Token | - |
Token ID | 12 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Thank | +0.034 |
ury | +0.030 |
wo | +0.029 |
ives | +0.029 |
vitamins | +0.029 |
Neg logit contributions | |
flower | -0.034 |
ble | -0.030 |
ric | -0.028 |
itating | -0.028 |
increasingly | -0.027 |
Token | up |
Token ID | 929 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Thank | +0.017 |
vitamins | +0.015 |
ury | +0.015 |
wo | +0.014 |
ives | +0.014 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
ric | -0.013 |
itating | -0.013 |
increasingly | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.022 |
itating | +0.018 |
packs | +0.018 |
increasingly | +0.017 |
Neg logit contributions | |
Thank | -0.041 |
leaf | -0.036 |
vitamins | -0.036 |
ury | -0.036 |
Bye | -0.035 |
Token | make |
Token ID | 787 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
flower | +0.024 |
ble | +0.021 |
ric | +0.020 |
increasingly | +0.018 |
packs | +0.018 |
Neg logit contributions | |
Thank | -0.028 |
ives | -0.026 |
ury | -0.025 |
leaf | -0.024 |
Bye | -0.024 |
Token | - |
Token ID | 12 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
flower | +0.120 |
ble | +0.110 |
ric | +0.098 |
itating | +0.098 |
increasingly | +0.095 |
Neg logit contributions | |
Thank | -0.128 |
ury | -0.110 |
ives | -0.108 |
vitamins | -0.106 |
wo | -0.106 |
Token | bel |
Token ID | 6667 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.015 |
itating | +0.014 |
ric | +0.013 |
increasingly | +0.013 |
Neg logit contributions | |
Thank | -0.021 |
ury | -0.018 |
vitamins | -0.018 |
ives | -0.018 |
wo | -0.018 |
Token | ieve |
Token ID | 12311 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ble | +0.223 |
flower | +0.215 |
itating | +0.191 |
increasingly | +0.183 |
ric | +0.181 |
Neg logit contributions | |
Thank | -0.294 |
wo | -0.255 |
ury | -0.252 |
sed | -0.246 |
vitamins | -0.245 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
flower | +0.060 |
ble | +0.053 |
itating | +0.047 |
ric | +0.046 |
increasingly | +0.045 |
Neg logit contributions | |
Thank | -0.072 |
ury | -0.062 |
ives | -0.062 |
vitamins | -0.061 |
wo | -0.061 |
Token | One |
Token ID | 1881 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Thank | +0.007 |
leaf | +0.006 |
ury | +0.006 |
vitamins | +0.006 |
ives | +0.006 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
ric | -0.005 |
itating | -0.005 |
packs | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
itating | +0.018 |
ric | +0.018 |
increasingly | +0.017 |
Neg logit contributions | |
Thank | -0.018 |
ury | -0.015 |
wo | -0.014 |
vitamins | -0.014 |
ives | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Thank | +0.030 |
vitamins | +0.027 |
leaf | +0.027 |
ives | +0.026 |
ury | +0.026 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
itating | -0.021 |
packs | -0.020 |
ric | -0.020 |
Token | red |
Token ID | 2266 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
flower | +0.016 |
ble | +0.015 |
ric | +0.013 |
packs | +0.013 |
increasingly | +0.013 |
Neg logit contributions | |
Thank | -0.016 |
ives | -0.014 |
ury | -0.014 |
leaf | -0.013 |
vitamins | -0.013 |
Token | cape |
Token ID | 36023 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
flower | +0.038 |
ble | +0.034 |
itating | +0.031 |
ric | +0.031 |
increasingly | +0.030 |
Neg logit contributions | |
Thank | -0.030 |
ury | -0.025 |
vitamins | -0.025 |
ives | -0.024 |
wo | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.010 |
itating | +0.009 |
ric | +0.009 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.012 |
vitamins | -0.011 |
ury | -0.010 |
leaf | -0.010 |
wo | -0.010 |
Token | make |
Token ID | 787 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
flower | +0.024 |
ble | +0.021 |
ric | +0.020 |
packs | +0.019 |
increasingly | +0.019 |
Neg logit contributions | |
Thank | -0.029 |
ives | -0.026 |
ury | -0.026 |
leaf | -0.025 |
vitamins | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
flower | +0.112 |
ble | +0.110 |
ric | +0.095 |
itating | +0.094 |
increasingly | +0.094 |
Neg logit contributions | |
Thank | -0.124 |
ury | -0.106 |
ives | -0.106 |
vitamins | -0.103 |
leaf | -0.101 |
Token | bel |
Token ID | 6667 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
flower | +0.010 |
ble | +0.009 |
itating | +0.008 |
ric | +0.008 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.015 |
ury | -0.013 |
ives | -0.013 |
leaf | -0.013 |
vitamins | -0.013 |
Token | ieve |
Token ID | 12311 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ble | +0.209 |
flower | +0.197 |
itating | +0.177 |
increasingly | +0.170 |
ric | +0.167 |
Neg logit contributions | |
Thank | -0.295 |
wo | -0.257 |
ury | -0.256 |
sed | -0.252 |
vitamins | -0.248 |
Token | he |
Token ID | 339 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
flower | +0.063 |
ble | +0.055 |
itating | +0.050 |
ric | +0.050 |
increasingly | +0.048 |
Neg logit contributions | |
Thank | -0.068 |
ury | -0.059 |
vitamins | -0.059 |
ives | -0.058 |
wo | -0.058 |
Token | had |
Token ID | 550 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
flower | +0.072 |
ble | +0.065 |
itating | +0.061 |
ric | +0.060 |
increasingly | +0.058 |
Neg logit contributions | |
Thank | -0.053 |
ury | -0.045 |
vitamins | -0.045 |
wo | -0.044 |
ives | -0.044 |
Token | super |
Token ID | 2208 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
flower | +0.032 |
ble | +0.029 |
packs | +0.027 |
ric | +0.026 |
increasingly | +0.025 |
Neg logit contributions | |
Thank | -0.039 |
ury | -0.033 |
ives | -0.033 |
leaf | -0.032 |
vitamins | -0.032 |
Token | powers |
Token ID | 30132 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
flower | +0.103 |
ble | +0.097 |
itating | +0.087 |
ric | +0.087 |
increasingly | +0.086 |
Neg logit contributions | |
Thank | -0.101 |
ury | -0.085 |
vitamins | -0.084 |
wo | -0.083 |
ives | -0.083 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.009 |
increasingly | +0.008 |
particular | +0.007 |
itating | +0.007 |
Neg logit contributions | |
ives | -0.011 |
Thank | -0.011 |
icol | -0.010 |
forts | -0.010 |
kids | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Thank | +0.010 |
ives | +0.009 |
ury | +0.009 |
vitamins | +0.008 |
leaf | +0.008 |
Neg logit contributions | |
flower | -0.011 |
ble | -0.010 |
ric | -0.009 |
itating | -0.009 |
increasingly | -0.009 |
Token | play |
Token ID | 711 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
flower | +0.032 |
ble | +0.028 |
itating | +0.028 |
ric | +0.027 |
increasingly | +0.026 |
Neg logit contributions | |
Thank | -0.025 |
vitamins | -0.021 |
ury | -0.021 |
wo | -0.021 |
ives | -0.020 |
Token | make |
Token ID | 787 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
flower | +0.058 |
ble | +0.051 |
itating | +0.045 |
increasingly | +0.043 |
ric | +0.043 |
Neg logit contributions | |
Thank | -0.079 |
ury | -0.068 |
vitamins | -0.068 |
ives | -0.068 |
wo | -0.067 |
Token | - |
Token ID | 12 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
flower | +0.109 |
ble | +0.098 |
itating | +0.089 |
ric | +0.087 |
increasingly | +0.085 |
Neg logit contributions | |
Thank | -0.118 |
ury | -0.102 |
vitamins | -0.100 |
ives | -0.099 |
wo | -0.099 |
Token | bel |
Token ID | 6667 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.009 |
ric | +0.008 |
itating | +0.008 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.014 |
ives | -0.013 |
ury | -0.013 |
leaf | -0.012 |
vitamins | -0.012 |
Token | ieve |
Token ID | 12311 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
ble | +0.219 |
flower | +0.218 |
itating | +0.190 |
increasingly | +0.182 |
ric | +0.181 |
Neg logit contributions | |
Thank | -0.277 |
wo | -0.239 |
ury | -0.237 |
vitamins | -0.232 |
ives | -0.229 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-03 |
Pos logit contributions | |
flower | +0.050 |
ble | +0.044 |
itating | +0.040 |
ric | +0.039 |
increasingly | +0.038 |
Neg logit contributions | |
Thank | -0.059 |
ury | -0.051 |
vitamins | -0.050 |
ives | -0.050 |
wo | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Thank | +0.000 |
ury | +0.000 |
leaf | +0.000 |
ives | +0.000 |
wo | +0.000 |
Neg logit contributions | |
flower | -0.000 |
ble | -0.000 |
itating | -0.000 |
ric | -0.000 |
increasingly | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Thank | +0.013 |
ury | +0.011 |
vitamins | +0.011 |
ives | +0.011 |
wo | +0.010 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.013 |
ric | -0.012 |
itating | -0.012 |
increasingly | -0.011 |
Token | One |
Token ID | 3198 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
flower | +0.007 |
ble | +0.006 |
itating | +0.005 |
ric | +0.005 |
increasingly | +0.005 |
Neg logit contributions | |
Thank | -0.015 |
ury | -0.013 |
vitamins | -0.013 |
ives | -0.013 |
wo | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Thank | +0.013 |
ury | +0.012 |
vitamins | +0.011 |
ives | +0.011 |
wo | +0.011 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.013 |
itating | -0.012 |
ric | -0.012 |
increasingly | -0.011 |
Token | they |
Token ID | 484 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
ric | +0.008 |
packs | +0.007 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.009 |
ives | -0.008 |
ury | -0.008 |
leaf | -0.007 |
vitamins | -0.007 |
Token | played |
Token ID | 2826 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
itating | +0.001 |
ric | +0.001 |
increasingly | +0.001 |
Neg logit contributions | |
Thank | -0.001 |
ury | -0.001 |
vitamins | -0.001 |
ives | -0.001 |
wo | -0.001 |
Token | make |
Token ID | 787 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
flower | +0.055 |
ble | +0.050 |
itating | +0.043 |
increasingly | +0.042 |
ric | +0.041 |
Neg logit contributions | |
Thank | -0.081 |
vitamins | -0.071 |
ury | -0.071 |
ives | -0.070 |
wo | -0.070 |
Token | - |
Token ID | 12 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
flower | +0.105 |
ble | +0.095 |
itating | +0.086 |
ric | +0.085 |
increasingly | +0.084 |
Neg logit contributions | |
Thank | -0.102 |
ury | -0.087 |
vitamins | -0.086 |
ives | -0.084 |
wo | -0.084 |
Token | bel |
Token ID | 6667 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
itating | +0.000 |
ric | +0.000 |
increasingly | +0.000 |
Neg logit contributions | |
Thank | -0.001 |
ives | -0.001 |
ury | -0.001 |
leaf | -0.001 |
hugs | -0.001 |
Token | ieve |
Token ID | 12311 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
flower | +0.211 |
ble | +0.208 |
itating | +0.185 |
increasingly | +0.176 |
ric | +0.175 |
Neg logit contributions | |
Thank | -0.264 |
wo | -0.229 |
ury | -0.227 |
vitamins | -0.225 |
sed | -0.219 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
flower | +0.047 |
ble | +0.042 |
itating | +0.038 |
ric | +0.038 |
increasingly | +0.036 |
Neg logit contributions | |
Thank | -0.052 |
ury | -0.045 |
vitamins | -0.045 |
ives | -0.044 |
wo | -0.044 |
Token | Finally |
Token ID | 9461 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
Thank | +0.001 |
leaf | +0.001 |
ury | +0.001 |
vitamins | +0.001 |
wo | +0.001 |
Neg logit contributions | |
flower | -0.001 |
ble | -0.001 |
ric | -0.001 |
itating | -0.001 |
increasingly | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Thank | +0.044 |
ury | +0.038 |
vitamins | +0.037 |
ives | +0.037 |
leaf | +0.037 |
Neg logit contributions | |
flower | -0.048 |
ble | -0.044 |
itating | -0.040 |
ric | -0.039 |
increasingly | -0.038 |
Token | they |
Token ID | 484 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Thank | +0.056 |
ury | +0.043 |
Happy | +0.043 |
wo | +0.042 |
thank | +0.041 |
Neg logit contributions | |
flower | -0.107 |
ble | -0.096 |
ric | -0.096 |
itating | -0.091 |
packs | -0.088 |
Token | he |
Token ID | 339 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
flower | +0.065 |
ric | +0.055 |
ble | +0.055 |
itating | +0.055 |
burn | +0.055 |
Neg logit contributions | |
Thank | -0.034 |
Happy | -0.027 |
hours | -0.026 |
thank | -0.026 |
vitamins | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
flower | +0.035 |
ble | +0.031 |
itating | +0.029 |
ric | +0.029 |
increasingly | +0.029 |
Neg logit contributions | |
Thank | -0.026 |
vitamins | -0.022 |
ury | -0.022 |
ives | -0.021 |
leaf | -0.021 |
Token | playing |
Token ID | 2712 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
flower | +0.032 |
ble | +0.028 |
ric | +0.027 |
itating | +0.026 |
increasingly | +0.026 |
Neg logit contributions | |
Thank | -0.024 |
ury | -0.020 |
wo | -0.020 |
hugs | -0.020 |
leaf | -0.020 |
Token | make |
Token ID | 787 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
flower | +0.028 |
ble | +0.024 |
ric | +0.023 |
itating | +0.022 |
increasingly | +0.021 |
Neg logit contributions | |
Thank | -0.032 |
ury | -0.028 |
vitamins | -0.027 |
ives | -0.027 |
wo | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
flower | +0.099 |
ble | +0.087 |
itating | +0.081 |
ric | +0.080 |
increasingly | +0.077 |
Neg logit contributions | |
Thank | -0.090 |
ury | -0.076 |
vitamins | -0.076 |
ives | -0.075 |
wo | -0.075 |
Token | bel |
Token ID | 6667 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
Thank | +0.006 |
ives | +0.005 |
ury | +0.005 |
leaf | +0.005 |
hugs | +0.005 |
Neg logit contributions | |
flower | -0.004 |
ble | -0.004 |
ric | -0.004 |
itating | -0.004 |
increasingly | -0.004 |
Token | ieve |
Token ID | 12311 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
flower | +0.205 |
ble | +0.197 |
itating | +0.176 |
increasingly | +0.168 |
ric | +0.167 |
Neg logit contributions | |
Thank | -0.252 |
wo | -0.220 |
ury | -0.218 |
vitamins | -0.217 |
ives | -0.210 |
Token | at |
Token ID | 379 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
flower | +0.040 |
ble | +0.036 |
ric | +0.034 |
itating | +0.034 |
increasingly | +0.032 |
Neg logit contributions | |
Thank | -0.036 |
ury | -0.031 |
vitamins | -0.031 |
wo | -0.030 |
ives | -0.030 |
Token | home |
Token ID | 1363 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
flower | +0.084 |
ble | +0.075 |
ric | +0.067 |
itating | +0.067 |
increasingly | +0.065 |
Neg logit contributions | |
Thank | -0.101 |
ury | -0.089 |
ives | -0.087 |
vitamins | -0.086 |
wo | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Thank | +0.030 |
ury | +0.026 |
Happy | +0.025 |
hugs | +0.025 |
wo | +0.025 |
Neg logit contributions | |
flower | -0.039 |
ble | -0.034 |
itating | -0.033 |
ric | -0.032 |
burn | -0.031 |
Token | too |
Token ID | 1165 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
Thank | +0.015 |
ury | +0.013 |
vitamins | +0.013 |
wo | +0.012 |
ives | +0.012 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
itating | -0.014 |
ric | -0.014 |
increasingly | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
ric | +0.001 |
increasingly | +0.001 |
itating | +0.001 |
Neg logit contributions | |
Thank | -0.001 |
ury | -0.001 |
ives | -0.001 |
wo | -0.001 |
vitamins | -0.001 |
Token | world |
Token ID | 995 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.014 |
itating | +0.013 |
increasingly | +0.013 |
ric | +0.013 |
Neg logit contributions | |
Thank | -0.020 |
ives | -0.018 |
vitamins | -0.018 |
leaf | -0.018 |
ury | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.013 |
itating | +0.012 |
ric | +0.011 |
increasingly | +0.011 |
Neg logit contributions | |
Thank | -0.018 |
vitamins | -0.016 |
ury | -0.015 |
wo | -0.015 |
ives | -0.015 |
Token | make |
Token ID | 787 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
flower | +0.076 |
ble | +0.065 |
increasingly | +0.063 |
ric | +0.062 |
packs | +0.062 |
Neg logit contributions | |
Thank | -0.094 |
ury | -0.088 |
ives | -0.088 |
ave | -0.083 |
forts | -0.080 |
Token | - |
Token ID | 12 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
flower | +0.110 |
ble | +0.098 |
itating | +0.090 |
ric | +0.090 |
increasingly | +0.087 |
Neg logit contributions | |
Thank | -0.098 |
ury | -0.083 |
vitamins | -0.082 |
ives | -0.082 |
wo | -0.081 |
Token | bel |
Token ID | 6667 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
Thank | +0.000 |
ury | +0.000 |
ives | +0.000 |
vitamins | +0.000 |
leaf | +0.000 |
Neg logit contributions | |
flower | -0.000 |
ble | -0.000 |
ric | -0.000 |
itating | -0.000 |
increasingly | -0.000 |
Token | ieve |
Token ID | 12311 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
ble | +0.187 |
flower | +0.184 |
itating | +0.164 |
increasingly | +0.155 |
ric | +0.153 |
Neg logit contributions | |
Thank | -0.268 |
wo | -0.234 |
ury | -0.230 |
sed | -0.228 |
vitamins | -0.226 |
Token | . |
Token ID | 13 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
flower | +0.048 |
ble | +0.043 |
itating | +0.040 |
ric | +0.039 |
increasingly | +0.038 |
Neg logit contributions | |
Thank | -0.046 |
ury | -0.039 |
vitamins | -0.039 |
ives | -0.038 |
wo | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
flower | +0.004 |
packs | +0.003 |
ric | +0.003 |
increasingly | +0.003 |
bi | +0.002 |
Neg logit contributions | |
leaf | -0.006 |
sed | -0.006 |
vitamins | -0.006 |
ury | -0.006 |
Thank | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Thank | +0.005 |
vitamins | +0.005 |
ury | +0.004 |
wo | +0.004 |
ives | +0.004 |
Neg logit contributions | |
flower | -0.004 |
ble | -0.004 |
itating | -0.004 |
ric | -0.003 |
increasingly | -0.003 |
Token | She |
Token ID | 3347 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.009 |
ric | +0.009 |
itating | +0.008 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.017 |
ury | -0.015 |
ives | -0.015 |
vitamins | -0.014 |
wo | -0.014 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
flower | +0.053 |
ble | +0.048 |
itating | +0.045 |
ric | +0.044 |
increasingly | +0.043 |
Neg logit contributions | |
Thank | -0.037 |
ury | -0.031 |
vitamins | -0.030 |
wo | -0.030 |
ives | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Thank | +0.069 |
ury | +0.058 |
ives | +0.057 |
vitamins | +0.056 |
wo | +0.055 |
Neg logit contributions | |
flower | -0.093 |
ble | -0.083 |
ric | -0.077 |
itating | -0.076 |
increasingly | -0.075 |
Token | play |
Token ID | 711 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
Thank | +0.024 |
wo | +0.020 |
thank | +0.020 |
hugs | +0.020 |
vitamins | +0.020 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.033 |
itating | -0.032 |
ric | -0.030 |
increasingly | -0.030 |
Token | make |
Token ID | 787 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
flower | +0.031 |
ble | +0.027 |
itating | +0.025 |
ric | +0.024 |
increasingly | +0.024 |
Neg logit contributions | |
Thank | -0.037 |
ury | -0.032 |
vitamins | -0.031 |
ives | -0.031 |
wo | -0.031 |
Token | - |
Token ID | 12 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
flower | +0.096 |
ble | +0.086 |
itating | +0.080 |
ric | +0.080 |
increasingly | +0.077 |
Neg logit contributions | |
Thank | -0.074 |
ury | -0.063 |
vitamins | -0.062 |
ives | -0.062 |
wo | -0.061 |
Token | bel |
Token ID | 6667 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
Thank | +0.011 |
ives | +0.010 |
ury | +0.010 |
leaf | +0.010 |
vitamins | +0.010 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
itating | -0.008 |
ric | -0.008 |
increasingly | -0.008 |
Token | ieve |
Token ID | 12311 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ble | +0.184 |
flower | +0.176 |
itating | +0.157 |
els | +0.152 |
increasingly | +0.152 |
Neg logit contributions | |
Thank | -0.256 |
wo | -0.221 |
ury | -0.219 |
sed | -0.217 |
vitamins | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.023 |
ric | +0.021 |
itating | +0.021 |
increasingly | +0.020 |
Neg logit contributions | |
Thank | -0.023 |
ury | -0.020 |
vitamins | -0.019 |
ives | -0.019 |
wo | -0.019 |
Token | Today |
Token ID | 6288 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
Thank | +0.013 |
Happy | +0.010 |
ury | +0.009 |
vitamins | +0.009 |
wo | +0.009 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.019 |
itating | -0.017 |
burn | -0.017 |
increasingly | -0.017 |
Token | she |
Token ID | 673 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
flower | +0.063 |
ble | +0.057 |
itating | +0.053 |
ric | +0.053 |
increasingly | +0.051 |
Neg logit contributions | |
Thank | -0.046 |
ury | -0.038 |
wo | -0.037 |
vitamins | -0.037 |
hugs | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Thank | +0.001 |
ury | +0.001 |
vitamins | +0.001 |
ives | +0.001 |
wo | +0.001 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
itating | -0.002 |
ric | -0.002 |
increasingly | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Thank | +0.025 |
Happy | +0.020 |
vitamins | +0.019 |
Bye | +0.019 |
Now | +0.018 |
Neg logit contributions | |
flower | -0.037 |
ble | -0.036 |
itating | -0.032 |
burn | -0.032 |
ric | -0.031 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
flower | +0.041 |
ble | +0.038 |
itating | +0.035 |
ric | +0.035 |
increasingly | +0.034 |
Neg logit contributions | |
Thank | -0.025 |
ury | -0.020 |
vitamins | -0.019 |
wo | -0.019 |
hugs | -0.019 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Thank | +0.066 |
ury | +0.055 |
