 |
iggle | +0.040 |
apy | +0.040 |
Neg logit contributions | |
clearing | -0.040 |
enclosure | -0.040 |
grizz | -0.040 |
Tooth | -0.038 |
ranger | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
its | +0.020 |
ower | +0.019 |
isel | +0.018 |
apy | +0.018 |
aged | +0.018 |
Neg logit contributions | |
ranger | -0.012 |
years | -0.011 |
clearing | -0.011 |
since | -0.011 |
café | -0.010 |
Token | play |
Token ID | 711 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
ranger | +0.009 |
years | +0.009 |
clearing | +0.009 |
since | +0.009 |
café | +0.009 |
Neg logit contributions | |
its | -0.009 |
ower | -0.008 |
apy | -0.008 |
isel | -0.008 |
aged | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
its | +0.087 |
apy | +0.081 |
ower | +0.081 |
aged | +0.078 |
ikes | +0.078 |
Neg logit contributions | |
ranger | -0.063 |
years | -0.059 |
since | -0.059 |
Tooth | -0.058 |
café | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -7.02e-04 |
Pos logit contributions | |
its | +0.005 |
ower | +0.005 |
isel | +0.005 |
ikes | +0.005 |
apy | +0.005 |
Neg logit contributions | |
ranger | -0.004 |
years | -0.003 |
since | -0.003 |
clearing | -0.003 |
café | -0.003 |
Token | boss |
Token ID | 6478 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
its | +0.001 |
ower | +0.001 |
apy | +0.001 |
isel | +0.001 |
aged | +0.001 |
Neg logit contributions | |
ranger | -0.001 |
years | -0.001 |
clearing | -0.001 |
since | -0.001 |
café | -0.001 |
Token | y |
Token ID | 88 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
its | +0.020 |
ower | +0.018 |
apy | +0.018 |
isel | +0.017 |
aged | +0.017 |
Neg logit contributions | |
ranger | -0.015 |
years | -0.014 |
since | -0.014 |
clearing | -0.014 |
café | -0.014 |
Token | dog |
Token ID | 3290 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
its | +0.238 |
ower | +0.223 |
apy | +0.216 |
aged | +0.214 |
isel | +0.212 |
Neg logit contributions | |
ranger | -0.161 |
years | -0.154 |
since | -0.150 |
clearing | -0.149 |
Tooth | -0.147 |
Token | again |
Token ID | 757 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
Tooth | +0.006 |
ranger | +0.006 |
clearing | +0.006 |
years | +0.006 |
dentist | +0.006 |
Neg logit contributions | |
its | -0.010 |
ower | -0.009 |
apy | -0.009 |
ikes | -0.009 |
aged | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ranger | +0.080 |
dentist | +0.073 |
Tooth | +0.073 |
clearing | +0.073 |
grizz | +0.073 |
Neg logit contributions | |
its | -0.120 |
ower | -0.115 |
apy | -0.113 |
aged | -0.110 |
ikes | -0.107 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
its | +0.025 |
ower | +0.023 |
apy | +0.023 |
aged | +0.023 |
ikes | +0.023 |
Neg logit contributions | |
ranger | -0.013 |
years | -0.013 |
clearing | -0.012 |
since | -0.012 |
banquet | -0.012 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ranger | +0.050 |
years | +0.048 |
since | +0.047 |
Tooth | +0.046 |
banquet | +0.045 |
Neg logit contributions | |
its | -0.072 |
ower | -0.065 |
apy | -0.065 |
ikes | -0.064 |
aged | -0.062 |
Token | play |
Token ID | 711 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
ranger | +0.023 |
years | +0.022 |
since | +0.021 |
clearing | +0.021 |
Tooth | +0.021 |
Neg logit contributions | |
its | -0.021 |
ower | -0.020 |
aged | -0.019 |
apy | -0.019 |
isel | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
its | +0.087 |
ower | +0.082 |
isel | +0.081 |
apy | +0.080 |
aged | +0.080 |
Neg logit contributions | |
ranger | -0.041 |
years | -0.038 |
clearing | -0.036 |
since | -0.036 |
Tooth | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
its | +0.015 |
ower | +0.014 |
isel | +0.014 |
ikes | +0.014 |
apy | +0.014 |
Neg logit contributions | |
years | -0.008 |
ranger | -0.008 |
dentist | -0.007 |
since | -0.007 |
Tooth | -0.007 |
Token | ash |
Token ID | 12530 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
its | +0.012 |
isel | +0.011 |
apy | +0.011 |
ower | +0.011 |
ikes | +0.011 |
Neg logit contributions | |
ranger | -0.008 |
clearing | -0.007 |
dentist | -0.007 |
years | -0.007 |
cafe | -0.007 |
Token | tr |
Token ID | 2213 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
ranger | +0.030 |
years | +0.029 |
clearing | +0.029 |
since | +0.028 |
café | +0.028 |
Neg logit contributions | |
its | -0.042 |
ower | -0.040 |
ikes | -0.038 |
apy | -0.038 |
aged | -0.037 |
Token | ay |