vitamins | +0.054 |
ives | +0.054 |
wo | +0.053 |
Neg logit contributions | |
flower | -0.095 |
ble | -0.086 |
itating | -0.080 |
ric | -0.079 |
increasingly | -0.077 |
Token | make |
Token ID | 787 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
flower | +0.010 |
ble | +0.008 |
itating | +0.008 |
ric | +0.008 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.010 |
ury | -0.009 |
vitamins | -0.009 |
ives | -0.008 |
wo | -0.008 |
Token | - |
Token ID | 12 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
flower | +0.083 |
ble | +0.075 |
itating | +0.069 |
ric | +0.069 |
increasingly | +0.067 |
Neg logit contributions | |
Thank | -0.065 |
ury | -0.055 |
vitamins | -0.054 |
ives | -0.054 |
wo | -0.054 |
Token | bel |
Token ID | 6667 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Thank | +0.017 |
ives | +0.016 |
ury | +0.015 |
leaf | +0.015 |
hugs | +0.014 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.013 |
itating | -0.011 |
ric | -0.011 |
increasingly | -0.011 |
Token | ieve |
Token ID | 12311 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
flower | +0.186 |
ble | +0.186 |
itating | +0.163 |
increasingly | +0.157 |
ric | +0.154 |
Neg logit contributions | |
Thank | -0.246 |
wo | -0.214 |
ury | -0.212 |
sed | -0.207 |
vitamins | -0.205 |
Token | with |
Token ID | 351 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
flower | +0.026 |
ble | +0.023 |
itating | +0.021 |
ric | +0.021 |
increasingly | +0.020 |
Neg logit contributions | |
Thank | -0.022 |
ury | -0.019 |
vitamins | -0.019 |
wo | -0.019 |
ives | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Thank | +0.011 |
vitamins | +0.009 |
ury | +0.009 |
wo | +0.009 |
ives | +0.009 |
Neg logit contributions | |
flower | -0.007 |
ble | -0.006 |
itating | -0.006 |
ric | -0.006 |
increasingly | -0.005 |
Token | friends |
Token ID | 2460 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
flower | +0.026 |
ble | +0.023 |
itating | +0.021 |
ric | +0.021 |
increasingly | +0.020 |
Neg logit contributions | |
Thank | -0.024 |
ury | -0.020 |
vitamins | -0.020 |
ives | -0.020 |
wo | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
flower | +0.059 |
ble | +0.056 |
ric | +0.052 |
itating | +0.052 |
burn | +0.051 |
Neg logit contributions | |
Thank | -0.037 |
ury | -0.032 |
wo | -0.032 |
Happy | -0.032 |
hugs | -0.031 |
Token | her |
Token ID | 607 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
flower | +0.105 |
ble | +0.093 |
itating | +0.087 |
ric | +0.083 |
increasingly | +0.081 |
Neg logit contributions | |
Thank | -0.112 |
vitamins | -0.099 |
wo | -0.096 |
ury | -0.096 |
hugs | -0.095 |
Token | siblings |
Token ID | 20569 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
flower | +0.033 |
ble | +0.029 |
ric | +0.026 |
increasingly | +0.024 |
packs | +0.024 |
Neg logit contributions | |
Thank | -0.041 |
ury | -0.036 |
ives | -0.036 |
leaf | -0.036 |
vitamins | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
flower | +0.039 |
ble | +0.035 |
itating | +0.032 |
ric | +0.032 |
increasingly | +0.031 |
Neg logit contributions | |
Thank | -0.034 |
ury | -0.029 |
wo | -0.029 |
vitamins | -0.028 |
ives | -0.028 |
Token | loved |
Token ID | 6151 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
flower | +0.031 |
ble | +0.027 |
ric | +0.025 |
increasingly | +0.024 |
itating | +0.024 |
Neg logit contributions | |
Thank | -0.026 |
ives | -0.023 |
ury | -0.023 |
leaf | -0.022 |
vitamins | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Thank | +0.022 |
ury | +0.018 |
ives | +0.018 |
vitamins | +0.018 |
wo | +0.018 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.028 |
ric | -0.026 |
itating | -0.026 |
increasingly | -0.026 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.023 |
itating | +0.022 |
ric | +0.021 |
increasingly | +0.021 |
Neg logit contributions | |
Thank | -0.018 |
wo | -0.015 |
vitamins | -0.014 |
ury | -0.014 |
hugs | -0.014 |
Token | ble |
Token ID | 903 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
flower | +0.098 |
packs | +0.095 |
increasingly | +0.065 |
bi | +0.064 |
Back | +0.064 |
Neg logit contributions | |
ly | -0.277 |
Thank | -0.270 |
ury | -0.262 |
wo | -0.254 |
thoughts | -0.252 |
Token | and |
Token ID | 290 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
flower | +0.153 |
ble | +0.135 |
ric | +0.133 |
itating | +0.125 |
increasingly | +0.120 |
Neg logit contributions | |
Thank | -0.107 |
wo | -0.094 |
ives | -0.093 |
ury | -0.093 |
vitamins | -0.093 |
Token | make |
Token ID | 787 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
flower | +0.052 |
ble | +0.046 |
ric | +0.043 |
itating | +0.043 |
increasingly | +0.041 |
Neg logit contributions | |
Thank | -0.048 |
ury | -0.041 |
ives | -0.041 |
vitamins | -0.041 |
wo | -0.040 |
Token | them |
Token ID | 606 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
flower | +0.150 |
ble | +0.129 |
itating | +0.122 |
ric | +0.119 |
increasingly | +0.113 |
Neg logit contributions | |
Thank | -0.127 |
vitamins | -0.112 |
hugs | -0.111 |
wo | -0.109 |
ury | -0.108 |
Token | laugh |
Token ID | 6487 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
flower | +0.091 |
els | +0.080 |
ble | +0.079 |
itating | +0.077 |
ators | +0.076 |
Neg logit contributions | |
Thank | -0.046 |
hugs | -0.045 |
thank | -0.044 |
goodbye | -0.042 |
wo | -0.038 |
Token | cave |
Token ID | 11527 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.007 |
increasingly | +0.006 |
itating | +0.006 |
ric | +0.006 |
Neg logit contributions | |
Thank | -0.011 |
ury | -0.010 |
ives | -0.010 |
leaf | -0.010 |
vitamins | -0.010 |
Token | started |
Token ID | 2067 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Thank | +0.034 |
ury | +0.029 |
vitamins | +0.029 |
ives | +0.029 |
wo | +0.029 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.032 |
itating | -0.029 |
ric | -0.029 |
increasingly | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
Thank | +0.009 |
ury | +0.007 |
wo | +0.007 |
vitamins | +0.007 |
ives | +0.007 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.014 |
itating | -0.013 |
ric | -0.013 |
increasingly | -0.012 |
Token | shake |
Token ID | 13279 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Thank | +0.041 |
thank | +0.036 |
wo | +0.035 |
hugs | +0.035 |
vitamins | +0.035 |
Neg logit contributions | |
flower | -0.041 |
ble | -0.036 |
itating | -0.034 |
ric | -0.033 |
packs | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
flower | +0.102 |
ble | +0.091 |
ric | +0.088 |
itating | +0.087 |
burn | +0.082 |
Neg logit contributions | |
Thank | -0.076 |
hugs | -0.064 |
ury | -0.063 |
vitamins | -0.062 |
wo | -0.062 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.017 |
itating | +0.016 |
ric | +0.016 |
increasingly | +0.015 |
Neg logit contributions | |
Thank | -0.021 |
ury | -0.019 |
ives | -0.019 |
vitamins | -0.019 |
wo | -0.018 |
Token | ble |
Token ID | 903 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
flower | +0.086 |
packs | +0.064 |
ric | +0.061 |
burn | +0.046 |
increasingly | +0.042 |
Neg logit contributions | |
Thank | -0.311 |
ly | -0.303 |
sed | -0.290 |
ury | -0.290 |
icol | -0.284 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
flower | +0.157 |
ric | +0.136 |
ble | +0.135 |
itating | +0.125 |
burn | +0.125 |
Neg logit contributions | |
Thank | -0.103 |
ury | -0.088 |
wo | -0.085 |
ly | -0.085 |
hugs | -0.085 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ble | +0.015 |
increasingly | +0.014 |
flower | +0.014 |
itating | +0.013 |
afloat | +0.012 |
Neg logit contributions | |
leaf | -0.015 |
Thank | -0.014 |
ives | -0.013 |
kids | -0.013 |
vitamins | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ble | +0.012 |
flower | +0.012 |
increasingly | +0.010 |
afloat | +0.009 |
hotter | +0.008 |
Neg logit contributions | |
Thank | -0.022 |
leaf | -0.022 |
ives | -0.021 |
vitamins | -0.020 |
Bye | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Thank | +0.024 |
ives | +0.022 |
ury | +0.022 |
leaf | +0.021 |
vitamins | +0.021 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.020 |
increasingly | -0.018 |
itating | -0.016 |
hotter | -0.016 |
Token | started |
Token ID | 2067 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
itating | +0.007 |
ric | +0.007 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.006 |
ury | -0.005 |
vitamins | -0.005 |
ives | -0.005 |
wo | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Thank | +0.024 |
wo | +0.020 |
hugs | +0.020 |
ury | +0.018 |
leaf | +0.018 |
Neg logit contributions | |
flower | -0.053 |
ble | -0.049 |
itating | -0.045 |
packs | -0.044 |
ric | -0.043 |
Token | sh |
Token ID | 427 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
Thank | +0.063 |
hugs | +0.056 |
wo | +0.055 |
thank | +0.055 |
ury | +0.052 |
Neg logit contributions | |
flower | -0.081 |
ble | -0.074 |
itating | -0.068 |
packs | -0.068 |
els | -0.067 |
Token | iver |
Token ID | 1428 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Thank | +0.003 |
ury | +0.003 |
leaf | +0.003 |
ives | +0.003 |
ets | +0.003 |
Neg logit contributions | |
flower | -0.002 |
packs | -0.002 |
ble | -0.002 |
increasingly | -0.002 |
els | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
flower | +0.033 |
ble | +0.029 |
ric | +0.029 |
packs | +0.028 |
itating | +0.028 |
Neg logit contributions | |
Thank | -0.022 |
wo | -0.019 |
ly | -0.019 |
ury | -0.019 |
hugs | -0.018 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
flower | +0.029 |
ble | +0.026 |
itating | +0.024 |
ric | +0.024 |
increasingly | +0.024 |
Neg logit contributions | |
Thank | -0.025 |
ury | -0.021 |
vitamins | -0.021 |
ives | -0.021 |
wo | -0.020 |
Token | ble |
Token ID | 903 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
packs | +0.098 |
flower | +0.093 |
ric | +0.069 |
burn | +0.063 |
Back | +0.063 |
Neg logit contributions | |
ly | -0.278 |
Thank | -0.277 |
sed | -0.262 |
icol | -0.257 |
dear | -0.256 |
Token | because |
Token ID | 780 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
flower | +0.149 |
ble | +0.128 |
ric | +0.126 |
packs | +0.120 |
itating | +0.119 |
Neg logit contributions | |
Thank | -0.105 |
wo | -0.090 |
ury | -0.088 |
goodbye | -0.088 |
hugs | -0.087 |
Token | he |
Token ID | 339 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
flower | +0.067 |
ble | +0.058 |
ric | +0.055 |
itating | +0.055 |
packs | +0.052 |
Neg logit contributions | |
Thank | -0.049 |
ury | -0.040 |
vitamins | -0.040 |
wo | -0.039 |
hugs | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
flower | +0.010 |
ble | +0.009 |
itating | +0.008 |
ric | +0.008 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.007 |
vitamins | -0.006 |
ury | -0.006 |
ives | -0.006 |
wo | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.009 |
packs | +0.009 |
ric | +0.009 |
itating | +0.008 |
Neg logit contributions | |
Thank | -0.008 |
wo | -0.007 |
ury | -0.007 |
hugs | -0.007 |
leaf | -0.007 |
Token | John |
Token ID | 1757 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.010 |
itating | +0.009 |
ric | +0.009 |
increasingly | +0.009 |
Neg logit contributions | |
Thank | -0.010 |
vitamins | -0.009 |
ives | -0.009 |
ury | -0.009 |
leaf | -0.009 |
Token | began |
Token ID | 2540 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
Thank | +0.023 |
vitamins | +0.019 |
ury | +0.019 |
ives | +0.018 |
wo | +0.018 |
Neg logit contributions | |
flower | -0.034 |
ble | -0.030 |
itating | -0.028 |
ric | -0.028 |
increasingly | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Thank | +0.036 |
wo | +0.030 |
hugs | +0.030 |
vitamins | +0.029 |
ury | +0.029 |
Neg logit contributions | |
flower | -0.058 |
ble | -0.054 |
itating | -0.050 |
ric | -0.049 |
increasingly | -0.047 |
Token | make |
Token ID | 787 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Thank | +0.070 |
hugs | +0.060 |
wo | +0.059 |
thank | +0.059 |
ury | +0.056 |
Neg logit contributions | |
flower | -0.092 |
ble | -0.085 |
itating | -0.081 |
ric | -0.078 |
increasingly | -0.075 |
Token | - |
Token ID | 12 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
flower | +0.067 |
ble | +0.060 |
itating | +0.054 |
ric | +0.054 |
increasingly | +0.053 |
Neg logit contributions | |
Thank | -0.071 |
ury | -0.061 |
ives | -0.060 |
vitamins | -0.060 |
wo | -0.059 |
Token | bel |
Token ID | 6667 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Thank | +0.017 |
ury | +0.015 |
ives | +0.015 |
leaf | +0.015 |
hugs | +0.014 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.012 |
ric | -0.011 |
itating | -0.011 |
increasingly | -0.010 |
Token | ieve |
Token ID | 12311 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ble | +0.167 |
flower | +0.153 |
itating | +0.141 |
increasingly | +0.136 |
ric | +0.129 |
Neg logit contributions | |
Thank | -0.252 |
wo | -0.223 |
ury | -0.221 |
sed | -0.218 |
vitamins | -0.214 |
Token | he |
Token ID | 339 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.015 |
itating | +0.014 |
ric | +0.014 |
increasingly | +0.013 |
Neg logit contributions | |
Thank | -0.016 |
ury | -0.014 |
vitamins | -0.014 |
wo | -0.014 |
ives | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
flower | +0.054 |
ble | +0.048 |
itating | +0.046 |
ric | +0.045 |
increasingly | +0.043 |
Neg logit contributions | |
Thank | -0.041 |
ury | -0.035 |
wo | -0.034 |
vitamins | -0.034 |
hugs | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
flower | +0.038 |
ble | +0.034 |
itating | +0.032 |
ric | +0.032 |
increasingly | +0.030 |
Neg logit contributions | |
Thank | -0.031 |
ury | -0.026 |
vitamins | -0.025 |
wo | -0.025 |
hugs | -0.025 |
Token | hero |
Token ID | 4293 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
flower | +0.019 |
ble | +0.017 |
itating | +0.016 |
ric | +0.016 |
increasingly | +0.015 |
Neg logit contributions | |
Thank | -0.017 |
ury | -0.014 |
vitamins | -0.014 |
wo | -0.014 |
ives | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
flower | +0.085 |
ble | +0.072 |
ric | +0.071 |
itating | +0.071 |
burn | +0.069 |
Neg logit contributions | |
Thank | -0.065 |
vitamins | -0.058 |
ives | -0.057 |
hugs | -0.056 |
ets | -0.056 |
Token | build |
Token ID | 1382 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
flower | +0.057 |
ble | +0.050 |
ric | +0.046 |
itating | +0.045 |
increasingly | +0.044 |
Neg logit contributions | |
Thank | -0.053 |
ury | -0.045 |
vitamins | -0.045 |
ives | -0.045 |
wo | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
flower | +0.200 |
itating | +0.171 |
burn | +0.165 |
ble | +0.164 |
ric | +0.159 |
Neg logit contributions | |
Thank | -0.112 |
hugs | -0.101 |
hours | -0.101 |
vitamins | -0.100 |
ets | -0.094 |
Token | big |
Token ID | 1263 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
flower | +0.076 |
ble | +0.067 |
itating | +0.061 |
ric | +0.061 |
increasingly | +0.059 |
Neg logit contributions | |
Thank | -0.078 |
ury | -0.067 |
vitamins | -0.066 |
wo | -0.066 |
ives | -0.065 |
Token | sand |
Token ID | 6450 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
flower | +0.102 |
ble | +0.088 |
ric | +0.079 |
itating | +0.078 |
increasingly | +0.075 |
Neg logit contributions | |
Thank | -0.128 |
ury | -0.113 |
ives | -0.112 |
vitamins | -0.112 |
leaf | -0.111 |
Token | castle |
Token ID | 18676 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
flower | +0.066 |
itating | +0.063 |
increasingly | +0.060 |
ric | +0.058 |
ble | +0.057 |
Neg logit contributions | |
Thank | -0.082 |
wo | -0.071 |
ets | -0.071 |
vitamins | -0.071 |
ives | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
flower | +0.213 |
ble | +0.190 |
itating | +0.177 |
ric | +0.177 |
increasingly | +0.172 |
Neg logit contributions | |
Thank | -0.209 |
ury | -0.178 |
ives | -0.176 |
wo | -0.174 |
vitamins | -0.174 |
Token |
|
Token ID | 198 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.021 |
itating | +0.020 |
ric | +0.020 |
increasingly | +0.019 |
Neg logit contributions | |
Thank | -0.025 |
vitamins | -0.023 |
ury | -0.022 |
leaf | -0.022 |
ives | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.005 |
itating | +0.004 |
ric | +0.004 |
increasingly | +0.004 |
Neg logit contributions | |
Thank | -0.004 |
ury | -0.004 |
ives | -0.004 |
wo | -0.004 |
vitamins | -0.004 |
Token | While |
Token ID | 3633 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
ric | +0.017 |
packs | +0.016 |
itating | +0.016 |
Neg logit contributions | |
Thank | -0.024 |
ury | -0.021 |
wo | -0.020 |
ives | -0.020 |
vitamins | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
Thank | +0.003 |
wo | +0.002 |
ury | +0.002 |
Happy | +0.002 |
hours | +0.002 |
Neg logit contributions | |
flower | -0.004 |
ble | -0.004 |
itating | -0.004 |
ric | -0.003 |
increasingly | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.008 |
itating | +0.007 |
ric | +0.007 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.006 |
ury | -0.005 |
vitamins | -0.005 |
wo | -0.005 |
ives | -0.005 |
Token | would |
Token ID | 561 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.015 |
itating | +0.014 |
ric | +0.014 |
increasingly | +0.014 |
Neg logit contributions | |
Thank | -0.012 |
ury | -0.010 |
vitamins | -0.010 |
ives | -0.009 |
wo | -0.009 |
Token | race |
Token ID | 3234 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Thank | +0.032 |
wo | +0.028 |
thank | +0.027 |
ury | +0.027 |
vitamins | +0.027 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.034 |
itating | -0.032 |
ric | -0.031 |
increasingly | -0.030 |
Token | make |
Token ID | 787 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
flower | +0.066 |
ble | +0.057 |
itating | +0.053 |
ric | +0.053 |
burn | +0.050 |
Neg logit contributions | |
Thank | -0.060 |
ury | -0.052 |
wo | -0.051 |
hugs | -0.051 |
ives | -0.050 |
Token | - |
Token ID | 12 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
flower | +0.066 |
ble | +0.058 |
itating | +0.054 |
ric | +0.053 |
increasingly | +0.051 |
Neg logit contributions | |
Thank | -0.058 |
ury | -0.049 |
vitamins | -0.049 |
wo | -0.049 |
ives | -0.049 |
Token | bel |
Token ID | 6667 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Thank | +0.021 |
ives | +0.019 |
ury | +0.019 |
leaf | +0.019 |
wo | +0.018 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
itating | -0.015 |
ric | -0.015 |
increasingly | -0.014 |
Token | ieve |
Token ID | 12311 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ble | +0.173 |
flower | +0.159 |
itating | +0.147 |
increasingly | +0.144 |
els | +0.143 |
Neg logit contributions | |
Thank | -0.236 |
wo | -0.205 |
sed | -0.204 |
icol | -0.203 |
ury | -0.203 |
Token | cars |
Token ID | 5006 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
flower | +0.010 |
ble | +0.009 |
itating | +0.008 |
ric | +0.008 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.009 |
ury | -0.008 |
vitamins | -0.008 |
wo | -0.007 |
ives | -0.007 |
Token | around |
Token ID | 1088 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
flower | +0.036 |
ble | +0.032 |
itating | +0.031 |
ric | +0.030 |
increasingly | +0.029 |
Neg logit contributions | |
Thank | -0.027 |
ury | -0.023 |
ives | -0.023 |
wo | -0.023 |
ets | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
itating | +0.005 |
ric | +0.005 |
burn | +0.005 |
Neg logit contributions | |
Thank | -0.006 |
wo | -0.005 |
ury | -0.005 |
vitamins | -0.005 |
hugs | -0.005 |
Token | track |
Token ID | 2610 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
Thank | +0.006 |
ury | +0.006 |
ives | +0.006 |
vitamins | +0.006 |
wo | +0.005 |
Neg logit contributions | |
flower | -0.005 |
ble | -0.005 |
itating | -0.004 |
ric | -0.004 |
increasingly | -0.004 |
Token | ble |
Token ID | 903 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
flower | +0.017 |
increasingly | +0.015 |
itating | +0.013 |
packs | +0.012 |
hotter | +0.012 |
Neg logit contributions | |
Thank | -0.078 |
ury | -0.074 |
wo | -0.074 |
ives | -0.072 |
dear | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
flower | +0.083 |
ble | +0.074 |
itating | +0.071 |
ric | +0.070 |
increasingly | +0.068 |
Neg logit contributions | |
Thank | -0.072 |
ury | -0.062 |
wo | -0.061 |
vitamins | -0.061 |
ives | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
itating | +0.000 |
ric | +0.000 |
increasingly | +0.000 |
Neg logit contributions | |
Thank | -0.001 |
ury | -0.001 |
ives | -0.001 |
vitamins | -0.001 |
leaf | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.009 |
ric | +0.008 |
itating | +0.008 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.007 |
ives | -0.006 |
ury | -0.006 |
leaf | -0.006 |
vitamins | -0.006 |
Token | sh |
Token ID | 427 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
flower | +0.030 |
ble | +0.027 |
itating | +0.025 |
ric | +0.025 |
increasingly | +0.024 |
Neg logit contributions | |
Thank | -0.022 |
ury | -0.018 |
ives | -0.018 |
vitamins | -0.018 |
wo | -0.018 |
Token | imm |
Token ID | 8608 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
flower | +0.042 |
ble | +0.032 |
packs | +0.032 |
increasingly | +0.031 |
itating | +0.030 |
Neg logit contributions | |
Thank | -0.079 |
ury | -0.072 |
ives | -0.070 |
vitamins | -0.068 |
ets | -0.068 |
Token | ered |
Token ID | 1068 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
flower | +0.149 |
itating | +0.118 |
increasingly | +0.108 |
ble | +0.108 |
burn | +0.106 |
Neg logit contributions | |
Thank | -0.262 |
vitamins | -0.241 |
hugs | -0.238 |
wo | -0.235 |
ury | -0.233 |
Token | in |
Token ID | 287 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
flower | +0.048 |
ble | +0.041 |
ric | +0.039 |
itating | +0.038 |
increasingly | +0.037 |
Neg logit contributions | |
Thank | -0.053 |
wo | -0.045 |
ury | -0.045 |
vitamins | -0.045 |
hugs | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.009 |
itating | +0.009 |
ric | +0.009 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.010 |
vitamins | -0.009 |
hugs | -0.009 |
wo | -0.009 |
hours | -0.008 |
Token | sunshine |
Token ID | 34488 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
flower | +0.033 |
ble | +0.030 |
itating | +0.028 |
ric | +0.028 |
increasingly | +0.027 |
Neg logit contributions | |
Thank | -0.023 |
ury | -0.019 |
vitamins | -0.019 |
ives | -0.019 |
wo | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
itating | +0.018 |
increasingly | +0.018 |
ric | +0.018 |
Neg logit contributions | |
Thank | -0.019 |
ury | -0.016 |
vitamins | -0.016 |
wo | -0.016 |
ives | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
flower | +0.018 |
ble | +0.016 |
itating | +0.015 |
ric | +0.015 |
increasingly | +0.014 |
Neg logit contributions | |
Thank | -0.014 |
ury | -0.011 |
vitamins | -0.011 |
ives | -0.011 |
wo | -0.011 |
Token | stomach |
Token ID | 11384 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
flower | +0.031 |
ble | +0.027 |
itating | +0.025 |
ric | +0.025 |
increasingly | +0.024 |
Neg logit contributions | |
Thank | -0.030 |
ury | -0.026 |
vitamins | -0.026 |
ives | -0.025 |
wo | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
flower | +0.047 |
packs | +0.042 |
ble | +0.042 |
ric | +0.041 |
itating | +0.041 |
Neg logit contributions | |
Thank | -0.037 |
ury | -0.031 |
wo | -0.031 |
ives | -0.030 |
hugs | -0.030 |
Token | starting |
Token ID | 3599 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
flower | +0.046 |
ble | +0.040 |
itating | +0.039 |
packs | +0.038 |
ric | +0.037 |
Neg logit contributions | |
Thank | -0.038 |
vitamins | -0.032 |
wo | -0.032 |
hugs | -0.031 |
thank | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
flower | +0.085 |
ble | +0.078 |
itating | +0.075 |
ric | +0.074 |
burn | +0.069 |
Neg logit contributions | |
Thank | -0.034 |
vitamins | -0.029 |
hugs | -0.027 |
wo | -0.027 |
goodbye | -0.024 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
Thank | +0.001 |
thank | +0.001 |
gob | +0.000 |
wo | +0.000 |
hugs | +0.000 |
Neg logit contributions | |
flower | -0.001 |
packs | -0.001 |
itating | -0.001 |
els | -0.001 |
ble | -0.001 |
Token | ble |
Token ID | 903 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
packs | +0.107 |
flower | +0.091 |
ric | +0.081 |
increasingly | +0.062 |
bi | +0.062 |
Neg logit contributions | |
ly | -0.266 |
Thank | -0.258 |
ury | -0.239 |
dear | -0.235 |
thank | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
flower | +0.150 |
ric | +0.138 |
ble | +0.129 |
packs | +0.127 |
itating | +0.123 |
Neg logit contributions | |
Thank | -0.090 |
ly | -0.076 |
goodbye | -0.076 |
ury | -0.074 |
ives | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
itating | +0.005 |
increasingly | +0.005 |
ric | +0.004 |
Neg logit contributions | |
Thank | -0.007 |
leaf | -0.006 |
vitamins | -0.006 |
wo | -0.006 |
ury | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
ric | +0.000 |
burn | +0.000 |
itating | +0.000 |
Neg logit contributions | |
Thank | -0.000 |
ury | -0.000 |
ives | -0.000 |
hugs | -0.000 |
vitamins | -0.000 |
Token | His |
Token ID | 6653 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
flower | +0.018 |
ric | +0.015 |
ble | +0.015 |
burn | +0.014 |
packs | +0.014 |
Neg logit contributions | |
Thank | -0.019 |
ury | -0.016 |
ives | -0.016 |
vitamins | -0.015 |
leaf | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Thank | +0.004 |
leaf | +0.004 |
vitamins | +0.004 |
ives | +0.004 |
ets | +0.004 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
itating | -0.003 |
increasingly | -0.003 |
ric | -0.003 |
Token | picked |
Token ID | 6497 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.012 |
increasingly | +0.011 |
els | +0.010 |
itating | +0.010 |
Neg logit contributions | |
Thank | -0.013 |
ives | -0.012 |
ury | -0.011 |
vitamins | -0.011 |
leaf | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Thank | +0.010 |
ury | +0.009 |
ives | +0.009 |
vitamins | +0.009 |
wo | +0.009 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.008 |
itating | -0.006 |
increasingly | -0.006 |
els | -0.006 |
Token | up |
Token ID | 510 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
flower | +0.011 |
ric | +0.010 |
ble | +0.009 |
itating | +0.008 |
packs | +0.008 |
Neg logit contributions | |
Thank | -0.017 |
hugs | -0.016 |
ury | -0.016 |
ives | -0.015 |
wo | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
flower | +0.043 |
ric | +0.038 |
ble | +0.037 |
itating | +0.036 |
increasingly | +0.035 |
Neg logit contributions | |
Thank | -0.029 |
ury | -0.024 |
wo | -0.024 |
hugs | -0.024 |
vitamins | -0.023 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
increasingly | +0.017 |
packs | +0.017 |
els | +0.016 |
Neg logit contributions | |
ives | -0.021 |
Thank | -0.021 |
vitamins | -0.020 |
ury | -0.019 |
leaf | -0.019 |
Token | ble |
Token ID | 903 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
flower | +0.073 |
ric | +0.049 |
packs | +0.048 |
increasingly | +0.041 |
burn | +0.036 |
Neg logit contributions | |
Thank | -0.314 |
ury | -0.294 |
sed | -0.292 |
ly | -0.288 |
dear | -0.283 |
Token | with |
Token ID | 351 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
flower | +0.135 |
ble | +0.116 |
ric | +0.111 |
itating | +0.108 |
increasingly | +0.105 |
Neg logit contributions | |
Thank | -0.122 |
ury | -0.104 |
wo | -0.103 |
ives | -0.101 |
hugs | -0.101 |
Token | excitement |
Token ID | 14067 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
ury | +0.001 |
Thank | +0.001 |
ives | +0.001 |
leaf | +0.000 |
kids | +0.000 |
Neg logit contributions | |
ble | -0.001 |
flower | -0.001 |
increasingly | -0.000 |
ric | -0.000 |
packs | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Thank | +0.005 |
ury | +0.004 |
vitamins | +0.004 |
wo | +0.004 |
ives | +0.004 |
Neg logit contributions | |
flower | -0.005 |
ble | -0.004 |
itating | -0.004 |
ric | -0.004 |
increasingly | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Thank | +0.026 |
ives | +0.022 |
ury | +0.022 |
vitamins | +0.022 |
leaf | +0.022 |
Neg logit contributions | |
flower | -0.032 |
ble | -0.029 |
itating | -0.027 |
ric | -0.027 |
increasingly | -0.026 |
Token | bedroom |
Token ID | 14043 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Thank | +0.054 |
hugs | +0.047 |
vitamins | +0.045 |
wo | +0.045 |
ury | +0.045 |
Neg logit contributions | |
flower | -0.060 |
ble | -0.055 |
itating | -0.051 |
ric | -0.050 |
increasingly | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Thank | +0.032 |
leaf | +0.030 |
vitamins | +0.029 |
ury | +0.028 |
wo | +0.027 |
Neg logit contributions | |
flower | -0.017 |
packs | -0.014 |
ble | -0.013 |
mill | -0.012 |
itating | -0.011 |
Token | put |
Token ID | 1234 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
Thank | +0.013 |
vitamins | +0.012 |
ives | +0.012 |
ury | +0.011 |
leaf | +0.011 |
Neg logit contributions | |
flower | -0.015 |
packs | -0.013 |
ble | -0.012 |
increasingly | -0.012 |
burn | -0.012 |
Token | their |
Token ID | 511 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
flower | +0.019 |
ble | +0.017 |
itating | +0.016 |
ric | +0.015 |
increasingly | +0.015 |
Neg logit contributions | |
Thank | -0.024 |
hugs | -0.021 |
vitamins | -0.021 |
Happy | -0.021 |
wo | -0.020 |
Token | doll |
Token ID | 3654 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
flower | +0.036 |
ble | +0.034 |
itating | +0.032 |
ric | +0.030 |
increasingly | +0.030 |
Neg logit contributions | |
Thank | -0.023 |
hugs | -0.020 |
vitamins | -0.019 |
wo | -0.019 |
ury | -0.018 |
Token | house |
Token ID | 4803 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ric | +0.103 |
itating | +0.103 |
ble | +0.102 |
increasingly | +0.102 |
flower | +0.099 |
Neg logit contributions | |
hugs | -0.083 |
goodbye | -0.079 |
Thank | -0.079 |
wo | -0.072 |
ives | -0.071 |
Token | away |
Token ID | 1497 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
flower | +0.191 |
ble | +0.171 |
itating | +0.163 |
ric | +0.163 |
increasingly | +0.153 |
Neg logit contributions | |
Thank | -0.215 |
ives | -0.188 |
hugs | -0.187 |
wo | -0.185 |
vitamins | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
flower | +0.068 |
ble | +0.060 |
ric | +0.059 |
itating | +0.058 |
increasingly | +0.054 |
Neg logit contributions | |
Thank | -0.051 |
hugs | -0.043 |
goodbye | -0.042 |
wo | -0.042 |
Happy | -0.042 |
Token | They |
Token ID | 1119 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
flower | +0.000 |
ble | +0.000 |
itating | +0.000 |
ric | +0.000 |
packs | +0.000 |
Neg logit contributions | |
Thank | -0.001 |
leaf | -0.001 |
ives | -0.001 |
vitamins | -0.001 |
ury | -0.001 |
Token | brushed |
Token ID | 31782 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Thank | +0.028 |
ury | +0.024 |
vitamins | +0.024 |
ives | +0.023 |
leaf | +0.023 |
Neg logit contributions | |
flower | -0.032 |
ble | -0.028 |
packs | -0.026 |
increasingly | -0.025 |
ric | -0.025 |
Token | their |
Token ID | 511 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Thank | +0.026 |
hugs | +0.024 |
wo | +0.023 |
goodbye | +0.023 |
ury | +0.023 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.016 |
itating | -0.015 |
ric | -0.015 |
increasingly | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Thank | +0.008 |
wo | +0.007 |
vitamins | +0.007 |
ives | +0.007 |
hugs | +0.007 |
Neg logit contributions | |
flower | -0.010 |
ric | -0.010 |
itating | -0.010 |
increasingly | -0.010 |
ble | -0.010 |
Token | make |
Token ID | 787 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
flower | +0.019 |
ble | +0.016 |
ric | +0.015 |
itating | +0.014 |
increasingly | +0.014 |
Neg logit contributions | |
Thank | -0.024 |
ury | -0.021 |
ives | -0.021 |
vitamins | -0.021 |
wo | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
flower | +0.136 |
ble | +0.117 |
itating | +0.112 |
ric | +0.110 |
increasingly | +0.106 |
Neg logit contributions | |
Thank | -0.118 |
vitamins | -0.100 |
ury | -0.099 |
wo | -0.098 |
hugs | -0.098 |
Token | big |
Token ID | 1263 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
flower | +0.071 |
ble | +0.062 |
itating | +0.061 |
ric | +0.060 |
increasingly | +0.057 |
Neg logit contributions | |
Thank | -0.061 |
wo | -0.051 |
thank | -0.050 |
vitamins | -0.049 |
ury | -0.049 |
Token | sand |
Token ID | 6450 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
flower | +0.105 |
ble | +0.092 |
itating | +0.084 |
ric | +0.083 |
increasingly | +0.081 |
Neg logit contributions | |
Thank | -0.115 |
ury | -0.099 |
vitamins | -0.099 |
wo | -0.098 |
ives | -0.097 |
Token | castle |
Token ID | 18676 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
itating | +0.068 |
increasingly | +0.067 |
flower | +0.067 |
ric | +0.066 |
ble | +0.060 |
Neg logit contributions | |
Thank | -0.065 |
wo | -0.057 |
thank | -0.055 |
vitamins | -0.053 |
hugs | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
flower | +0.209 |
ble | +0.186 |
ric | +0.175 |
itating | +0.174 |
increasingly | +0.170 |
Neg logit contributions | |
Thank | -0.204 |
ury | -0.173 |
wo | -0.170 |
ives | -0.170 |
vitamins | -0.170 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Thank | +0.001 |
vitamins | +0.001 |
ury | +0.001 |
ives | +0.001 |
leaf | +0.001 |
Neg logit contributions | |
flower | -0.001 |
ble | -0.001 |
itating | -0.001 |
ric | -0.001 |
packs | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Thank | +0.011 |
vitamins | +0.009 |
ives | +0.009 |
leaf | +0.009 |
ury | +0.009 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.013 |
ric | -0.011 |
increasingly | -0.011 |
itating | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
Thank | +0.047 |
leaf | +0.047 |
ives | +0.045 |
kids | +0.044 |
ets | +0.044 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.029 |
increasingly | -0.023 |
itating | -0.021 |
mill | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Thank | +0.028 |
vitamins | +0.026 |
ives | +0.026 |
leaf | +0.025 |
ets | +0.025 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.032 |
itating | -0.029 |
ric | -0.029 |
increasingly | -0.028 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Thank | +0.006 |
vitamins | +0.005 |
ury | +0.005 |
ives | +0.005 |
leaf | +0.005 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
itating | -0.006 |
ric | -0.006 |
increasingly | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
flower | +0.016 |
ble | +0.013 |
itating | +0.013 |
ric | +0.012 |
burn | +0.012 |
Neg logit contributions | |
Thank | -0.013 |
hugs | -0.011 |
vitamins | -0.011 |
wo | -0.011 |
ury | -0.011 |
Token | house |
Token ID | 2156 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Thank | +0.006 |
ury | +0.005 |
vitamins | +0.005 |
ives | +0.005 |
wo | +0.005 |
Neg logit contributions | |
flower | -0.007 |
ble | -0.007 |
itating | -0.006 |
ric | -0.006 |
increasingly | -0.006 |
Token | shake |
Token ID | 13279 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
Thank | +0.007 |
hugs | +0.006 |
wo | +0.006 |
thank | +0.006 |
ury | +0.006 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
ric | -0.007 |
itating | -0.007 |
increasingly | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
flower | +0.070 |
ble | +0.064 |
ric | +0.063 |
itating | +0.060 |
increasingly | +0.057 |
Neg logit contributions | |
Thank | -0.039 |
ly | -0.034 |
hugs | -0.033 |
wo | -0.032 |
ury | -0.032 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.005 |
itating | +0.004 |
ric | +0.004 |
increasingly | +0.004 |
Neg logit contributions | |
Thank | -0.006 |
ury | -0.005 |
vitamins | -0.005 |
ives | -0.005 |
wo | -0.005 |
Token | ble |
Token ID | 903 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
flower | +0.096 |
packs | +0.072 |
ric | +0.070 |
increasingly | +0.064 |
Back | +0.058 |
Neg logit contributions | |
ly | -0.266 |
Thank | -0.257 |
sed | -0.251 |
ury | -0.243 |
dear | -0.242 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
flower | +0.140 |
ric | +0.123 |
ble | +0.122 |
itating | +0.112 |
increasingly | +0.112 |
Neg logit contributions | |
Thank | -0.081 |
wo | -0.070 |
ly | -0.069 |
ury | -0.069 |
ets | -0.069 |
Token | They |
Token ID | 1119 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.008 |
itating | +0.007 |
ric | +0.007 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.008 |
ury | -0.007 |
vitamins | -0.007 |
ives | -0.007 |
wo | -0.007 |
Token | hugged |
Token ID | 41130 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Thank | +0.011 |
vitamins | +0.009 |
ury | +0.009 |
ives | +0.009 |
leaf | +0.009 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.013 |
ric | -0.012 |
itating | -0.012 |
increasingly | -0.012 |
Token | each |
Token ID | 1123 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Thank | +0.064 |
ury | +0.056 |
vitamins | +0.056 |
ives | +0.056 |
wo | +0.055 |
Neg logit contributions | |
flower | -0.057 |
ble | -0.050 |
ric | -0.045 |
itating | -0.045 |
increasingly | -0.044 |
Token | vegetables |
Token ID | 13701 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
flower | +0.070 |
ble | +0.061 |
increasingly | +0.055 |
packs | +0.054 |
els | +0.054 |
Neg logit contributions | |
Thank | -0.062 |
ury | -0.058 |
ives | -0.056 |
wo | -0.053 |
Bye | -0.051 |
Token | ! |
Token ID | 0 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Thank | +0.023 |
ury | +0.020 |
ives | +0.019 |
wo | +0.019 |
vitamins | +0.019 |
Neg logit contributions | |
flower | -0.032 |
ble | -0.029 |
ric | -0.028 |
itating | -0.027 |
increasingly | -0.027 |
Token | All |
Token ID | 1439 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
flower | +0.019 |
ble | +0.017 |
itating | +0.016 |
ric | +0.016 |
increasingly | +0.015 |
Neg logit contributions | |
Thank | -0.012 |
ury | -0.010 |
ives | -0.009 |
vitamins | -0.009 |
wo | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ble | +0.017 |
flower | +0.017 |
ric | +0.016 |
itating | +0.015 |
burn | +0.015 |
Neg logit contributions | |
Thank | -0.011 |
hugs | -0.010 |
Happy | -0.009 |
hours | -0.009 |
leaf | -0.009 |
Token | b |
Token ID | 275 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Thank | +0.072 |
ury | +0.062 |
ives | +0.062 |
wo | +0.060 |
vitamins | +0.059 |
Neg logit contributions | |
flower | -0.077 |
ble | -0.068 |
itating | -0.062 |
ric | -0.061 |
increasingly | -0.061 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
Thank | +0.070 |
Bye | +0.053 |
Happy | +0.052 |
wo | +0.051 |
ury | +0.050 |
Neg logit contributions | |
flower | -0.162 |
ble | -0.149 |
ric | -0.141 |
els | -0.137 |
itating | -0.136 |
Token | ies |
Token ID | 444 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Thank | +0.385 |
ury | +0.348 |
vitamins | +0.346 |
ives | +0.344 |
leaf | +0.343 |
Neg logit contributions | |
flower | -0.114 |
ble | -0.084 |
ric | -0.064 |
itating | -0.063 |
increasingly | -0.055 |
Token | were |
Token ID | 547 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Thank | +0.021 |
ury | +0.017 |
ives | +0.017 |
wo | +0.017 |
vitamins | +0.017 |
Neg logit contributions | |
flower | -0.029 |
ble | -0.027 |
ric | -0.025 |
itating | -0.025 |
increasingly | -0.024 |
Token | over |
Token ID | 625 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Thank | +0.021 |
vitamins | +0.018 |
wo | +0.017 |
hugs | +0.017 |
ury | +0.016 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.027 |
itating | -0.026 |
ric | -0.026 |
burn | -0.025 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.016 |
itating | +0.015 |
ric | +0.014 |
increasingly | +0.014 |
Neg logit contributions | |
Thank | -0.014 |
ury | -0.012 |
vitamins | -0.012 |
ives | -0.011 |
wo | -0.011 |
Token | ed |
Token ID | 276 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Thank | +0.155 |
vitamins | +0.129 |
ury | +0.123 |
wo | +0.123 |
leaf | +0.118 |
Neg logit contributions | |
flower | -0.292 |
ble | -0.258 |
itating | -0.243 |
packs | -0.241 |
ric | -0.239 |
Token | parade |
Token ID | 16134 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Thank | +0.024 |
ury | +0.020 |
vitamins | +0.020 |
ives | +0.020 |
wo | +0.020 |
Neg logit contributions | |
flower | -0.024 |
ble | -0.021 |
itating | -0.020 |
ric | -0.019 |
increasingly | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
flower | +0.012 |
ble | +0.011 |
ric | +0.010 |
itating | +0.010 |
increasingly | +0.010 |
Neg logit contributions | |
Thank | -0.012 |
ury | -0.010 |
ives | -0.010 |
wo | -0.010 |
vitamins | -0.010 |
Token | All |
Token ID | 1439 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
flower | +0.000 |
ble | +0.000 |
increasingly | +0.000 |
itating | +0.000 |
ric | +0.000 |
Neg logit contributions | |
Thank | -0.000 |
vitamins | -0.000 |
ury | -0.000 |
ives | -0.000 |
leaf | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.024 |
ric | +0.022 |
itating | +0.021 |
burn | +0.021 |
Neg logit contributions | |
Thank | -0.017 |
hugs | -0.015 |
Happy | -0.015 |
leaf | -0.014 |
ury | -0.014 |
Token | b |
Token ID | 275 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Thank | +0.068 |
ives | +0.058 |
ury | +0.058 |
sed | +0.056 |
icol | +0.056 |
Neg logit contributions | |
flower | -0.061 |
ble | -0.053 |
itating | -0.051 |
ric | -0.049 |
increasingly | -0.049 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
Thank | +0.068 |
vitamins | +0.050 |
Happy | +0.049 |
wo | +0.048 |
Bye | +0.047 |
Neg logit contributions | |
flower | -0.152 |
ble | -0.139 |
ric | -0.134 |
itating | -0.129 |
packs | -0.128 |
Token | ies |
Token ID | 444 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Thank | +0.371 |
ury | +0.335 |
vitamins | +0.334 |
ives | +0.331 |
wo | +0.331 |
Neg logit contributions | |
flower | -0.111 |
ble | -0.082 |
ric | -0.063 |
itating | -0.062 |
increasingly | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Thank | +0.016 |
vitamins | +0.013 |
ury | +0.013 |
ives | +0.013 |
wo | +0.013 |
Neg logit contributions | |
flower | -0.021 |
ble | -0.019 |
itating | -0.018 |
ric | -0.017 |
increasingly | -0.017 |
Token | people |
Token ID | 661 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
Thank | +0.017 |
ury | +0.015 |
vitamins | +0.015 |
ives | +0.015 |
wo | +0.014 |
Neg logit contributions | |
flower | -0.018 |
ble | -0.016 |
itating | -0.014 |
ric | -0.014 |