Token ID | 323 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
its | +0.015 |
aged | +0.014 |
isel | +0.013 |
ower | +0.013 |
apy | +0.013 |
Neg logit contributions | |
ranger | -0.018 |
years | -0.018 |
since | -0.017 |
dentist | -0.017 |
Tooth | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
its | +0.319 |
isel | +0.314 |
apy | +0.301 |
aged | +0.300 |
ower | +0.300 |
Neg logit contributions | |
ranger | -0.132 |
years | -0.131 |
since | -0.124 |
dentist | -0.119 |
Tooth | -0.116 |
Token | It |
Token ID | 632 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
its | +0.030 |
ower | +0.028 |
apy | +0.028 |
aged | +0.027 |
isel | +0.027 |
Neg logit contributions | |
ranger | -0.024 |
years | -0.022 |
clearing | -0.022 |
since | -0.022 |
café | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
its | +0.062 |
ower | +0.057 |
apy | +0.056 |
aged | +0.056 |
ikes | +0.055 |
Neg logit contributions | |
ranger | -0.037 |
years | -0.036 |
clearing | -0.035 |
since | -0.034 |
café | -0.034 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
ranger | +0.059 |
café | +0.058 |
clearing | +0.056 |
cafe | +0.056 |
enclosure | +0.055 |
Neg logit contributions | |
its | -0.058 |
ower | -0.053 |
aged | -0.053 |
apy | -0.052 |
isel | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
ranger | +0.032 |
clearing | +0.031 |
years | +0.030 |
café | +0.029 |
Tooth | +0.029 |
Neg logit contributions | |
its | -0.052 |
ower | -0.048 |
ikes | -0.047 |
aged | -0.046 |
apy | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
its | +0.027 |
apy | +0.025 |
aged | +0.024 |
ower | +0.024 |
isel | +0.024 |
Neg logit contributions | |
ranger | -0.021 |
years | -0.021 |
since | -0.021 |
banquet | -0.020 |
Fairy | -0.020 |
Token | leaves |
Token ID | 5667 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ranger | +0.014 |
years | +0.013 |
since | +0.013 |
clearing | +0.013 |
café | +0.012 |
Neg logit contributions | |
its | -0.021 |
ower | -0.020 |
apy | -0.019 |
aged | -0.019 |
isel | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -7.73e-03 |
Pos logit contributions | |
ranger | +0.012 |
years | +0.012 |
clearing | +0.011 |
Tooth | +0.011 |
café | +0.011 |
Neg logit contributions | |
its | -0.027 |
ower | -0.026 |
apy | -0.025 |
aged | -0.025 |
isel | -0.025 |
Token | scattered |
Token ID | 16830 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
its | +0.014 |
apy | +0.013 |
aged | +0.013 |
ower | +0.012 |
isel | +0.012 |
Neg logit contributions | |
years | -0.012 |
ranger | -0.012 |
clearing | -0.011 |
Tooth | -0.011 |
since | -0.011 |
Token | them |
Token ID | 606 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
its | +0.073 |
apy | +0.066 |
ower | +0.066 |
isel | +0.065 |
aged | +0.065 |
Neg logit contributions | |
ranger | -0.060 |
years | -0.057 |
Tooth | -0.056 |
clearing | -0.056 |
since | -0.055 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
its | +0.191 |
ower | +0.179 |
isel | +0.176 |
apy | +0.175 |
ikes | +0.172 |
Neg logit contributions | |
ranger | -0.114 |
years | -0.107 |
since | -0.104 |
clearing | -0.102 |
café | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
its | +0.288 |
ower | +0.271 |
isel | +0.265 |
aged | +0.264 |
apy | +0.263 |
Neg logit contributions | |
ranger | -0.125 |
years | -0.116 |
since | -0.112 |
clearing | -0.110 |
Tooth | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | +3.98e-03 |
Pos logit contributions | |
its | +0.011 |
apy | +0.011 |
ower | +0.010 |
aged | +0.010 |
isel | +0.010 |
Neg logit contributions | |
years | -0.007 |
ranger | -0.006 |
since | -0.006 |
clearing | -0.006 |
banquet | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ranger | +0.004 |
years | +0.003 |
clearing | +0.003 |
since | +0.003 |
café | +0.003 |
Neg logit contributions | |
its | -0.010 |
ower | -0.010 |
aged | -0.009 |
isel | -0.009 |
apy | -0.009 |
Token | S |
Token ID | 50 |
Feature activation | -3.72e-05 |
Pos logit contributions | |
ranger | +0.017 |
years | +0.016 |
Tooth | +0.016 |
Prince | +0.016 |
Fairy | +0.016 |
Neg logit contributions | |
its | -0.025 |
apy | -0.024 |
ower | -0.024 |
aged | -0.023 |
isel | -0.023 |
Token | ara |
Token ID | 3301 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
its | +0.000 |
ower | +0.000 |
ikes | +0.000 |
oom | +0.000 |
isel | +0.000 |
Neg logit contributions | |
Prince | -0.000 |
ranger | -0.000 |
years | -0.000 |
clearing | -0.000 |
Fairy | -0.000 |