increasingly | -0.014 |
Token | cheered |
Token ID | 34767 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
itating | +0.002 |
ric | +0.002 |
increasingly | +0.002 |
Neg logit contributions | |
Thank | -0.001 |
vitamins | -0.001 |
ury | -0.001 |
ives | -0.001 |
wo | -0.001 |
Token | as |
Token ID | 355 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
Thank | +0.054 |
vitamins | +0.046 |
ury | +0.046 |
ives | +0.045 |
leaf | +0.045 |
Neg logit contributions | |
flower | -0.064 |
ble | -0.058 |
itating | -0.053 |
ric | -0.052 |
increasingly | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Thank | +0.008 |
hugs | +0.007 |
Happy | +0.007 |
vitamins | +0.007 |
wo | +0.007 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.008 |
itating | -0.007 |
ric | -0.007 |
increasingly | -0.006 |
Token | tree |
Token ID | 5509 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
Thank | +0.009 |
ury | +0.007 |
vitamins | +0.007 |
wo | +0.007 |
ives | +0.007 |
Neg logit contributions | |
flower | -0.011 |
ble | -0.010 |
itating | -0.009 |
ric | -0.009 |
increasingly | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Thank | +0.039 |
ury | +0.033 |
wo | +0.032 |
ives | +0.032 |
hugs | +0.032 |
Neg logit contributions | |
flower | -0.044 |
ble | -0.041 |
itating | -0.037 |
increasingly | -0.036 |
ric | -0.036 |
Token | Both |
Token ID | 5747 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.020 |
itating | +0.019 |
ric | +0.019 |
increasingly | +0.018 |
Neg logit contributions | |
Thank | -0.018 |
vitamins | -0.015 |
ury | -0.015 |
ives | -0.015 |
wo | -0.015 |
Token | b |
Token ID | 275 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
flower | +0.056 |
ble | +0.050 |
itating | +0.047 |
ric | +0.046 |
increasingly | +0.046 |
Neg logit contributions | |
Thank | -0.041 |
ury | -0.035 |
vitamins | -0.035 |
ives | -0.034 |
wo | -0.034 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
Thank | +0.062 |
vitamins | +0.045 |
ury | +0.045 |
Bye | +0.045 |
Happy | +0.044 |
Neg logit contributions | |
flower | -0.150 |
ble | -0.136 |
ric | -0.130 |
itating | -0.127 |
packs | -0.126 |
Token | ies |
Token ID | 444 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Thank | +0.360 |
ury | +0.326 |
vitamins | +0.325 |
ives | +0.323 |
leaf | +0.320 |
Neg logit contributions | |
flower | -0.115 |
ble | -0.087 |
ric | -0.068 |
itating | -0.068 |
increasingly | -0.060 |
Token | agreed |
Token ID | 4987 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Thank | +0.013 |
ury | +0.010 |
vitamins | +0.010 |
wo | +0.010 |
ives | +0.010 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
itating | -0.016 |
ric | -0.016 |
increasingly | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Thank | +0.029 |
ury | +0.024 |
vitamins | +0.023 |
wo | +0.023 |
ives | +0.023 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.034 |
itating | -0.032 |
ric | -0.032 |
increasingly | -0.031 |
Token | it |
Token ID | 340 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Thank | +0.063 |
ury | +0.053 |
vitamins | +0.053 |
wo | +0.052 |
ives | +0.052 |
Neg logit contributions | |
flower | -0.067 |
ble | -0.060 |
itating | -0.055 |
ric | -0.054 |
increasingly | -0.052 |
Token | had |
Token ID | 550 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
Thank | +0.038 |
ury | +0.033 |
vitamins | +0.032 |
ives | +0.032 |
wo | +0.032 |
Neg logit contributions | |
flower | -0.041 |
ble | -0.036 |
itating | -0.033 |
ric | -0.033 |
increasingly | -0.032 |
Token | She |
Token ID | 1375 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.014 |
itating | +0.014 |
ric | +0.013 |
increasingly | +0.013 |
Neg logit contributions | |
Thank | -0.015 |
vitamins | -0.014 |
ury | -0.013 |
ives | -0.013 |
leaf | -0.013 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
flower | +0.039 |
ble | +0.033 |
increasingly | +0.031 |
itating | +0.030 |
ric | +0.030 |
Neg logit contributions | |
Thank | -0.033 |
vitamins | -0.028 |
ives | -0.028 |
leaf | -0.027 |
ury | -0.026 |
Token | so |
Token ID | 523 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Thank | +0.080 |
ury | +0.070 |
ives | +0.068 |
vitamins | +0.067 |
wo | +0.066 |
Neg logit contributions | |
flower | -0.075 |
ble | -0.066 |
ric | -0.059 |
itating | -0.058 |
increasingly | -0.058 |
Token | many |
Token ID | 867 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
flower | +0.033 |
ble | +0.030 |
ric | +0.029 |
itating | +0.028 |
increasingly | +0.027 |
Neg logit contributions | |
Thank | -0.019 |
ury | -0.015 |
wo | -0.014 |
ives | -0.014 |
vitamins | -0.014 |
Token | b |
Token ID | 275 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Thank | +0.086 |
ury | +0.073 |
ives | +0.071 |
vitamins | +0.071 |
wo | +0.070 |
Neg logit contributions | |
flower | -0.104 |
ble | -0.093 |
itating | -0.086 |
ric | -0.085 |
increasingly | -0.084 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
Thank | +0.065 |
Happy | +0.047 |
ury | +0.046 |
Bye | +0.046 |
wo | +0.046 |
Neg logit contributions | |
flower | -0.150 |
ble | -0.139 |
ric | -0.130 |
itating | -0.127 |
els | -0.126 |
Token | ies |
Token ID | 444 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Thank | +0.381 |
Bye | +0.343 |
ury | +0.341 |
leaf | +0.340 |
ives | +0.336 |
Neg logit contributions | |
flower | -0.095 |
ble | -0.064 |
ric | -0.045 |
packs | -0.039 |
itating | -0.037 |
Token | that |
Token ID | 326 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Thank | +0.010 |
ury | +0.009 |
wo | +0.009 |
ives | +0.009 |
vitamins | +0.009 |
Neg logit contributions | |
flower | -0.013 |
ble | -0.012 |
itating | -0.011 |
ric | -0.011 |
increasingly | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Thank | +0.070 |
ury | +0.060 |
ives | +0.059 |
vitamins | +0.059 |
wo | +0.058 |
Neg logit contributions | |
flower | -0.081 |
ble | -0.072 |
itating | -0.065 |
ric | -0.065 |
increasingly | -0.064 |
Token | so |
Token ID | 523 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
itating | +0.008 |
ric | +0.008 |
packs | +0.007 |
Neg logit contributions | |
Thank | -0.006 |
wo | -0.006 |
vitamins | -0.006 |
hugs | -0.005 |
ury | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
flower | +0.038 |
ble | +0.034 |
ric | +0.032 |
itating | +0.031 |
increasingly | +0.030 |
Neg logit contributions | |
Thank | -0.029 |
vitamins | -0.024 |
ury | -0.024 |
wo | -0.024 |
ives | -0.024 |
Token | win |
Token ID | 1592 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Thank | +0.025 |
ury | +0.022 |
vitamins | +0.021 |
ives | +0.021 |
wo | +0.021 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.025 |
itating | -0.023 |
increasingly | -0.022 |
ric | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
flower | +0.066 |
ble | +0.059 |
ric | +0.055 |
itating | +0.055 |
increasingly | +0.053 |
Neg logit contributions | |
Thank | -0.057 |
ury | -0.049 |
ives | -0.048 |
wo | -0.048 |
vitamins | -0.048 |
Token | Jane |
Token ID | 12091 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Thank | +0.000 |
ury | +0.000 |
vitamins | +0.000 |
wo | +0.000 |
ives | +0.000 |
Neg logit contributions | |
flower | -0.000 |
ble | -0.000 |
itating | -0.000 |
ric | -0.000 |
increasingly | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Thank | +0.015 |
hugs | +0.012 |
wo | +0.012 |
ury | +0.012 |
ives | +0.012 |
Neg logit contributions | |
flower | -0.023 |
ble | -0.021 |
itating | -0.020 |
ric | -0.020 |
increasingly | -0.019 |
Token | over |
Token ID | 625 |
Feature activation | +9.97e-02 |
Pos logit contributions | |
Thank | +0.026 |
thank | +0.021 |
goodbye | +0.020 |
hugs | +0.020 |
wo | +0.020 |
Neg logit contributions | |
flower | -0.042 |
ble | -0.037 |
els | -0.036 |
ric | -0.035 |
packs | -0.035 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.008 |
itating | +0.007 |
ric | +0.007 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.003 |
ury | -0.003 |
vitamins | -0.002 |
ives | -0.002 |
wo | -0.002 |
Token | ed |
Token ID | 276 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Thank | +0.159 |
vitamins | +0.146 |
wo | +0.134 |
ury | +0.131 |
leaf | +0.128 |
Neg logit contributions | |
flower | -0.283 |
ble | -0.247 |
itating | -0.235 |
packs | -0.232 |
ric | -0.224 |
Token | ! |
Token ID | 0 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Thank | +0.101 |
ury | +0.083 |
hugs | +0.082 |
wo | +0.082 |
ives | +0.081 |
Neg logit contributions | |
flower | -0.125 |
ble | -0.112 |
ric | -0.107 |
itating | -0.104 |
increasingly | -0.100 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
Thank | +0.012 |
ury | +0.010 |
vitamins | +0.010 |
ives | +0.010 |
wo | +0.010 |
Neg logit contributions | |
flower | -0.013 |
ble | -0.012 |
itating | -0.011 |
ric | -0.011 |
increasingly | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Thank | +0.024 |
ives | +0.020 |
Happy | +0.020 |
ury | +0.020 |
hugs | +0.019 |
Neg logit contributions | |
flower | -0.023 |
ble | -0.021 |
itating | -0.019 |
ric | -0.019 |
increasingly | -0.018 |
Token | upon |
Token ID | 2402 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
flower | +0.053 |
ble | +0.044 |
increasingly | +0.041 |
ric | +0.040 |
burn | +0.040 |
Neg logit contributions | |
Thank | -0.066 |
wo | -0.059 |
ury | -0.058 |
hugs | -0.057 |
thank | -0.057 |
Token | was |
Token ID | 373 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
ric | +0.007 |
itating | +0.007 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.007 |
ury | -0.006 |
ives | -0.006 |
hugs | -0.006 |
wo | -0.006 |
Token | ready |
Token ID | 3492 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
Thank | +0.019 |
hours | +0.016 |
thank | +0.016 |
wo | +0.016 |
Happy | +0.015 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.028 |
ric | -0.028 |
itating | -0.027 |
els | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.004 |
itating | +0.004 |
ric | +0.004 |
increasingly | +0.004 |
Neg logit contributions | |
Thank | -0.004 |
ury | -0.004 |
vitamins | -0.004 |
ives | -0.004 |
wo | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Thank | +0.016 |
Happy | +0.013 |
ury | +0.013 |
wo | +0.013 |
hugs | +0.012 |
Neg logit contributions | |
flower | -0.024 |
ble | -0.022 |
ric | -0.021 |
itating | -0.021 |
increasingly | -0.020 |
Token | b |
Token ID | 275 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Thank | +0.026 |
ury | +0.022 |
vitamins | +0.022 |
ives | +0.022 |
wo | +0.021 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.027 |
itating | -0.025 |
ric | -0.025 |
increasingly | -0.024 |
Token | unn |
Token ID | 20935 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
Thank | +0.053 |
ury | +0.042 |
vitamins | +0.041 |
ives | +0.041 |
wo | +0.040 |
Neg logit contributions | |
flower | -0.108 |
ble | -0.099 |
itating | -0.093 |
ric | -0.092 |
increasingly | -0.090 |
Token | ies |
Token ID | 444 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Thank | +0.331 |
ury | +0.300 |
vitamins | +0.298 |
ives | +0.297 |
wo | +0.296 |
Neg logit contributions | |
flower | -0.117 |
ble | -0.093 |
itating | -0.078 |
ric | -0.075 |
increasingly | -0.070 |
Token | hopped |
Token ID | 45230 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
itating | +0.008 |
ric | +0.008 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.006 |
ury | -0.005 |
ives | -0.005 |
vitamins | -0.005 |
wo | -0.005 |
Token | over |
Token ID | 625 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Thank | +0.033 |
ives | +0.029 |
ury | +0.029 |
wo | +0.029 |
vitamins | +0.028 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.019 |
ric | -0.018 |
itating | -0.017 |
increasingly | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
flower | +0.028 |
ble | +0.025 |
itating | +0.023 |
ric | +0.023 |
increasingly | +0.022 |
Neg logit contributions | |
Thank | -0.022 |
ury | -0.018 |
vitamins | -0.018 |
ives | -0.018 |
wo | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
Thank | +0.038 |
ury | +0.034 |
ives | +0.033 |
vitamins | +0.033 |
wo | +0.032 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.027 |
ric | -0.025 |
itating | -0.024 |
increasingly | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
flower | +0.018 |
ble | +0.016 |
ric | +0.015 |
itating | +0.014 |
increasingly | +0.014 |
Neg logit contributions | |
Thank | -0.015 |
ury | -0.013 |
ives | -0.013 |
wo | -0.013 |
vitamins | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
flower | +0.010 |
ble | +0.009 |
itating | +0.008 |
ric | +0.008 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.008 |
vitamins | -0.007 |
ury | -0.007 |
wo | -0.007 |
ives | -0.007 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.014 |
itating | +0.013 |
ric | +0.012 |
increasingly | +0.012 |
Neg logit contributions | |
Thank | -0.011 |
vitamins | -0.009 |
ives | -0.009 |
ury | -0.009 |
wo | -0.009 |
Token | some |
Token ID | 617 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
Thank | +0.077 |
ury | +0.067 |
vitamins | +0.065 |
ives | +0.065 |
wo | +0.063 |
Neg logit contributions | |
flower | -0.078 |
ble | -0.069 |
itating | -0.063 |
increasingly | -0.062 |
ric | -0.062 |
Token | b |
Token ID | 275 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Thank | +0.039 |
ury | +0.033 |
vitamins | +0.033 |
ives | +0.032 |
wo | +0.032 |
Neg logit contributions | |
flower | -0.048 |
ble | -0.043 |
itating | -0.040 |
ric | -0.040 |
increasingly | -0.039 |
Token | unn |
Token ID | 20935 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
Thank | +0.072 |
Happy | +0.057 |
Bye | +0.056 |
vitamins | +0.054 |
wo | +0.053 |
Neg logit contributions | |
flower | -0.130 |
ble | -0.115 |
ric | -0.112 |
els | -0.108 |
itating | -0.107 |
Token | ies |
Token ID | 444 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
Thank | +0.335 |
ury | +0.304 |
vitamins | +0.302 |
ives | +0.300 |
wo | +0.300 |
Neg logit contributions | |
flower | -0.114 |
ble | -0.090 |
itating | -0.074 |
ric | -0.071 |
increasingly | -0.066 |
Token | running |
Token ID | 2491 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Thank | +0.004 |
hugs | +0.004 |
wo | +0.003 |
ury | +0.003 |
thank | +0.003 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.006 |
ric | -0.005 |
burn | -0.005 |
itating | -0.005 |
Token | around |
Token ID | 1088 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Thank | +0.033 |
wo | +0.029 |
ury | +0.029 |
ives | +0.028 |
hugs | +0.028 |
Neg logit contributions | |
flower | -0.037 |
ble | -0.034 |
ric | -0.031 |
itating | -0.030 |
burn | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Thank | +0.030 |
ury | +0.025 |
wo | +0.025 |
vitamins | +0.025 |
ives | +0.025 |
Neg logit contributions | |
flower | -0.032 |
ble | -0.029 |
itating | -0.026 |
ric | -0.026 |
increasingly | -0.025 |
Token | some |
Token ID | 617 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Thank | +0.008 |
ury | +0.007 |
vitamins | +0.007 |
ives | +0.007 |
leaf | +0.007 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
itating | -0.008 |
ric | -0.008 |
increasingly | -0.008 |
Token | b |
Token ID | 275 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Thank | +0.072 |
ury | +0.062 |
ives | +0.062 |
wo | +0.060 |
vitamins | +0.059 |
Neg logit contributions | |
flower | -0.077 |
ble | -0.068 |
itating | -0.062 |
ric | -0.061 |
increasingly | -0.061 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
Thank | +0.070 |
Bye | +0.053 |
Happy | +0.052 |
wo | +0.051 |
ury | +0.050 |
Neg logit contributions | |
flower | -0.162 |
ble | -0.149 |
ric | -0.141 |
els | -0.137 |
itating | -0.136 |
Token | ies |
Token ID | 444 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Thank | +0.385 |
ury | +0.348 |
vitamins | +0.346 |
ives | +0.344 |
leaf | +0.343 |
Neg logit contributions | |
flower | -0.114 |
ble | -0.084 |
ric | -0.064 |
itating | -0.063 |
increasingly | -0.055 |
Token | were |
Token ID | 547 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Thank | +0.021 |
ury | +0.017 |
ives | +0.017 |
wo | +0.017 |
vitamins | +0.017 |
Neg logit contributions | |
flower | -0.029 |
ble | -0.027 |
ric | -0.025 |
itating | -0.025 |
increasingly | -0.024 |
Token | over |
Token ID | 625 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Thank | +0.021 |
vitamins | +0.018 |
wo | +0.017 |
hugs | +0.017 |
ury | +0.016 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.027 |
itating | -0.026 |
ric | -0.026 |
burn | -0.025 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.016 |
itating | +0.015 |
ric | +0.014 |
increasingly | +0.014 |
Neg logit contributions | |
Thank | -0.014 |
ury | -0.012 |
vitamins | -0.012 |
ives | -0.011 |
wo | -0.011 |
Token | ed |
Token ID | 276 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Thank | +0.155 |
vitamins | +0.129 |
ury | +0.123 |
wo | +0.123 |
leaf | +0.118 |
Neg logit contributions | |
flower | -0.292 |
ble | -0.258 |
itating | -0.243 |
packs | -0.241 |
ric | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
Thank | +0.085 |
ury | +0.071 |
wo | +0.069 |
hugs | +0.069 |
ives | +0.068 |
Neg logit contributions | |
flower | -0.111 |
ble | -0.101 |
ric | -0.096 |
itating | -0.094 |
increasingly | -0.091 |
Token | |
Token ID | 220 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
Thank | +0.002 |
ury | +0.002 |
vitamins | +0.002 |
ives | +0.002 |
wo | +0.002 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
itating | -0.003 |
ric | -0.003 |
increasingly | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Thank | +0.038 |
ives | +0.033 |
ury | +0.032 |
wo | +0.029 |
hugs | +0.029 |
Neg logit contributions | |
flower | -0.060 |
ble | -0.051 |
burn | -0.047 |
itating | -0.047 |
increasingly | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Thank | +0.010 |
ury | +0.008 |
ives | +0.008 |
leaf | +0.008 |
wo | +0.008 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.012 |
ric | -0.011 |
burn | -0.011 |
itating | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
Thank | +0.004 |
hugs | +0.004 |
thank | +0.004 |
wo | +0.004 |
Happy | +0.004 |
Neg logit contributions | |
flower | -0.005 |
ble | -0.004 |
itating | -0.004 |
ric | -0.004 |
increasingly | -0.004 |
Token | cross |
Token ID | 3272 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Thank | +0.003 |
ury | +0.003 |
thank | +0.003 |
leaf | +0.003 |
wo | +0.003 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
packs | -0.003 |
itating | -0.003 |
ric | -0.003 |
Token | glow |
Token ID | 19634 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
flower | +0.090 |
ble | +0.083 |
itating | +0.077 |
ric | +0.075 |
burn | +0.073 |
Neg logit contributions | |
Thank | -0.077 |
thank | -0.068 |
goodbye | -0.067 |
hugs | -0.066 |
hours | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
flower | +0.047 |
ric | +0.047 |
ble | +0.045 |
itating | +0.043 |
increasingly | +0.041 |
Neg logit contributions | |
Thank | -0.034 |
ly | -0.032 |
ets | -0.031 |
goodbye | -0.029 |
hours | -0.029 |
Token | For |
Token ID | 1114 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
flower | +0.003 |
ble | +0.003 |
itating | +0.003 |
ric | +0.003 |
increasingly | +0.003 |
Neg logit contributions | |
Thank | -0.002 |
ury | -0.002 |
vitamins | -0.002 |
wo | -0.002 |
ives | -0.002 |
Token | days |
Token ID | 1528 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
Thank | +0.018 |
ury | +0.017 |
ives | +0.016 |
wo | +0.016 |
vitamins | +0.016 |
Neg logit contributions | |
flower | -0.016 |
ble | -0.014 |
ric | -0.013 |
increasingly | -0.013 |
itating | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
Thank | +0.238 |
vitamins | +0.223 |
leaf | +0.214 |
ives | +0.206 |
ury | +0.205 |
Neg logit contributions | |
flower | -0.201 |
ble | -0.170 |
itating | -0.159 |
ric | -0.153 |
increasingly | -0.151 |
Token | months |
Token ID | 1933 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Thank | +0.049 |
ives | +0.045 |
ury | +0.044 |
wo | +0.044 |
leaf | +0.043 |
Neg logit contributions | |
flower | -0.044 |
ble | -0.037 |
increasingly | -0.034 |
ric | -0.034 |
itating | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
Thank | +0.090 |
vitamins | +0.083 |
leaf | +0.078 |
wo | +0.078 |
ury | +0.078 |
Neg logit contributions | |
flower | -0.083 |
ble | -0.070 |
itating | -0.064 |
ric | -0.063 |
packs | -0.063 |
Token | years |
Token ID | 812 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Thank | +0.023 |
ives | +0.021 |
ury | +0.021 |
leaf | +0.020 |
wo | +0.020 |
Neg logit contributions | |
flower | -0.021 |
ble | -0.018 |
ric | -0.016 |
increasingly | -0.016 |
itating | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Thank | +0.133 |
vitamins | +0.118 |
ives | +0.117 |
ury | +0.114 |
leaf | +0.114 |
Neg logit contributions | |
flower | -0.141 |
ble | -0.125 |
itating | -0.113 |
ric | -0.109 |
increasingly | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
flower | +0.052 |
ble | +0.047 |
itating | +0.039 |
increasingly | +0.039 |
ric | +0.037 |
Neg logit contributions | |
Thank | -0.073 |
ury | -0.065 |
leaf | -0.064 |
ives | -0.064 |
wo | -0.063 |
Token | The |
Token ID | 383 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
leaf | +0.001 |
ury | +0.001 |
ives | +0.001 |
ets | +0.001 |
vitamins | +0.001 |
Neg logit contributions | |
flower | -0.001 |
ble | -0.001 |
increasingly | -0.001 |
ric | -0.001 |
itating | -0.001 |
Token | bird |
Token ID | 6512 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Thank | +0.033 |
ury | +0.030 |
ives | +0.030 |
vitamins | +0.029 |
wo | +0.028 |
Neg logit contributions | |
flower | -0.033 |
ble | -0.030 |
ric | -0.024 |
itating | -0.024 |
increasingly | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Thank | +0.025 |
ury | +0.021 |
vitamins | +0.021 |
wo | +0.021 |
ives | +0.021 |
Neg logit contributions | |
flower | -0.032 |
ble | -0.029 |
itating | -0.027 |
ric | -0.027 |
increasingly | -0.026 |
Token | over |
Token ID | 625 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Thank | +0.007 |
thank | +0.006 |
hugs | +0.006 |
goodbye | +0.006 |
wo | +0.006 |
Neg logit contributions | |
flower | -0.013 |
els | -0.012 |
packs | -0.012 |
ble | -0.012 |
itating | -0.011 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.021 |
itating | +0.019 |
increasingly | +0.019 |
ric | +0.019 |
Neg logit contributions | |
Thank | -0.011 |
ury | -0.009 |
ives | -0.009 |
vitamins | -0.009 |
leaf | -0.009 |
Token | ed |
Token ID | 276 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Thank | +0.174 |
vitamins | +0.170 |
wo | +0.155 |
dear | +0.150 |
icol | +0.149 |
Neg logit contributions | |
flower | -0.258 |
ble | -0.222 |
packs | -0.212 |
itating | -0.199 |
mill | -0.197 |
Token | . |
Token ID | 13 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
Thank | +0.102 |
ury | +0.087 |
vitamins | +0.086 |
ives | +0.086 |
wo | +0.085 |
Neg logit contributions | |
flower | -0.104 |
ble | -0.092 |
itating | -0.085 |
ric | -0.084 |
increasingly | -0.081 |
Token | |
Token ID | 220 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
leaf | +0.004 |
ury | +0.004 |
ives | +0.004 |
ets | +0.004 |
vitamins | +0.004 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
ric | -0.003 |
itating | -0.003 |
increasingly | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Thank | +0.042 |
ury | +0.035 |
ives | +0.035 |
wo | +0.033 |
vitamins | +0.033 |
Neg logit contributions | |
flower | -0.052 |
ble | -0.045 |
itating | -0.042 |
ric | -0.041 |
increasingly | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
Thank | +0.017 |
vitamins | +0.015 |
ury | +0.015 |
wo | +0.015 |
ives | +0.015 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.014 |
itating | -0.013 |
ric | -0.012 |
increasingly | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.018 |
ric | +0.017 |
itating | +0.017 |
increasingly | +0.016 |
Neg logit contributions | |
Thank | -0.024 |
wo | -0.021 |
goodbye | -0.020 |
Happy | -0.020 |
hugs | -0.020 |
Token | ! |
Token ID | 0 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
flower | +0.078 |
ble | +0.068 |
itating | +0.063 |
ric | +0.062 |
increasingly | +0.060 |
Neg logit contributions | |
Thank | -0.073 |
ury | -0.062 |
wo | -0.061 |
vitamins | -0.061 |
hugs | -0.060 |
Token | Will |
Token ID | 2561 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
flower | +0.003 |
ble | +0.002 |
ric | +0.002 |
itating | +0.002 |
increasingly | +0.002 |
Neg logit contributions | |
Thank | -0.002 |
vitamins | -0.002 |
ury | -0.002 |
ives | -0.002 |
leaf | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Thank | +0.122 |
vitamins | +0.106 |
ives | +0.103 |
leaf | +0.101 |
wo | +0.101 |
Neg logit contributions | |
flower | -0.138 |
ble | -0.125 |
itating | -0.114 |
ric | -0.112 |
increasingly | -0.110 |
Token | over |
Token ID | 625 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Thank | +0.020 |
Happy | +0.015 |
hugs | +0.015 |
wo | +0.015 |
thank | +0.015 |
Neg logit contributions | |
flower | -0.029 |
ble | -0.027 |
els | -0.025 |
itating | -0.024 |
packs | -0.024 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.021 |
itating | +0.020 |
ric | +0.019 |
increasingly | +0.019 |
Neg logit contributions | |
Thank | -0.009 |
ury | -0.007 |
vitamins | -0.007 |
ives | -0.007 |
wo | -0.007 |
Token | ed |
Token ID | 276 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Thank | +0.157 |
vitamins | +0.141 |
wo | +0.130 |
ury | +0.128 |
leaf | +0.127 |
Neg logit contributions | |
flower | -0.281 |
ble | -0.248 |
packs | -0.235 |
itating | -0.233 |
ric | -0.226 |
Token | by |
Token ID | 416 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Thank | +0.092 |
ury | +0.077 |
hugs | +0.074 |
wo | +0.074 |
ives | +0.073 |
Neg logit contributions | |
flower | -0.118 |
ble | -0.104 |
ric | -0.101 |
itating | -0.098 |
increasingly | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Thank | +0.061 |
wo | +0.052 |
thank | +0.050 |
Happy | +0.050 |
hugs | +0.050 |
Neg logit contributions | |
flower | -0.063 |
ble | -0.055 |
itating | -0.052 |
packs | -0.050 |
ric | -0.049 |
Token | recognition |
Token ID | 9465 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Thank | +0.016 |
ives | +0.015 |
ury | +0.015 |
vitamins | +0.014 |
wo | +0.014 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.014 |
itating | -0.013 |
ric | -0.013 |
mill | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
Thank | +0.008 |
ury | +0.007 |
wo | +0.007 |
ives | +0.007 |
hugs | +0.007 |
Neg logit contributions | |
flower | -0.011 |
ble | -0.010 |
ric | -0.009 |
itating | -0.009 |
increasingly | -0.009 |
Token | flower |
Token ID | 15061 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.018 |
itating | +0.018 |
ric | +0.017 |
increasingly | +0.017 |
Neg logit contributions | |
Thank | -0.022 |
wo | -0.018 |
ury | -0.018 |
vitamins | -0.018 |
ives | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
Thank | +0.004 |
wo | +0.003 |
ury | +0.003 |
ives | +0.003 |
hugs | +0.003 |
Neg logit contributions | |
flower | -0.004 |
ble | -0.004 |
increasingly | -0.004 |
itating | -0.004 |
ric | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
itating | +0.002 |
increasingly | +0.002 |
ric | +0.002 |
Neg logit contributions | |
leaf | -0.002 |
Thank | -0.002 |
vitamins | -0.002 |
ury | -0.002 |
ives | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
Thank | +0.036 |
vitamins | +0.031 |
ury | +0.030 |
ives | +0.030 |
leaf | +0.030 |
Neg logit contributions | |
flower | -0.043 |
ble | -0.037 |
ric | -0.034 |
itating | -0.034 |
increasingly | -0.033 |
Token | over |
Token ID | 625 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Thank | +0.015 |
hugs | +0.012 |
wo | +0.011 |
thank | +0.011 |
leaf | +0.011 |
Neg logit contributions | |
flower | -0.023 |
ble | -0.021 |
packs | -0.020 |
ric | -0.019 |
itating | -0.019 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
flower | +0.030 |
ble | +0.027 |
itating | +0.025 |
increasingly | +0.025 |
ric | +0.025 |
Neg logit contributions | |
Thank | -0.012 |
ury | -0.010 |
vitamins | -0.010 |
ives | -0.010 |
wo | -0.009 |
Token | ed |
Token ID | 276 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Thank | +0.162 |
vitamins | +0.154 |
wo | +0.138 |
ury | +0.134 |
leaf | +0.133 |
Neg logit contributions | |
flower | -0.278 |
ble | -0.239 |
packs | -0.224 |
itating | -0.224 |
burn | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
Thank | +0.093 |
ury | +0.078 |
wo | +0.077 |
ives | +0.076 |
hugs | +0.076 |
Neg logit contributions | |
flower | -0.109 |
ble | -0.098 |
ric | -0.092 |
itating | -0.090 |
increasingly | -0.087 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Thank | +0.031 |
ives | +0.031 |
vitamins | +0.030 |
ury | +0.030 |
leaf | +0.027 |
Neg logit contributions | |
flower | -0.045 |
ble | -0.040 |
increasingly | -0.036 |
itating | -0.035 |
ric | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Thank | +0.011 |
ury | +0.010 |
vitamins | +0.010 |
ives | +0.010 |
wo | +0.009 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.008 |
itating | -0.008 |
ric | -0.007 |
increasingly | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Thank | +0.022 |
ury | +0.021 |
ives | +0.021 |
vitamins | +0.020 |
ets | +0.020 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.016 |
ric | -0.014 |
itating | -0.013 |
increasingly | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Thank | +0.047 |
hugs | +0.041 |
ives | +0.041 |
vitamins | +0.041 |
ury | +0.040 |
Neg logit contributions | |
flower | -0.067 |
ble | -0.060 |
ric | -0.058 |
itating | -0.057 |
burn | -0.054 |
Token | school |
Token ID | 1524 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Thank | +0.031 |
vitamins | +0.027 |
wo | +0.026 |
ury | +0.026 |
hugs | +0.026 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.028 |
itating | -0.026 |
ric | -0.025 |
increasingly | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Thank | +0.040 |
ury | +0.035 |
vitamins | +0.034 |
ives | +0.034 |
wo | +0.034 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.033 |
itating | -0.030 |
ric | -0.030 |
increasingly | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Thank | +0.016 |
leaf | +0.015 |
vitamins | +0.015 |
ury | +0.015 |
kids | +0.014 |
Neg logit contributions | |
flower | -0.012 |
ble | -0.010 |
itating | -0.010 |
increasingly | -0.009 |
ric | -0.009 |
Token | B |
Token ID | 33 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Thank | +0.024 |
ury | +0.021 |
leaf | +0.021 |
vitamins | +0.021 |
ives | +0.020 |
Neg logit contributions | |
flower | -0.025 |
ble | -0.023 |
ric | -0.022 |
itating | -0.020 |
packs | -0.020 |
Token | unn |
Token ID | 20935 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
Thank | +0.114 |
vitamins | +0.098 |
ury | +0.097 |
wo | +0.096 |
leaf | +0.095 |
Neg logit contributions | |
flower | -0.102 |
ble | -0.089 |
itating | -0.081 |
ric | -0.081 |
increasingly | -0.077 |
Token | ies |
Token ID | 444 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
Thank | +0.341 |
ury | +0.309 |
vitamins | +0.306 |
ives | +0.305 |
leaf | +0.304 |
Neg logit contributions | |
flower | -0.106 |
ble | -0.080 |
ric | -0.063 |
itating | -0.061 |
increasingly | -0.053 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Thank | +0.001 |
ury | +0.001 |
ives | +0.001 |
vitamins | +0.001 |
wo | +0.001 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
itating | -0.001 |
ric | -0.001 |
increasingly | -0.001 |
Token | carrots |
Token ID | 34397 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Thank | +0.063 |
vitamins | +0.053 |
ury | +0.052 |
wo | +0.052 |
ives | +0.051 |
Neg logit contributions | |
flower | -0.086 |
ble | -0.077 |
itating | -0.073 |
ric | -0.072 |
increasingly | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Thank | +0.068 |
vitamins | +0.057 |
ives | +0.057 |
ury | +0.056 |
wo | +0.056 |
Neg logit contributions | |
flower | -0.097 |
ble | -0.086 |
itating | -0.084 |
ric | -0.084 |
increasingly | -0.081 |
Token | grass |
Token ID | 8701 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Thank | +0.007 |
ury | +0.006 |
ives | +0.006 |
leaf | +0.006 |
Bye | +0.006 |
Neg logit contributions | |
flower | -0.007 |
ble | -0.006 |
ric | -0.006 |
increasingly | -0.006 |
packs | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
Thank | +0.082 |
vitamins | +0.070 |
ury | +0.069 |
wo | +0.068 |
ives | +0.068 |
Neg logit contributions | |
flower | -0.094 |
ble | -0.084 |
itating | -0.079 |
ric | -0.077 |
increasingly | -0.075 |
Token | The |
Token ID | 383 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
Thank | +0.001 |
ury | +0.001 |
ives | +0.000 |
vitamins | +0.000 |
wo | +0.000 |
Neg logit contributions | |
flower | -0.001 |
ble | -0.001 |
itating | -0.001 |
ric | -0.001 |
increasingly | -0.001 |
Token | squirrel |
Token ID | 33039 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Thank | +0.033 |
ury | +0.029 |
ives | +0.029 |
vitamins | +0.028 |
leaf | +0.028 |
Neg logit contributions | |
flower | -0.040 |
ble | -0.036 |
itating | -0.032 |
ric | -0.032 |
increasingly | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Thank | +0.037 |
wo | +0.031 |
ury | +0.030 |
hugs | +0.030 |
ives | +0.030 |
Neg logit contributions | |
flower | -0.066 |
ble | -0.063 |
itating | -0.059 |
ric | -0.059 |
increasingly | -0.056 |
Token | over |
Token ID | 625 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Thank | +0.012 |
thank | +0.009 |
wo | +0.009 |
hugs | +0.009 |
goodbye | +0.009 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.018 |
itating | -0.017 |
ric | -0.017 |
packs | -0.017 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
flower | +0.030 |
ble | +0.027 |
itating | +0.026 |
ric | +0.026 |
increasingly | +0.025 |
Neg logit contributions | |
Thank | -0.012 |
ury | -0.009 |
vitamins | -0.009 |
ives | -0.009 |
wo | -0.009 |
Token | ed |
Token ID | 276 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Thank | +0.152 |
vitamins | +0.129 |
wo | +0.123 |
ury | +0.122 |
leaf | +0.118 |
Neg logit contributions | |
flower | -0.286 |
ble | -0.256 |
itating | -0.240 |
packs | -0.236 |
ric | -0.234 |
Token | ! |
Token ID | 0 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
Thank | +0.087 |
ury | +0.072 |
wo | +0.071 |
hugs | +0.070 |
ives | +0.070 |
Neg logit contributions | |
flower | -0.108 |
ble | -0.096 |
ric | -0.092 |
itating | -0.090 |
increasingly | -0.087 |
Token | He |
Token ID | 679 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Thank | +0.004 |
ury | +0.004 |
ives | +0.003 |
vitamins | +0.003 |
wo | +0.003 |
Neg logit contributions | |
flower | -0.005 |
ble | -0.005 |
itating | -0.005 |
ric | -0.004 |
increasingly | -0.004 |
Token | thanked |
Token ID | 26280 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
Thank | +0.011 |
vitamins | +0.010 |
ives | +0.010 |
ury | +0.009 |
leaf | +0.009 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.016 |
increasingly | -0.014 |
itating | -0.014 |
ric | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Thank | +0.039 |
ury | +0.034 |
vitamins | +0.034 |
ives | +0.034 |
wo | +0.033 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.027 |
itating | -0.024 |
ric | -0.024 |
increasingly | -0.023 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.014 |
itating | +0.013 |
ric | +0.013 |
increasingly | +0.012 |
Neg logit contributions | |
Thank | -0.013 |
ury | -0.011 |
vitamins | -0.011 |
ives | -0.011 |
wo | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
Thank | +0.001 |
ury | +0.001 |
vitamins | +0.001 |
wo | +0.001 |
ives | +0.001 |
Neg logit contributions | |
flower | -0.001 |
ble | -0.001 |
itating | -0.001 |
ric | -0.001 |
increasingly | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
leaf | +0.002 |
Thank | +0.002 |
vitamins | +0.002 |
sed | +0.002 |
wo | +0.002 |
Neg logit contributions | |
flower | -0.001 |
ric | -0.001 |
itating | -0.001 |
increasingly | -0.001 |
ble | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
flower | +0.007 |
ble | +0.006 |
increasingly | +0.006 |
ric | +0.006 |
itating | +0.006 |
Neg logit contributions | |
Thank | -0.005 |
ives | -0.005 |
ury | -0.005 |
vitamins | -0.005 |
leaf | -0.004 |
Token | over |
Token ID | 625 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
Thank | +0.007 |
wo | +0.006 |
hugs | +0.006 |
vitamins | +0.006 |
leaf | +0.006 |
Neg logit contributions | |
flower | -0.011 |
ble | -0.010 |
ric | -0.009 |
itating | -0.009 |
packs | -0.009 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
flower | +0.035 |
ble | +0.032 |
increasingly | +0.030 |
itating | +0.030 |
ric | +0.029 |
Neg logit contributions | |
Thank | -0.016 |
ury | -0.013 |
ives | -0.013 |
vitamins | -0.013 |
wo | -0.012 |
Token | ed |
Token ID | 276 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Thank | +0.161 |
vitamins | +0.152 |
wo | +0.138 |
ury | +0.134 |
leaf | +0.134 |
Neg logit contributions | |
flower | -0.268 |
ble | -0.235 |
packs | -0.222 |
itating | -0.218 |
ric | -0.208 |
Token | that |
Token ID | 326 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Thank | +0.095 |
ury | +0.080 |
wo | +0.078 |
vitamins | +0.078 |
ives | +0.078 |
Neg logit contributions | |
flower | -0.110 |
ble | -0.097 |
ric | -0.092 |
itating | -0.090 |
increasingly | -0.087 |
Token | her |
Token ID | 607 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
Thank | +0.091 |
ury | +0.076 |
vitamins | +0.076 |
wo | +0.075 |
ives | +0.074 |
Neg logit contributions | |
flower | -0.106 |
ble | -0.095 |
itating | -0.088 |
ric | -0.088 |
increasingly | -0.085 |
Token | pet |
Token ID | 4273 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
Thank | +0.037 |
ury | +0.032 |
vitamins | +0.032 |
ives | +0.031 |
wo | +0.031 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.034 |
itating | -0.031 |
ric | -0.031 |
increasingly | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Thank | +0.040 |
ury | +0.033 |
vitamins | +0.033 |
ives | +0.033 |
wo | +0.033 |
Neg logit contributions | |
flower | -0.048 |
ble | -0.043 |
itating | -0.040 |
ric | -0.040 |
increasingly | -0.039 |
Token | rock |
Token ID | 3881 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
flower | +0.052 |
ble | +0.046 |
ric | +0.041 |
itating | +0.041 |
increasingly | +0.039 |
Neg logit contributions | |
Thank | -0.045 |
ury | -0.039 |
ives | -0.039 |
vitamins | -0.038 |
leaf | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
itating | +0.005 |
ric | +0.005 |
increasingly | +0.005 |
Neg logit contributions | |
Thank | -0.005 |
ury | -0.004 |
wo | -0.004 |
hugs | -0.004 |
ives | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.004 |
itating | +0.004 |
increasingly | +0.004 |
packs | +0.004 |
Neg logit contributions | |
Thank | -0.005 |
vitamins | -0.005 |
leaf | -0.005 |
ury | -0.004 |
wo | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Thank | +0.030 |
vitamins | +0.026 |
ives | +0.026 |
ury | +0.026 |
leaf | +0.025 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
ric | -0.021 |
itating | -0.021 |
increasingly | -0.021 |
Token | over |
Token ID | 625 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Thank | +0.013 |
wo | +0.010 |
hugs | +0.010 |
ury | +0.010 |
leaf | +0.010 |
Neg logit contributions | |
flower | -0.018 |
ble | -0.016 |
ric | -0.015 |
itating | -0.015 |
packs | -0.015 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
flower | +0.026 |
ble | +0.023 |
increasingly | +0.022 |
itating | +0.022 |
packs | +0.022 |
Neg logit contributions | |
Thank | -0.013 |
vitamins | -0.012 |
ury | -0.011 |
ives | -0.011 |
leaf | -0.011 |
Token | ed |
Token ID | 276 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Thank | +0.161 |
vitamins | +0.150 |
wo | +0.137 |
ury | +0.133 |
leaf | +0.132 |
Neg logit contributions | |
flower | -0.273 |
ble | -0.235 |
packs | -0.227 |
itating | -0.222 |
burn | -0.212 |
Token | and |
Token ID | 290 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
Thank | +0.094 |
ury | +0.078 |
hugs | +0.076 |
wo | +0.076 |
ives | +0.076 |
Neg logit contributions | |
flower | -0.114 |
ble | -0.103 |
ric | -0.098 |
itating | -0.095 |
increasingly | -0.093 |
Token | knew |
Token ID | 2993 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Thank | +0.026 |
ives | +0.026 |
vitamins | +0.025 |
ury | +0.025 |
ets | +0.023 |
Neg logit contributions | |
flower | -0.041 |
ble | -0.037 |
increasingly | -0.034 |
itating | -0.033 |
mill | -0.032 |
Token | it |
Token ID | 340 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
itating | +0.018 |
ric | +0.018 |
increasingly | +0.017 |
Neg logit contributions | |
Thank | -0.015 |
ury | -0.012 |
vitamins | -0.012 |
wo | -0.012 |
ives | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Thank | +0.020 |
vitamins | +0.017 |
ury | +0.017 |
ives | +0.017 |
wo | +0.017 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
itating | -0.015 |
ric | -0.015 |
increasingly | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
Thank | +0.048 |
ury | +0.045 |
ives | +0.042 |
Bye | +0.041 |
leaf | +0.040 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.025 |
ric | -0.023 |
packs | -0.023 |
els | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
Thank | +0.034 |
ury | +0.029 |
vitamins | +0.029 |
ives | +0.029 |
wo | +0.029 |
Neg logit contributions | |
flower | -0.033 |
ble | -0.029 |
itating | -0.027 |
ric | -0.027 |
increasingly | -0.026 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
flower | +0.003 |
increasingly | +0.003 |
itating | +0.003 |
house | +0.002 |
ble | +0.002 |
Neg logit contributions | |
leaf | -0.005 |
vitamins | -0.005 |
sed | -0.004 |
wo | -0.004 |
kids | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Thank | +0.041 |
vitamins | +0.036 |
leaf | +0.035 |
ives | +0.035 |
ury | +0.035 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.033 |
itating | -0.029 |
ric | -0.029 |
increasingly | -0.028 |
Token | over |
Token ID | 625 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Thank | +0.012 |
hugs | +0.009 |
wo | +0.009 |
thank | +0.009 |
goodbye | +0.009 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
ric | -0.017 |
els | -0.017 |
packs | -0.016 |
Token | joy |
Token ID | 2633 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
flower | +0.027 |
ble | +0.023 |
increasingly | +0.022 |
itating | +0.022 |
packs | +0.021 |
Neg logit contributions | |
Thank | -0.015 |
vitamins | -0.013 |
ives | -0.013 |
ury | -0.013 |
leaf | -0.013 |
Token | ed |
Token ID | 276 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
vitamins | +0.181 |
Thank | +0.177 |
wo | +0.160 |
leaf | +0.158 |
thank | +0.156 |
Neg logit contributions | |
flower | -0.248 |
packs | -0.205 |
ble | -0.203 |
y | -0.190 |
itating | -0.188 |
Token | and |
Token ID | 290 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
Thank | +0.095 |
ury | +0.081 |
wo | +0.079 |
ives | +0.079 |
vitamins | +0.079 |
Neg logit contributions | |
flower | -0.107 |
ble | -0.095 |
ric | -0.088 |
itating | -0.088 |
increasingly | -0.085 |
Token | played |
Token ID | 2826 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
vitamins | +0.028 |
ives | +0.028 |
ury | +0.026 |
Thank | +0.026 |
ets | +0.025 |
Neg logit contributions | |
flower | -0.037 |
ble | -0.034 |
increasingly | -0.031 |
itating | -0.029 |
mill | -0.028 |
Token | with |
Token ID | 351 |
Feature activation | -5.09e-04 |
Pos logit contributions | |
flower | +0.043 |
ble | +0.039 |
itating | +0.032 |
increasingly | +0.032 |
mill | +0.029 |
Neg logit contributions | |
Thank | -0.073 |
vitamins | -0.066 |
ury | -0.066 |
wo | -0.065 |
ives | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
Thank | +0.000 |
ury | +0.000 |
ives | +0.000 |
vitamins | +0.000 |
wo | +0.000 |
Neg logit contributions | |
flower | -0.000 |
ble | -0.000 |
itating | -0.000 |
ric | -0.000 |
increasingly | -0.000 |
Token | kind |
Token ID | 1611 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
flower | +0.093 |
ble | +0.084 |
itating | +0.079 |
ric | +0.079 |
increasingly | +0.075 |
Neg logit contributions | |
Thank | -0.060 |
vitamins | -0.049 |
ury | -0.048 |
hugs | -0.047 |
wo | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Thank | +0.042 |
leaf | +0.038 |
ury | +0.037 |
wo | +0.037 |
vitamins | +0.037 |
Neg logit contributions | |
flower | -0.034 |
ble | -0.029 |
packs | -0.026 |
itating | -0.025 |
ric | -0.025 |
Token | Thank |
Token ID | 6952 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Thank | +0.001 |
ury | +0.001 |
leaf | +0.001 |
ives | +0.001 |
vitamins | +0.001 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
ric | -0.001 |
itating | -0.001 |
increasingly | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Thank | +0.075 |
ives | +0.066 |
ury | +0.066 |
sed | +0.065 |
icol | +0.064 |
Neg logit contributions | |
flower | -0.111 |
ble | -0.106 |
els | -0.092 |
itating | -0.090 |
ric | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Thank | +0.035 |
leaf | +0.035 |
vitamins | +0.033 |
ury | +0.031 |
ives | +0.031 |
Neg logit contributions | |
flower | -0.044 |
ble | -0.039 |
ric | -0.035 |
itating | -0.034 |
packs | -0.034 |
Token | Amen |
Token ID | 34717 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
ets | +0.022 |
ives | +0.022 |
hours | +0.022 |
ury | +0.021 |
leaf | +0.021 |
Neg logit contributions | |
flower | -0.045 |
ble | -0.040 |
ric | -0.039 |
itating | -0.037 |
burn | -0.035 |
Token | ." |
Token ID | 526 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Thank | +0.198 |
leaf | +0.195 |
vitamins | +0.187 |
ury | +0.184 |
icol | +0.183 |
Neg logit contributions | |
flower | -0.219 |
ble | -0.197 |
ric | -0.187 |
packs | -0.179 |
itating | -0.169 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Thank | +0.071 |
vitamins | +0.064 |
ury | +0.064 |
leaf | +0.063 |
ives | +0.062 |
Neg logit contributions | |
flower | -0.061 |
ble | -0.054 |
itating | -0.050 |
ric | -0.048 |
increasingly | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
Thank | +0.006 |
vitamins | +0.005 |
ury | +0.005 |
ives | +0.005 |
wo | +0.005 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
itating | -0.005 |
ric | -0.004 |
increasingly | -0.004 |
Token | Then |
Token ID | 6423 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.004 |
ric | +0.004 |
itating | +0.004 |
increasingly | +0.004 |
Neg logit contributions | |
Thank | -0.005 |
ury | -0.005 |
ives | -0.005 |
vitamins | -0.005 |
wo | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
flower | +0.065 |
ble | +0.059 |
ric | +0.057 |
itating | +0.057 |
increasingly | +0.053 |
Neg logit contributions | |
Thank | -0.045 |
hugs | -0.036 |
Happy | -0.036 |
wo | -0.036 |
thank | -0.035 |
Token | thought |
Token ID | 1807 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Thank | +0.030 |
vitamins | +0.026 |
leaf | +0.025 |
ives | +0.024 |
Bye | +0.024 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.026 |
itating | -0.024 |
increasingly | -0.024 |
ric | -0.024 |
Token | they |
Token ID | 484 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Thank | +0.012 |
ives | +0.010 |
ury | +0.010 |
vitamins | +0.010 |
leaf | +0.009 |
Neg logit contributions | |
flower | -0.011 |
ble | -0.011 |
itating | -0.010 |
increasingly | -0.009 |
ric | -0.009 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.021 |
itating | +0.019 |
ric | +0.019 |
increasingly | +0.019 |
Neg logit contributions | |
Thank | -0.016 |
ury | -0.013 |
vitamins | -0.013 |
ives | -0.013 |
wo | -0.013 |
Token | like |
Token ID | 588 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.021 |
itating | +0.020 |
ric | +0.019 |
increasingly | +0.019 |
Neg logit contributions | |
Thank | -0.023 |
ury | -0.019 |
vitamins | -0.019 |
ives | -0.019 |
wo | -0.019 |
Token | ac |
Token ID | 936 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.017 |
increasingly | +0.015 |
packs | +0.015 |
mill | +0.015 |
Neg logit contributions | |
Thank | -0.023 |
ives | -0.020 |
ury | -0.020 |
vitamins | -0.019 |
leaf | -0.019 |
Token | rob |
Token ID | 22609 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
Thank | +0.038 |
wo | +0.030 |
vitamins | +0.030 |
ury | +0.029 |
sed | +0.028 |
Neg logit contributions | |
flower | -0.062 |
ble | -0.056 |
itating | -0.052 |
ric | -0.051 |
burn | -0.049 |
Token | ats |
Token ID | 1381 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Thank | +0.249 |
ury | +0.212 |
wo | +0.205 |
vitamins | +0.204 |
leaf | +0.204 |
Neg logit contributions | |
flower | -0.194 |
ble | -0.170 |
ric | -0.153 |
itating | -0.153 |
packs | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Thank | +0.082 |
wo | +0.071 |
ives | +0.070 |
hugs | +0.069 |
ury | +0.069 |
Neg logit contributions | |
flower | -0.103 |
ble | -0.097 |
ric | -0.090 |
itating | -0.088 |
increasingly | -0.087 |
Token | She |
Token ID | 1375 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Thank | +0.007 |
leaf | +0.007 |
vitamins | +0.007 |
ives | +0.006 |
wo | +0.006 |
Neg logit contributions | |
flower | -0.005 |
itating | -0.004 |
ble | -0.004 |
increasingly | -0.004 |
ric | -0.004 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
increasingly | +0.008 |
itating | +0.007 |
ric | +0.007 |
Neg logit contributions | |
Thank | -0.008 |
ives | -0.006 |
vitamins | -0.006 |
leaf | -0.006 |
ury | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Thank | +0.069 |
ives | +0.061 |
ury | +0.059 |
vitamins | +0.058 |
leaf | +0.057 |
Neg logit contributions | |
flower | -0.069 |
ble | -0.063 |
ric | -0.058 |
increasingly | -0.055 |
itating | -0.054 |
Token | he |
Token ID | 339 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
Thank | +0.007 |
ives | +0.006 |
vitamins | +0.006 |
ury | +0.006 |
wo | +0.006 |
Neg logit contributions | |
flower | -0.007 |
ble | -0.006 |
itating | -0.006 |
increasingly | -0.006 |
ric | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
increasingly | +0.001 |
itating | +0.001 |
ric | +0.001 |
Neg logit contributions | |
Thank | -0.001 |
vitamins | -0.001 |
ives | -0.001 |
leaf | -0.001 |
ury | -0.001 |
Token | two |
Token ID | 734 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Thank | +0.069 |
ury | +0.061 |
ives | +0.060 |
vitamins | +0.059 |
wo | +0.059 |
Neg logit contributions | |
flower | -0.057 |
ble | -0.053 |
increasingly | -0.046 |
ric | -0.046 |
itating | -0.046 |
Token | other |
Token ID | 584 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.009 |
itating | +0.009 |
ric | +0.009 |
increasingly | +0.008 |
Neg logit contributions | |
Thank | -0.008 |
ury | -0.007 |
vitamins | -0.007 |
wo | -0.007 |
ives | -0.007 |
Token | b |
Token ID | 275 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Thank | +0.071 |
ury | +0.061 |
ives | +0.060 |
vitamins | +0.059 |
leaf | +0.059 |
Neg logit contributions | |
flower | -0.077 |
ble | -0.068 |
itating | -0.062 |
ric | -0.062 |
increasingly | -0.061 |
Token | unn |
Token ID | 20935 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
Thank | +0.079 |
Bye | +0.061 |
Happy | +0.060 |
thank | +0.058 |
wo | +0.056 |
Neg logit contributions | |
flower | -0.142 |
ble | -0.128 |
ric | -0.126 |
els | -0.122 |
packs | -0.121 |
Token | ies |
Token ID | 444 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Thank | +0.341 |
ury | +0.308 |
vitamins | +0.307 |
ives | +0.305 |
leaf | +0.304 |
Neg logit contributions | |
flower | -0.101 |
ble | -0.074 |
ric | -0.057 |
itating | -0.055 |
increasingly | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
Thank | +0.007 |
hugs | +0.006 |
wo | +0.006 |
ury | +0.006 |
ives | +0.006 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
ric | -0.009 |
itating | -0.009 |
increasingly | -0.009 |
Token | Paul |
Token ID | 3362 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Thank | +0.031 |
ury | +0.027 |
vitamins | +0.026 |
ives | +0.026 |
wo | +0.026 |
Neg logit contributions | |
flower | -0.037 |
ble | -0.033 |
itating | -0.031 |
ric | -0.031 |
increasingly | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Thank | +0.053 |
ury | +0.046 |
wo | +0.045 |
hugs | +0.044 |
ives | +0.043 |
Neg logit contributions | |
flower | -0.066 |
ble | -0.061 |
itating | -0.056 |
increasingly | -0.056 |
ric | -0.055 |
Token | Mary |
Token ID | 5335 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Thank | +0.007 |
ury | +0.006 |
ives | +0.006 |
vitamins | +0.006 |
wo | +0.006 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.008 |
itating | -0.007 |
ric | -0.007 |
increasingly | -0.007 |
Token | asked |
Token ID | 1965 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
Thank | +0.004 |
vitamins | +0.003 |
ives | +0.003 |
leaf | +0.003 |
ury | +0.003 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
itating | -0.005 |
ric | -0.005 |
increasingly | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Thank | +0.006 |
ury | +0.006 |
leaf | +0.006 |
vitamins | +0.006 |
ives | +0.006 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
packs | -0.002 |
increasingly | -0.002 |
els | -0.002 |
Token | tree |
Token ID | 5509 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
flower | +0.019 |
ble | +0.017 |
itating | +0.016 |
ric | +0.016 |
increasingly | +0.015 |
Neg logit contributions | |
Thank | -0.018 |
ury | -0.016 |
vitamins | -0.015 |
ives | -0.015 |
wo | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
Thank | +0.024 |
wo | +0.020 |
hugs | +0.019 |
thank | +0.019 |
goodbye | +0.019 |
Neg logit contributions | |
flower | -0.050 |
ble | -0.049 |
ric | -0.047 |
itating | -0.046 |
burn | -0.046 |
Token | " |
Token ID | 366 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Thank | +0.003 |
vitamins | +0.003 |
ury | +0.003 |
ives | +0.003 |
leaf | +0.003 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.006 |
itating | -0.005 |
ric | -0.005 |
increasingly | -0.005 |
Token | Why |
Token ID | 5195 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.011 |
ric | +0.010 |
itating | +0.010 |
packs | +0.010 |
Neg logit contributions | |
Thank | -0.016 |
ury | -0.014 |
ives | -0.013 |
Bye | -0.013 |
vitamins | -0.013 |
Token | do |
Token ID | 466 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
flower | +0.145 |
ble | +0.134 |
ric | +0.118 |
packs | +0.113 |
itating | +0.113 |
Neg logit contributions | |
Thank | -0.145 |
leaf | -0.128 |
vitamins | -0.124 |
ives | -0.122 |
ury | -0.121 |
Token | you |
Token ID | 345 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
flower | +0.115 |
ble | +0.111 |
itating | +0.101 |
ric | +0.099 |
increasingly | +0.098 |
Neg logit contributions | |
Thank | -0.058 |
ives | -0.047 |
vitamins | -0.046 |
leaf | -0.044 |
ury | -0.044 |
Token | look |
Token ID | 804 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
itating | +0.002 |
increasingly | +0.002 |
Neg logit contributions | |
Thank | -0.002 |
vitamins | -0.002 |
ury | -0.002 |
wo | -0.002 |
ives | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
ric | +0.001 |
itating | +0.001 |
increasingly | +0.001 |
Neg logit contributions | |
Thank | -0.001 |
ury | -0.001 |
wo | -0.001 |
vitamins | -0.001 |
ives | -0.001 |
Token | empty |
Token ID | 6565 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
flower | +0.088 |
ble | +0.080 |
itating | +0.073 |
ric | +0.069 |
increasingly | +0.068 |
Neg logit contributions | |
Thank | -0.106 |
vitamins | -0.092 |
ury | -0.092 |
ives | -0.091 |
leaf | -0.090 |
Token | thank |
Token ID | 5875 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.012 |
itating | +0.011 |
increasingly | +0.011 |
ric | +0.011 |
Neg logit contributions | |
Thank | -0.005 |
ives | -0.005 |
ury | -0.005 |
vitamins | -0.005 |
leaf | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Thank | +0.022 |
vitamins | +0.018 |
ives | +0.018 |
ury | +0.017 |
wo | +0.017 |
Neg logit contributions | |
flower | -0.041 |
ble | -0.039 |
itating | -0.036 |
ric | -0.034 |
els | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.006 |
ric | +0.005 |
itating | +0.005 |
increasingly | +0.005 |
Neg logit contributions | |
Thank | -0.006 |
ury | -0.005 |
wo | -0.005 |
ives | -0.005 |
vitamins | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
flower | +0.022 |
ble | +0.019 |
ric | +0.017 |
itating | +0.016 |
els | +0.015 |
Neg logit contributions | |
Thank | -0.045 |
ives | -0.042 |
ury | -0.041 |
vitamins | -0.041 |
leaf | -0.039 |
Token | aer |
Token ID | 9551 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
flower | +0.069 |
ble | +0.062 |
ric | +0.054 |
itating | +0.054 |
increasingly | +0.051 |
Neg logit contributions | |
Thank | -0.078 |
ives | -0.070 |
ury | -0.070 |
vitamins | -0.068 |
leaf | -0.066 |
Token | opl |
Token ID | 20106 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
flower | +0.012 |
ble | +0.010 |
ric | +0.010 |
itating | +0.009 |
mill | +0.008 |
Neg logit contributions | |
Thank | -0.022 |
vitamins | -0.020 |
ury | -0.019 |
sed | -0.019 |
Happy | -0.019 |
Token | ane |
Token ID | 1531 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
flower | +0.114 |
ble | +0.097 |
increasingly | +0.088 |
ric | +0.087 |
itating | +0.087 |
Neg logit contributions | |
Thank | -0.163 |
ury | -0.144 |
ives | -0.142 |
wo | -0.140 |
leaf | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
flower | +0.111 |
ble | +0.108 |
increasingly | +0.099 |
itating | +0.099 |
ric | +0.099 |
Neg logit contributions | |
Thank | -0.075 |
wo | -0.063 |
thank | -0.062 |
goodbye | -0.060 |
ury | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
Thank | +0.003 |
vitamins | +0.003 |
leaf | +0.003 |
wo | +0.003 |
ury | +0.003 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.002 |
itating | -0.002 |
ric | -0.002 |
packs | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Thank | +0.006 |
ury | +0.005 |
vitamins | +0.005 |
ives | +0.005 |
wo | +0.005 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
itating | -0.005 |
ric | -0.004 |
increasingly | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
flower | +0.012 |
ble | +0.010 |
ric | +0.009 |
packs | +0.009 |
burn | +0.008 |
Neg logit contributions | |
Thank | -0.017 |
ury | -0.016 |
ives | -0.015 |
leaf | -0.015 |
vitamins | -0.015 |
Token | white |
Token ID | 2330 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Thank | +0.021 |
ury | +0.018 |
wo | +0.017 |
ives | +0.017 |
vitamins | +0.017 |
Neg logit contributions | |
flower | -0.024 |
ble | -0.021 |
itating | -0.019 |
ric | -0.019 |
increasingly | -0.019 |
Token | material |
Token ID | 2587 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Thank | +0.077 |
ury | +0.065 |
Bye | +0.063 |
wo | +0.062 |
vitamins | +0.062 |
Neg logit contributions | |
flower | -0.082 |
ble | -0.070 |
packs | -0.065 |
els | -0.064 |
ric | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Thank | +0.078 |
hugs | +0.069 |
ives | +0.069 |
vitamins | +0.069 |
wo | +0.067 |
Neg logit contributions | |
flower | -0.112 |
ble | -0.100 |
itating | -0.099 |
ric | -0.096 |
increasingly | -0.093 |
Token | started |
Token ID | 2067 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.014 |
increasingly | +0.012 |
packs | +0.012 |
els | +0.012 |
Neg logit contributions | |
Thank | -0.015 |
ives | -0.013 |
ury | -0.013 |
Bye | -0.013 |
wo | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
flower | +0.038 |
ble | +0.036 |
itating | +0.034 |
ric | +0.032 |
increasingly | +0.031 |
Neg logit contributions | |
Thank | -0.019 |
hugs | -0.016 |
vitamins | -0.016 |
wo | -0.016 |
ury | -0.015 |
Token | create |
Token ID | 2251 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Thank | +0.020 |
vitamins | +0.017 |
hugs | +0.016 |
ury | +0.016 |
thank | +0.016 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.025 |
itating | -0.024 |
ric | -0.023 |
packs | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
flower | +0.150 |
ble | +0.129 |
itating | +0.124 |
ric | +0.121 |
increasingly | +0.114 |
Neg logit contributions | |
Thank | -0.124 |
vitamins | -0.108 |
hugs | -0.106 |
ury | -0.105 |
wo | -0.104 |
Token | After |
Token ID | 2293 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
flower | +0.003 |
ble | +0.003 |
itating | +0.003 |
ric | +0.003 |
increasingly | +0.003 |
Neg logit contributions | |
Thank | -0.003 |
ury | -0.002 |
vitamins | -0.002 |
ives | -0.002 |
wo | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
Thank | +0.012 |
ury | +0.010 |
vitamins | +0.010 |
ives | +0.010 |
wo | +0.010 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.012 |
itating | -0.011 |
ric | -0.011 |
increasingly | -0.011 |
Token | few |
Token ID | 1178 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Thank | +0.051 |
ives | +0.044 |
vitamins | +0.044 |
leaf | +0.043 |
ury | +0.042 |
Neg logit contributions | |
flower | -0.051 |
ble | -0.045 |
itating | -0.041 |
ric | -0.040 |
increasingly | -0.040 |
Token | minutes |
Token ID | 2431 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.012 |
increasingly | +0.012 |
els | +0.012 |
itating | +0.011 |
Neg logit contributions | |
Thank | -0.006 |
ury | -0.004 |
Bye | -0.004 |
ives | -0.004 |
leaf | -0.004 |
Token | 't |
Token ID | 470 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Thank | +0.040 |
ives | +0.035 |
hugs | +0.032 |
wo | +0.031 |
thank | +0.031 |
Neg logit contributions | |
flower | -0.106 |
bi | -0.089 |
packs | -0.089 |
ric | -0.088 |
increasingly | -0.087 |
Token | want |
Token ID | 765 |
Feature activation | +1.41e-03 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.023 |
itating | +0.021 |
ric | +0.021 |
increasingly | +0.021 |
Neg logit contributions | |
Thank | -0.013 |
ury | -0.010 |
vitamins | -0.010 |
ives | -0.010 |
wo | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
flower | +0.000 |
ble | +0.000 |
itating | +0.000 |
ric | +0.000 |
increasingly | +0.000 |
Neg logit contributions | |
Thank | -0.000 |
vitamins | -0.000 |
ury | -0.000 |
wo | -0.000 |
ives | -0.000 |
Token | make |
Token ID | 787 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Thank | +0.009 |
thank | +0.008 |
hugs | +0.008 |
Bye | +0.007 |
wo | +0.007 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.014 |
itating | -0.013 |
increasingly | -0.013 |
packs | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
flower | +0.123 |
ble | +0.103 |
itating | +0.102 |
ric | +0.100 |
increasingly | +0.096 |
Neg logit contributions | |
Thank | -0.075 |
hugs | -0.074 |
Happy | -0.068 |
vitamins | -0.067 |
dear | -0.065 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
flower | +0.078 |
ble | +0.077 |
itating | +0.072 |
ric | +0.072 |
ithering | +0.071 |
Neg logit contributions | |
hugs | -0.045 |
goodbye | -0.044 |
Thank | -0.044 |
thank | -0.043 |
dear | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
flower | +0.196 |
ble | +0.184 |
itating | +0.183 |
ric | +0.182 |
increasingly | +0.169 |
Neg logit contributions | |
Thank | -0.125 |
thank | -0.106 |
hugs | -0.105 |
wo | -0.102 |
goodbye | -0.099 |
Token | They |
Token ID | 1119 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Thank | +0.001 |
ury | +0.001 |
vitamins | +0.001 |
Happy | +0.001 |
Bye | +0.001 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
itating | -0.001 |
ric | -0.001 |
els | -0.001 |
Token | wish |
Token ID | 4601 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
Thank | +0.024 |
ury | +0.021 |
vitamins | +0.021 |
ives | +0.020 |
leaf | +0.020 |
Neg logit contributions | |
flower | -0.026 |
ble | -0.023 |
ric | -0.022 |
itating | -0.021 |
increasingly | -0.021 |
Token | they |
Token ID | 484 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Thank | +0.032 |
ury | +0.028 |
vitamins | +0.027 |
ives | +0.027 |
leaf | +0.027 |
Neg logit contributions | |
flower | -0.032 |
ble | -0.028 |
itating | -0.026 |
ric | -0.026 |
increasingly | -0.025 |
Token | could |
Token ID | 714 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.013 |
itating | +0.012 |
ric | +0.012 |
increasingly | +0.012 |
Neg logit contributions | |
Thank | -0.008 |
ury | -0.006 |
vitamins | -0.006 |
ives | -0.006 |
wo | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
Thank | +0.003 |
vitamins | +0.003 |
hugs | +0.003 |
wo | +0.003 |
ury | +0.003 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
itating | -0.003 |
ric | -0.003 |
increasingly | -0.002 |
Token | house |
Token ID | 2156 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
flower | +0.022 |
ble | +0.020 |
itating | +0.019 |
ric | +0.018 |
increasingly | +0.018 |
Neg logit contributions | |
Thank | -0.023 |
ury | -0.019 |
vitamins | -0.019 |
wo | -0.019 |
hugs | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
itating | +0.001 |
ric | +0.001 |
increasingly | +0.001 |
Neg logit contributions | |
Thank | -0.001 |
ury | -0.001 |
ives | -0.001 |
vitamins | -0.001 |
wo | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
itating | +0.002 |
ric | +0.002 |
increasingly | +0.002 |
Neg logit contributions | |
Thank | -0.002 |
vitamins | -0.001 |
leaf | -0.001 |
ury | -0.001 |
ives | -0.001 |
Token | light |
Token ID | 1657 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
Thank | +0.012 |
ury | +0.010 |
ives | +0.010 |
vitamins | +0.010 |
wo | +0.010 |
Neg logit contributions | |
flower | -0.012 |
ble | -0.010 |
itating | -0.009 |
ric | -0.009 |
increasingly | -0.009 |
Token | bul |
Token ID | 15065 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
flower | +0.023 |
ric | +0.022 |
ble | +0.022 |
itating | +0.022 |
increasingly | +0.021 |
Neg logit contributions | |
Thank | -0.016 |
hugs | -0.013 |
ury | -0.013 |
wo | -0.013 |
ives | -0.012 |
Token | b |
Token ID | 65 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
flower | +0.126 |
ble | +0.107 |
ric | +0.096 |
itating | +0.096 |
increasingly | +0.094 |
Neg logit contributions | |
Thank | -0.194 |
ury | -0.172 |
leaf | -0.170 |
ives | -0.169 |
hugs | -0.168 |
Token | stopped |
Token ID | 5025 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
flower | +0.059 |
increasingly | +0.052 |
itating | +0.051 |
ble | +0.050 |
ric | +0.049 |
Neg logit contributions | |
Thank | -0.037 |
ives | -0.033 |
ury | -0.032 |
hugs | -0.031 |
wo | -0.030 |
Token | working |
Token ID | 1762 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Thank | +0.016 |
wo | +0.014 |
hugs | +0.013 |
ury | +0.013 |
Happy | +0.013 |
Neg logit contributions | |
flower | -0.025 |
itating | -0.022 |
ble | -0.022 |
increasingly | -0.022 |
ric | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
flower | +0.024 |
ble | +0.021 |
itating | +0.019 |
ric | +0.019 |
increasingly | +0.019 |
Neg logit contributions | |
Thank | -0.024 |
ury | -0.021 |
vitamins | -0.020 |
ives | -0.020 |
wo | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Thank | +0.004 |
leaf | +0.004 |
vitamins | +0.004 |
ury | +0.004 |
wo | +0.004 |
Neg logit contributions | |
flower | -0.004 |
ble | -0.004 |
itating | -0.004 |
increasingly | -0.004 |
ric | -0.004 |
Token | let |
Token ID | 1309 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Thank | +0.016 |
vitamins | +0.015 |
ives | +0.014 |
leaf | +0.014 |
ury | +0.014 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.019 |
itating | -0.017 |
ric | -0.017 |
burn | -0.017 |
Token | 's |
Token ID | 338 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.015 |
itating | +0.014 |
ric | +0.013 |
burn | +0.013 |
Neg logit contributions | |
Thank | -0.019 |
vitamins | -0.016 |
leaf | -0.016 |
ury | -0.016 |
wo | -0.016 |
Token | go |
Token ID | 467 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.022 |
itating | +0.022 |
increasingly | +0.021 |
ric | +0.021 |
Neg logit contributions | |
Thank | -0.021 |
thank | -0.019 |
hugs | -0.018 |
wo | -0.017 |
Bye | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
flower | +0.089 |
ble | +0.080 |
itating | +0.073 |
ric | +0.072 |
increasingly | +0.070 |
Neg logit contributions | |
Thank | -0.084 |
ury | -0.072 |
vitamins | -0.072 |
wo | -0.070 |
ives | -0.070 |
Token | try |
Token ID | 1949 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.013 |
itating | +0.012 |
ric | +0.012 |
increasingly | +0.012 |
Neg logit contributions | |
Thank | -0.013 |
vitamins | -0.012 |
ury | -0.012 |
ives | -0.012 |
wo | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
flower | +0.082 |
ble | +0.074 |
itating | +0.068 |
ric | +0.068 |
increasingly | +0.065 |
Neg logit contributions | |
Thank | -0.072 |
ury | -0.061 |
ives | -0.060 |
vitamins | -0.060 |
wo | -0.059 |
Token | fix |
Token ID | 4259 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
flower | +0.035 |
ble | +0.030 |
itating | +0.030 |
ric | +0.029 |
increasingly | +0.029 |
Neg logit contributions | |
Thank | -0.026 |
hugs | -0.022 |
thank | -0.022 |
ury | -0.021 |
wo | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
flower | +0.088 |
ble | +0.079 |
itating | +0.073 |
ric | +0.072 |
increasingly | +0.070 |
Neg logit contributions | |
Thank | -0.075 |
ury | -0.063 |
vitamins | -0.063 |
wo | -0.062 |
ives | -0.061 |
Token | doll |
Token ID | 3654 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
flower | +0.047 |
ble | +0.041 |
itating | +0.037 |
ric | +0.037 |
increasingly | +0.036 |
Neg logit contributions | |
Thank | -0.053 |
ury | -0.046 |
vitamins | -0.045 |
ives | -0.045 |
wo | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
flower | +0.091 |
ble | +0.087 |
increasingly | +0.084 |
ric | +0.082 |
itating | +0.082 |
Neg logit contributions | |
Thank | -0.058 |
ives | -0.049 |
ury | -0.049 |
hugs | -0.045 |
wo | -0.045 |
Token | Maybe |
Token ID | 6674 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
ric | +0.008 |
itating | +0.008 |
packs | +0.007 |
Neg logit contributions | |
vitamins | -0.005 |
Thank | -0.005 |
leaf | -0.005 |
ives | -0.005 |
ury | -0.005 |
Token | need |
Token ID | 761 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
Thank | +0.020 |
ury | +0.017 |
vitamins | +0.016 |
wo | +0.016 |
ives | +0.016 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
itating | -0.023 |
ric | -0.023 |
increasingly | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
packs | +0.002 |
increasingly | +0.002 |
Neg logit contributions | |
Thank | -0.003 |
ury | -0.002 |
ives | -0.002 |
wo | -0.002 |
icol | -0.002 |
Token | play |
Token ID | 711 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Thank | +0.027 |
ury | +0.023 |
vitamins | +0.022 |
wo | +0.022 |
hugs | +0.022 |
Neg logit contributions | |
flower | -0.034 |
ble | -0.030 |
itating | -0.028 |
ric | -0.027 |
increasingly | -0.027 |
Token | ." |
Token ID | 526 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.011 |
itating | +0.010 |
ric | +0.010 |
increasingly | +0.010 |
Neg logit contributions | |
Thank | -0.015 |
ury | -0.013 |
vitamins | -0.013 |
ives | -0.013 |
wo | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Thank | +0.032 |
ury | +0.025 |
wo | +0.025 |
vitamins | +0.025 |
ives | +0.025 |
Neg logit contributions | |
flower | -0.044 |
ble | -0.039 |
ric | -0.037 |
itating | -0.037 |
burn | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
flower | +0.026 |
ble | +0.022 |
itating | +0.021 |
ric | +0.021 |
increasingly | +0.020 |
Neg logit contributions | |
Thank | -0.020 |
ury | -0.017 |
ives | -0.017 |
vitamins | -0.017 |
wo | -0.017 |
Token | S |
Token ID | 50 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
flower | +0.026 |
ric | +0.021 |
itating | +0.020 |
burn | +0.019 |
ble | +0.019 |
Neg logit contributions | |
Thank | -0.028 |
ury | -0.025 |
vitamins | -0.024 |
ives | -0.023 |
Now | -0.023 |
Token | ara |
Token ID | 3301 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
flower | +0.004 |
ble | +0.004 |
itating | +0.003 |
ric | +0.003 |
increasingly | +0.003 |
Neg logit contributions | |
Thank | -0.003 |
ives | -0.003 |
ury | -0.003 |
vitamins | -0.003 |
hugs | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Thank | +0.046 |
ury | +0.038 |
vitamins | +0.038 |
ives | +0.037 |
wo | +0.037 |
Neg logit contributions | |
flower | -0.057 |
ble | -0.051 |
itating | -0.047 |
ric | -0.047 |
increasingly | -0.046 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Thank | +0.023 |
ury | +0.018 |
vitamins | +0.017 |
ives | +0.017 |
leaf | +0.017 |
Neg logit contributions | |
flower | -0.049 |
ble | -0.045 |
ric | -0.042 |
itating | -0.042 |
increasingly | -0.041 |
Token | jog |
Token ID | 48342 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
flower | +0.029 |
ble | +0.026 |
itating | +0.024 |
ric | +0.023 |
increasingly | +0.023 |
Neg logit contributions | |
Thank | -0.028 |
vitamins | -0.024 |
ury | -0.024 |
wo | -0.023 |
ives | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
flower | +0.048 |
ric | +0.042 |
itating | +0.042 |
ble | +0.041 |
packs | +0.039 |
Neg logit contributions | |
Thank | -0.041 |
hugs | -0.036 |
ives | -0.035 |
ury | -0.035 |
vitamins | -0.034 |
Token | mix |
Token ID | 5022 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
flower | +0.049 |
ble | +0.044 |
itating | +0.041 |
ric | +0.040 |
increasingly | +0.039 |
Neg logit contributions | |
Thank | -0.040 |
ury | -0.034 |
vitamins | -0.034 |
wo | -0.033 |
ives | -0.033 |
Token | into |
Token ID | 656 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
flower | +0.108 |
ric | +0.103 |
itating | +0.097 |
ble | +0.093 |
burn | +0.093 |
Neg logit contributions | |
Thank | -0.068 |
ly | -0.065 |
ives | -0.064 |
hugs | -0.063 |
ets | -0.062 |
Token | little |
Token ID | 1310 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
flower | +0.099 |
ble | +0.087 |
itating | +0.082 |
ric | +0.081 |
increasingly | +0.076 |
Neg logit contributions | |
Thank | -0.091 |
vitamins | -0.078 |
ury | -0.077 |
hugs | -0.076 |
wo | -0.076 |
Token | pieces |
Token ID | 5207 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
flower | +0.004 |
ble | +0.003 |
itating | +0.003 |
ric | +0.003 |
increasingly | +0.003 |
Neg logit contributions | |
Thank | -0.003 |
ury | -0.003 |
vitamins | -0.003 |
ives | -0.003 |
hugs | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
flower | +0.021 |
ric | +0.018 |
ble | +0.018 |
itating | +0.018 |
increasingly | +0.017 |
Neg logit contributions | |
Thank | -0.014 |
ives | -0.013 |
vitamins | -0.012 |
ury | -0.012 |
hugs | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
itating | +0.008 |
ric | +0.008 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.008 |
ury | -0.007 |
vitamins | -0.007 |
ives | -0.007 |
wo | -0.007 |
Token | served |
Token ID | 4983 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
flower | +0.030 |
ble | +0.027 |
itating | +0.025 |
ric | +0.025 |
increasingly | +0.025 |
Neg logit contributions | |
Thank | -0.023 |
ury | -0.020 |
vitamins | -0.019 |
ives | -0.019 |
wo | -0.019 |
Token | them |
Token ID | 606 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
itating | +0.007 |
ric | +0.007 |
increasingly | +0.007 |
Neg logit contributions | |
Thank | -0.010 |
ury | -0.009 |
vitamins | -0.009 |
wo | -0.009 |
ives | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
hugs | +0.002 |
Thank | +0.002 |
ives | +0.002 |
goodbye | +0.002 |
vitamins | +0.001 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
itating | -0.003 |
ric | -0.003 |
ithering | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
flower | +0.003 |
ble | +0.002 |
ric | +0.002 |
itating | +0.002 |
increasingly | +0.002 |
Neg logit contributions | |
Thank | -0.003 |
ury | -0.003 |
ives | -0.003 |
vitamins | -0.003 |
wo | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
increasingly | +0.018 |
ric | +0.017 |
itating | +0.017 |
Neg logit contributions | |
Thank | -0.016 |
ury | -0.013 |
wo | -0.013 |
hugs | -0.013 |
ives | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
flower | +0.009 |
itating | +0.007 |
ble | +0.007 |
increasingly | +0.007 |
ric | +0.007 |
Neg logit contributions | |
vitamins | -0.010 |
Thank | -0.010 |
leaf | -0.009 |
ives | -0.009 |
ets | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
Thank | +0.012 |
vitamins | +0.011 |
wo | +0.010 |
ury | +0.010 |
sed | +0.010 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.009 |
itating | -0.008 |
ric | -0.007 |
increasingly | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
itating | +0.002 |
ric | +0.002 |
increasingly | +0.002 |
Neg logit contributions | |
Thank | -0.004 |
vitamins | -0.003 |
wo | -0.003 |
ury | -0.003 |
ives | -0.003 |
Token | Sarah |
Token ID | 29284 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
flower | +0.016 |
ble | +0.014 |
itating | +0.013 |
ric | +0.012 |
increasingly | +0.012 |
Neg logit contributions | |
Thank | -0.020 |
ury | -0.017 |
vitamins | -0.017 |
wo | -0.017 |
ives | -0.017 |
Token | ! |
Token ID | 0 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.022 |
itating | +0.020 |
ric | +0.020 |
increasingly | +0.020 |
Neg logit contributions | |
Thank | -0.020 |
ury | -0.017 |
vitamins | -0.017 |
ives | -0.017 |
wo | -0.017 |
Token | Put |
Token ID | 5930 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.016 |
itating | +0.015 |
ric | +0.015 |
increasingly | +0.014 |
Neg logit contributions | |
Thank | -0.009 |
vitamins | -0.007 |
ury | -0.007 |
ives | -0.007 |
wo | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
Thank | +0.016 |
ury | +0.013 |
vitamins | +0.013 |
ives | +0.013 |
wo | +0.013 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.013 |
ric | -0.012 |
itating | -0.012 |
increasingly | -0.011 |
Token | candy |
Token ID | 18550 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
flower | +0.058 |
ble | +0.053 |
increasingly | +0.048 |
itating | +0.048 |
ric | +0.047 |
Neg logit contributions | |
Thank | -0.031 |
ury | -0.026 |
leaf | -0.024 |
wo | -0.024 |
ives | -0.024 |
Token | back |
Token ID | 736 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
Thank | +0.045 |
ives | +0.041 |
ury | +0.040 |
wo | +0.039 |
hugs | +0.039 |
Neg logit contributions | |
flower | -0.037 |
ric | -0.034 |
ble | -0.031 |
itating | -0.030 |
increasingly | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
flower | +0.044 |
ble | +0.039 |
ric | +0.037 |
itating | +0.037 |
increasingly | +0.036 |
Neg logit contributions | |
Thank | -0.043 |
hugs | -0.036 |
ury | -0.036 |
wo | -0.036 |
ives | -0.036 |
Token | then |
Token ID | 788 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.018 |
itating | +0.017 |
ric | +0.017 |
increasingly | +0.016 |
Neg logit contributions | |
Thank | -0.018 |
ury | -0.015 |
vitamins | -0.015 |
ives | -0.015 |
wo | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.018 |
ric | +0.017 |
itating | +0.017 |
increasingly | +0.016 |
Neg logit contributions | |
Thank | -0.014 |
ury | -0.012 |
wo | -0.012 |
hugs | -0.011 |
Happy | -0.011 |
Token | strong |
Token ID | 1913 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Thank | +0.008 |
vitamins | +0.007 |
ives | +0.007 |
ury | +0.007 |
wo | +0.006 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
itating | -0.006 |
increasingly | -0.006 |
ric | -0.006 |
Token | wind |
Token ID | 2344 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Thank | +0.012 |
vitamins | +0.010 |
ives | +0.010 |
ury | +0.010 |
leaf | +0.010 |
Neg logit contributions | |
flower | -0.016 |
ble | -0.015 |
itating | -0.013 |
ric | -0.013 |
increasingly | -0.013 |
Token | blew |
Token ID | 17948 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Thank | +0.014 |
wo | +0.011 |
ury | +0.011 |
hugs | +0.011 |
ives | +0.010 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.020 |
itating | -0.020 |
ric | -0.020 |
increasingly | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.015 |
ric | +0.014 |
itating | +0.014 |
packs | +0.013 |
Neg logit contributions | |
Thank | -0.019 |
wo | -0.016 |
hugs | -0.016 |
ury | -0.016 |
vitamins | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.013 |
increasingly | +0.012 |
itating | +0.012 |
ric | +0.012 |
Neg logit contributions | |
Thank | -0.013 |
vitamins | -0.013 |
ives | -0.012 |
ury | -0.012 |
ets | -0.012 |
Token | k |
Token ID | 479 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
Thank | +0.007 |
ury | +0.006 |
vitamins | +0.006 |
wo | +0.006 |
ives | +0.006 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.008 |
itating | -0.008 |
ric | -0.008 |
increasingly | -0.007 |
Token | ite |
Token ID | 578 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
Thank | +0.028 |
ury | +0.025 |
ives | +0.024 |
leaf | +0.024 |
hugs | +0.023 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.014 |
increasingly | -0.012 |
ric | -0.012 |
itating | -0.012 |
Token | almost |
Token ID | 2048 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
flower | +0.046 |
ble | +0.041 |
itating | +0.038 |
ric | +0.037 |
increasingly | +0.036 |
Neg logit contributions | |
Thank | -0.044 |
ury | -0.038 |
vitamins | -0.038 |
ives | -0.037 |
wo | -0.037 |
Token | flew |
Token ID | 13112 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.015 |
itating | +0.012 |
burn | +0.011 |
increasingly | +0.011 |
Neg logit contributions | |
Thank | -0.019 |
vitamins | -0.017 |
leaf | -0.017 |
kids | -0.016 |
ives | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
flower | +0.019 |
ble | +0.016 |
itating | +0.015 |
ric | +0.014 |
increasingly | +0.014 |
Neg logit contributions | |
Thank | -0.023 |
leaf | -0.021 |
ury | -0.021 |
vitamins | -0.021 |
ives | -0.020 |
Token | |
Token ID | 220 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
flower | +0.006 |
itating | +0.004 |
packs | +0.004 |
bi | +0.004 |
increasingly | +0.004 |
Neg logit contributions | |
vitamins | -0.007 |
leaf | -0.007 |
Thank | -0.007 |
ury | -0.007 |
sed | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
Thank | +0.024 |
ury | +0.020 |
ives | +0.020 |
wo | +0.019 |
vitamins | +0.019 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.026 |
ric | -0.024 |
itating | -0.024 |
increasingly | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Thank | +0.002 |
vitamins | +0.002 |
ury | +0.002 |
wo | +0.002 |
sed | +0.002 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
itating | -0.002 |
ric | -0.001 |
increasingly | -0.001 |
Token | She |
Token ID | 3347 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.011 |
ric | +0.011 |
burn | +0.010 |
packs | +0.010 |
Neg logit contributions | |
Thank | -0.016 |
ury | -0.014 |
ives | -0.014 |
leaf | -0.013 |
wo | -0.013 |
Token | ran |
Token ID | 4966 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
flower | +0.053 |
ble | +0.047 |
increasingly | +0.043 |
itating | +0.042 |
ric | +0.042 |
Neg logit contributions | |
Thank | -0.044 |
vitamins | -0.037 |
ury | -0.037 |
ives | -0.037 |
leaf | -0.035 |
Token | all |
Token ID | 477 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Thank | +0.057 |
vitamins | +0.050 |
ury | +0.049 |
wo | +0.048 |
ives | +0.048 |
Neg logit contributions | |
flower | -0.045 |
ble | -0.040 |
itating | -0.036 |
increasingly | -0.035 |
ric | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Thank | +0.109 |
hugs | +0.095 |
leaf | +0.092 |
Happy | +0.091 |
ives | +0.089 |
Neg logit contributions | |
flower | -0.121 |
ble | -0.112 |
ric | -0.101 |
itating | -0.101 |
increasingly | -0.096 |
Token | way |
Token ID | 835 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Thank | +0.089 |
ury | +0.076 |
ives | +0.075 |
vitamins | +0.075 |
wo | +0.074 |
Neg logit contributions | |
flower | -0.083 |
ble | -0.073 |
itating | -0.068 |
ric | -0.065 |
increasingly | -0.064 |
Token | home |
Token ID | 1363 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Thank | +0.032 |
ury | +0.027 |
hugs | +0.027 |
wo | +0.027 |
ives | +0.026 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.028 |
ric | -0.026 |
itating | -0.025 |
increasingly | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
Thank | +0.106 |
vitamins | +0.092 |
ury | +0.090 |
leaf | +0.090 |
wo | +0.089 |
Neg logit contributions | |
flower | -0.101 |
ble | -0.091 |
itating | -0.082 |
ric | -0.080 |
increasingly | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Thank | +0.017 |
ury | +0.015 |
vitamins | +0.015 |
wo | +0.015 |
ives | +0.014 |
Neg logit contributions | |
flower | -0.031 |
increasingly | -0.025 |
ble | -0.025 |
ric | -0.024 |
burn | -0.024 |
Token | One |
Token ID | 1881 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.012 |
itating | +0.011 |
ric | +0.011 |
increasingly | +0.011 |
Neg logit contributions | |
Thank | -0.012 |
ury | -0.010 |
vitamins | -0.010 |
ives | -0.010 |
wo | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
flower | +0.033 |
ble | +0.032 |
ric | +0.031 |
itating | +0.031 |
els | +0.029 |
Neg logit contributions | |
Thank | -0.020 |
ury | -0.017 |
wo | -0.017 |
vitamins | -0.016 |
hours | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Thank | +0.033 |
leaf | +0.031 |
vitamins | +0.030 |
ives | +0.030 |
sed | +0.029 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.026 |
increasingly | -0.023 |
itating | -0.022 |
burn | -0.021 |
Token | he |
Token ID | 339 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
Thank | +0.021 |
ives | +0.019 |
vitamins | +0.018 |
ury | +0.018 |
leaf | +0.018 |
Neg logit contributions | |
flower | -0.025 |
ble | -0.023 |
itating | -0.020 |
increasingly | -0.020 |
ric | -0.020 |
Token | discovered |
Token ID | 5071 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
Thank | +0.001 |
ury | +0.001 |
vitamins | +0.001 |
wo | +0.001 |
ives | +0.001 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
ric | -0.002 |
itating | -0.002 |
increasingly | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
Thank | +0.025 |
vitamins | +0.021 |
ury | +0.021 |
hugs | +0.021 |
wo | +0.020 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.027 |
itating | -0.026 |
ric | -0.026 |
packs | -0.025 |
Token | hive |
Token ID | 35881 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
itating | +0.001 |
ric | +0.001 |
packs | +0.001 |
Neg logit contributions | |
Thank | -0.001 |
ury | -0.001 |
wo | -0.001 |
vitamins | -0.001 |
hugs | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
ric | +0.005 |
itating | +0.005 |
increasingly | +0.005 |
Neg logit contributions | |
Thank | -0.007 |
ives | -0.006 |
ury | -0.006 |
wo | -0.006 |
vitamins | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.004 |
itating | +0.004 |
ric | +0.004 |
increasingly | +0.004 |
Neg logit contributions | |
Thank | -0.004 |
vitamins | -0.004 |
hugs | -0.004 |
Happy | -0.003 |
hours | -0.003 |
Token | garden |
Token ID | 11376 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.010 |
itating | +0.009 |
ric | +0.009 |
increasingly | +0.009 |
Neg logit contributions | |
Thank | -0.013 |
ury | -0.011 |
ives | -0.011 |
leaf | -0.011 |
wo | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Thank | +0.107 |
vitamins | +0.092 |
leaf | +0.092 |
ury | +0.092 |
wo | +0.091 |
Neg logit contributions | |
flower | -0.110 |
ble | -0.094 |
packs | -0.085 |
ric | -0.084 |
itating | -0.081 |
Token | Ben |
Token ID | 3932 |
Feature activation | -7.83e-03 |
Pos logit contributions | |
Thank | +0.011 |
ury | +0.009 |
wo | +0.009 |
vitamins | +0.009 |
ives | +0.009 |
Neg logit contributions | |
flower | -0.013 |
ble | -0.011 |
itating | -0.011 |
ric | -0.010 |
increasingly | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
Thank | +0.000 |
ury | +0.000 |
vitamins | +0.000 |
ives | +0.000 |
wo | +0.000 |
Neg logit contributions | |
flower | -0.001 |
ble | -0.000 |
ric | -0.000 |
itating | -0.000 |
increasingly | -0.000 |
Token | best |
Token ID | 1266 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
flower | +0.049 |
ble | +0.044 |
itating | +0.041 |
ric | +0.040 |
increasingly | +0.039 |
Neg logit contributions | |
Thank | -0.037 |
wo | -0.031 |
hugs | -0.031 |
vitamins | -0.030 |
Happy | -0.030 |
Token | friends |
Token ID | 2460 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
flower | +0.004 |
ble | +0.004 |
packs | +0.003 |
els | +0.003 |
ric | +0.003 |
Neg logit contributions | |
Thank | -0.007 |
ury | -0.006 |
vitamins | -0.006 |
ives | -0.006 |
leaf | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Thank | +0.019 |
ury | +0.016 |
wo | +0.016 |
vitamins | +0.016 |
ives | +0.016 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.018 |
itating | -0.016 |
ric | -0.016 |
increasingly | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
Thank | +0.023 |
Happy | +0.018 |
wo | +0.018 |
vitamins | +0.018 |
ury | +0.017 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.038 |
itating | -0.034 |
ric | -0.033 |
mill | -0.032 |
Token | liked |
Token ID | 8288 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
flower | +0.007 |
ble | +0.006 |
ric | +0.006 |
itating | +0.006 |
increasingly | +0.005 |
Neg logit contributions | |
Thank | -0.004 |
ury | -0.003 |
vitamins | -0.003 |
ives | -0.003 |
leaf | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
Thank | +0.037 |
vitamins | +0.030 |
ury | +0.030 |
wo | +0.030 |
ives | +0.029 |
Neg logit contributions | |
flower | -0.060 |
ble | -0.055 |
itating | -0.051 |
ric | -0.050 |
increasingly | -0.049 |
Token | play |
Token ID | 711 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
flower | +0.004 |
itating | +0.004 |
ble | +0.004 |
increasingly | +0.004 |
ric | +0.003 |
Neg logit contributions | |
Thank | -0.002 |
thank | -0.002 |
hugs | -0.002 |
wo | -0.002 |
Happy | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
flower | +0.033 |
ble | +0.029 |
itating | +0.026 |
ric | +0.026 |
increasingly | +0.025 |
Neg logit contributions | |
Thank | -0.041 |
ury | -0.036 |
vitamins | -0.035 |
ives | -0.035 |
wo | -0.035 |
Token | it |
Token ID | 340 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
Thank | +0.021 |
ury | +0.018 |
ives | +0.018 |
vitamins | +0.018 |
leaf | +0.018 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
ric | -0.013 |
itating | -0.013 |
increasingly | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Thank | +0.047 |
ury | +0.040 |
wo | +0.040 |
hugs | +0.039 |
ives | +0.038 |
Neg logit contributions | |
flower | -0.062 |
ble | -0.056 |
ric | -0.054 |
itating | -0.051 |
increasingly | -0.050 |
Token | much |
Token ID | 881 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.012 |
itating | +0.011 |
increasingly | +0.011 |
ric | +0.010 |
Neg logit contributions | |
Thank | -0.018 |
ives | -0.016 |
ury | -0.016 |
vitamins | -0.016 |
leaf | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
Thank | +0.001 |
vitamins | +0.001 |
ives | +0.001 |
ury | +0.001 |
leaf | +0.001 |
Neg logit contributions | |
flower | -0.001 |
ble | -0.001 |
itating | -0.001 |
increasingly | -0.001 |
mill | -0.001 |
Token | Mia |
Token ID | 32189 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
flower | +0.000 |
ble | +0.000 |
itating | +0.000 |
ric | +0.000 |
increasingly | +0.000 |
Neg logit contributions | |
Thank | -0.000 |
ury | -0.000 |
leaf | -0.000 |
vitamins | -0.000 |
wo | -0.000 |
Token | 's |
Token ID | 338 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
flower | +0.054 |
ble | +0.048 |
itating | +0.045 |
ric | +0.044 |
increasingly | +0.044 |
Neg logit contributions | |
Thank | -0.039 |
ury | -0.033 |
vitamins | -0.033 |
ives | -0.032 |
leaf | -0.032 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Thank | +0.033 |
ury | +0.029 |
vitamins | +0.029 |
ives | +0.029 |
wo | +0.028 |
Neg logit contributions | |
flower | -0.029 |
ble | -0.025 |
itating | -0.023 |
ric | -0.023 |
increasingly | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.017 |
itating | +0.016 |
increasingly | +0.015 |
ric | +0.015 |
Neg logit contributions | |
Thank | -0.018 |
vitamins | -0.016 |
ury | -0.015 |
ives | -0.015 |
leaf | -0.015 |
Token | she |
Token ID | 673 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
Thank | +0.042 |
ives | +0.041 |
leaf | +0.041 |
vitamins | +0.039 |
ets | +0.039 |
Neg logit contributions | |
flower | -0.039 |
ble | -0.037 |
itating | -0.031 |
increasingly | -0.031 |
mill | -0.030 |
Token | could |
Token ID | 714 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
itating | +0.001 |
ric | +0.001 |
increasingly | +0.001 |
Neg logit contributions | |
Thank | -0.001 |
vitamins | -0.001 |
leaf | -0.001 |
ives | -0.001 |
wo | -0.001 |
Token | make |
Token ID | 787 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Thank | +0.027 |
thank | +0.022 |
ury | +0.022 |
hugs | +0.022 |
wo | +0.021 |
Neg logit contributions | |
flower | -0.040 |
ble | -0.035 |
itating | -0.034 |
ric | -0.033 |
increasingly | -0.033 |
Token | make |
Token ID | 787 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.015 |
itating | +0.014 |
ric | +0.014 |
increasingly | +0.013 |
Neg logit contributions | |
Thank | -0.017 |
ury | -0.014 |
vitamins | -0.014 |
wo | -0.014 |
ives | -0.014 |
Token | bubbles |
Token ID | 25037 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
flower | +0.137 |
itating | +0.113 |
ble | +0.113 |
ric | +0.108 |
packs | +0.104 |
Neg logit contributions | |
Thank | -0.098 |
hugs | -0.088 |
vitamins | -0.087 |
wo | -0.084 |
ury | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -6.75e-04 |
Pos logit contributions | |
flower | +0.075 |
ric | +0.067 |
itating | +0.066 |
bi | +0.065 |
increasingly | +0.064 |
Neg logit contributions | |
Thank | -0.044 |
ives | -0.041 |
ets | -0.040 |
wo | -0.040 |
thank | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
Thank | +0.000 |
ury | +0.000 |
vitamins | +0.000 |
ives | +0.000 |
wo | +0.000 |
Neg logit contributions | |
flower | -0.000 |
ble | -0.000 |
ric | -0.000 |
itating | -0.000 |
burn | -0.000 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
flower | +0.004 |
ble | +0.004 |
itating | +0.004 |
ric | +0.004 |
increasingly | +0.003 |
Neg logit contributions | |
Thank | -0.003 |
ury | -0.002 |
vitamins | -0.002 |
ives | -0.002 |
wo | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Thank | +0.063 |
vitamins | +0.055 |
hugs | +0.054 |
wo | +0.053 |
ives | +0.052 |
Neg logit contributions | |
flower | -0.082 |
ble | -0.072 |
itating | -0.070 |
ric | -0.068 |
increasingly | -0.064 |
Token | big |
Token ID | 1263 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Thank | +0.028 |
wo | +0.023 |
ury | +0.023 |
vitamins | +0.023 |
hugs | +0.022 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.027 |
ric | -0.026 |
itating | -0.026 |
packs | -0.025 |
Token | bottle |
Token ID | 9294 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.010 |
ric | +0.009 |
itating | +0.009 |
increasingly | +0.009 |
Neg logit contributions | |
Thank | -0.011 |
ury | -0.010 |
ives | -0.009 |
vitamins | -0.009 |
wo | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Thank | +0.022 |
ives | +0.019 |
ury | +0.019 |
wo | +0.018 |
vitamins | +0.018 |
Neg logit contributions | |
flower | -0.025 |
ble | -0.022 |
ric | -0.022 |
itating | -0.021 |
increasingly | -0.021 |
Token | shampoo |
Token ID | 47259 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
flower | +0.092 |
ble | +0.082 |
ric | +0.073 |
increasingly | +0.072 |
els | +0.069 |
Neg logit contributions | |
Thank | -0.098 |
ury | -0.091 |
ives | -0.086 |
Bye | -0.084 |
wo | -0.083 |
Token | on |
Token ID | 319 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
Thank | +0.006 |
ury | +0.006 |
wo | +0.006 |
ives | +0.005 |
vitamins | +0.005 |
Neg logit contributions | |
flower | -0.006 |
itating | -0.006 |
ble | -0.006 |
ric | -0.005 |
increasingly | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.007 |
itating | +0.007 |
increasingly | +0.007 |
ric | +0.006 |
Neg logit contributions | |
Thank | -0.007 |
leaf | -0.006 |
vitamins | -0.006 |
ives | -0.006 |
ury | -0.006 |
Token | stayed |
Token ID | 9658 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.011 |
increasingly | +0.011 |
ric | +0.010 |
itating | +0.010 |
Neg logit contributions | |
Thank | -0.012 |
vitamins | -0.011 |
ives | -0.011 |
leaf | -0.010 |
ury | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Thank | +0.011 |
hugs | +0.010 |
goodbye | +0.010 |
hours | +0.010 |
thank | +0.009 |
Neg logit contributions | |
flower | -0.014 |
ric | -0.012 |
ble | -0.011 |
itating | -0.011 |
els | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Thank | +0.019 |
vitamins | +0.016 |
wo | +0.016 |
ury | +0.016 |
hugs | +0.016 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
itating | -0.014 |
ric | -0.014 |
increasingly | -0.013 |
Token | cave |
Token ID | 11527 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Thank | +0.001 |
vitamins | +0.001 |
hugs | +0.001 |
ury | +0.001 |
wo | +0.001 |
Neg logit contributions | |
flower | -0.001 |
ble | -0.001 |
itating | -0.001 |
ric | -0.001 |
packs | -0.001 |
Token | forever |
Token ID | 8097 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Thank | +0.066 |
ury | +0.057 |
vitamins | +0.057 |
ives | +0.056 |
leaf | +0.056 |
Neg logit contributions | |
flower | -0.069 |
ble | -0.061 |
itating | -0.056 |
ric | -0.055 |
increasingly | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Thank | +0.138 |
vitamins | +0.120 |
leaf | +0.119 |
ury | +0.118 |
ives | +0.118 |
Neg logit contributions | |
flower | -0.126 |
ble | -0.112 |
itating | -0.101 |
ric | -0.099 |
increasingly | -0.097 |
Token | never |
Token ID | 1239 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
Thank | +0.015 |
leaf | +0.014 |
ives | +0.014 |
vitamins | +0.014 |
ury | +0.013 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.013 |
increasingly | -0.012 |
itating | -0.011 |
ric | -0.011 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Thank | +0.025 |
leaf | +0.024 |
vitamins | +0.024 |
ives | +0.023 |
ury | +0.022 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.026 |
packs | -0.024 |
increasingly | -0.024 |
itating | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Thank | +0.061 |
vitamins | +0.053 |
ury | +0.052 |
wo | +0.052 |
ives | +0.051 |
Neg logit contributions | |
flower | -0.056 |
ble | -0.050 |
itating | -0.046 |
ric | -0.045 |
increasingly | -0.043 |
Token | family |
Token ID | 1641 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Thank | +0.021 |
hugs | +0.021 |
dear | +0.020 |
wo | +0.020 |
thank | +0.018 |
Neg logit contributions | |
itating | -0.030 |
flower | -0.030 |
ble | -0.029 |
ric | -0.028 |
increasingly | -0.027 |
Token | fish |
Token ID | 5916 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
flower | +0.073 |
ble | +0.070 |
increasingly | +0.064 |
ric | +0.063 |
itating | +0.060 |
Neg logit contributions | |
Thank | -0.075 |
ury | -0.069 |
ives | -0.068 |
wo | -0.063 |
sed | -0.063 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Thank | +0.039 |
ury | +0.032 |
ives | +0.031 |
wo | +0.031 |
vitamins | +0.031 |
Neg logit contributions | |
flower | -0.062 |
ble | -0.057 |
itating | -0.054 |
ric | -0.054 |
increasingly | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Thank | +0.007 |
ives | +0.006 |
ury | +0.006 |
wo | +0.005 |
hugs | +0.005 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.008 |
ric | -0.007 |
itating | -0.007 |
burn | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
flower | +0.047 |
ble | +0.041 |
ric | +0.039 |
itating | +0.038 |
burn | +0.037 |
Neg logit contributions | |
Thank | -0.036 |
ives | -0.030 |
ury | -0.030 |
hugs | -0.030 |
wo | -0.030 |
Token | Lou |
Token ID | 24016 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
flower | +0.048 |
ble | +0.042 |
ric | +0.041 |
burn | +0.038 |
mill | +0.037 |
Neg logit contributions | |
Thank | -0.046 |
ury | -0.040 |
ives | -0.040 |
Happy | -0.038 |
hugs | -0.038 |
Token | ise |
Token ID | 786 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Thank | +0.011 |
ury | +0.009 |
vitamins | +0.009 |
ives | +0.009 |
wo | +0.009 |
Neg logit contributions | |
flower | -0.012 |
ble | -0.010 |
itating | -0.010 |
ric | -0.009 |
increasingly | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
Thank | +0.107 |
wo | +0.090 |
ury | +0.090 |
hugs | +0.089 |
ives | +0.086 |
Neg logit contributions | |
flower | -0.143 |
ble | -0.131 |
itating | -0.125 |
ric | -0.123 |
increasingly | -0.120 |
Token | so |
Token ID | 523 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Thank | +0.003 |
wo | +0.002 |
hugs | +0.002 |
thank | +0.002 |
leaf | +0.002 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
ric | -0.005 |
packs | -0.005 |
burn | -0.005 |
Token | excited |
Token ID | 6568 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
flower | +0.037 |
ric | +0.033 |
ble | +0.032 |
burn | +0.032 |
els | +0.031 |
Neg logit contributions | |
Thank | -0.017 |
thank | -0.013 |
wo | -0.012 |
hugs | -0.012 |
ury | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Thank | +0.004 |
vitamins | +0.004 |
ury | +0.004 |
ives | +0.004 |
leaf | +0.004 |
Neg logit contributions | |
flower | -0.005 |
ble | -0.004 |
itating | -0.004 |
ric | -0.004 |
increasingly | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
Thank | +0.010 |
wo | +0.009 |
ury | +0.009 |
vitamins | +0.008 |
hugs | +0.008 |
Neg logit contributions | |
flower | -0.013 |
ble | -0.012 |
ric | -0.011 |
itating | -0.011 |
increasingly | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Thank | +0.046 |
ury | +0.043 |
ives | +0.043 |
leaf | +0.042 |
ets | +0.041 |
Neg logit contributions | |
flower | -0.061 |
ble | -0.058 |
increasingly | -0.051 |
mill | -0.050 |
itating | -0.049 |
Token | car |
Token ID | 1097 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
Thank | +0.015 |
ury | +0.014 |
leaf | +0.014 |
vitamins | +0.014 |
ives | +0.014 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
packs | -0.014 |
ric | -0.013 |
itating | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
flower | +0.043 |
ble | +0.040 |
itating | +0.038 |
ric | +0.037 |
increasingly | +0.036 |
Neg logit contributions | |
Thank | -0.039 |
wo | -0.033 |
ury | -0.033 |
hugs | -0.032 |
ives | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Thank | +0.011 |
vitamins | +0.009 |
wo | +0.009 |
thank | +0.009 |
hugs | +0.009 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.012 |
itating | -0.012 |
ric | -0.012 |
burn | -0.011 |
Token | dragon |
Token ID | 10441 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
Thank | +0.023 |
ives | +0.020 |
vitamins | +0.020 |
ury | +0.020 |
leaf | +0.019 |
Neg logit contributions | |
flower | -0.024 |
ble | -0.022 |
itating | -0.020 |
ric | -0.019 |
increasingly | -0.019 |
Token | who |
Token ID | 508 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Thank | +0.039 |
ury | +0.033 |
wo | +0.033 |
ives | +0.031 |
hugs | +0.030 |
Neg logit contributions | |
flower | -0.045 |
ble | -0.043 |
itating | -0.041 |
increasingly | -0.040 |
ric | -0.040 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Thank | +0.105 |
ury | +0.087 |
vitamins | +0.086 |
ives | +0.084 |
wo | +0.083 |
Neg logit contributions | |
flower | -0.149 |
ble | -0.132 |
ric | -0.122 |
itating | -0.120 |
packs | -0.118 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Thank | +0.030 |
ury | +0.025 |
ives | +0.025 |
vitamins | +0.024 |
leaf | +0.024 |
Neg logit contributions | |
flower | -0.037 |
ble | -0.033 |
ric | -0.030 |
itating | -0.030 |
increasingly | -0.030 |
Token | take |
Token ID | 1011 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Thank | +0.007 |
ury | +0.006 |
thank | +0.006 |
wo | +0.006 |
vitamins | +0.005 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.008 |
itating | -0.007 |
ric | -0.007 |
increasingly | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.010 |
packs | +0.009 |
increasingly | +0.009 |
ric | +0.009 |
Neg logit contributions | |
Thank | -0.012 |
ury | -0.011 |
ives | -0.010 |
vitamins | -0.010 |
wo | -0.010 |
Token | princess |
Token ID | 21752 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Thank | +0.016 |
ury | +0.014 |
ives | +0.013 |
vitamins | +0.013 |
wo | +0.013 |
Neg logit contributions | |
flower | -0.018 |
ble | -0.016 |
itating | -0.014 |
ric | -0.014 |
packs | -0.014 |
Token | crooked |
Token ID | 45571 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
flower | +0.071 |
ble | +0.064 |
itating | +0.059 |
ric | +0.059 |
increasingly | +0.057 |
Neg logit contributions | |
Thank | -0.054 |
ury | -0.045 |
vitamins | -0.044 |
ives | -0.044 |
wo | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
flower | +0.138 |
ble | +0.122 |
ric | +0.111 |
itating | +0.110 |
increasingly | +0.107 |
Neg logit contributions | |
Thank | -0.144 |
ury | -0.125 |
vitamins | -0.123 |
ives | -0.122 |
leaf | -0.121 |
Token | |
Token ID | 220 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
flower | +0.029 |
ble | +0.026 |
itating | +0.024 |
ric | +0.024 |
increasingly | +0.023 |
Neg logit contributions | |
Thank | -0.020 |
ury | -0.016 |
wo | -0.016 |
vitamins | -0.015 |
Happy | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
Thank | +0.028 |
ives | +0.023 |
ury | +0.023 |
vitamins | +0.022 |
wo | +0.022 |
Neg logit contributions | |
flower | -0.042 |
ble | -0.037 |
itating | -0.034 |
increasingly | -0.034 |
burn | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Thank | +0.003 |
ury | +0.002 |
ives | +0.002 |
vitamins | +0.002 |
wo | +0.002 |
Neg logit contributions | |
flower | -0.004 |
ble | -0.003 |
ric | -0.003 |
itating | -0.003 |
burn | -0.003 |
Token | T |
Token ID | 51 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.013 |
ric | +0.012 |
burn | +0.011 |
els | +0.011 |
Neg logit contributions | |
Thank | -0.013 |
ury | -0.012 |
Bye | -0.011 |
ives | -0.011 |
leaf | -0.011 |
Token | ricia |
Token ID | 26654 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Thank | +0.149 |
vitamins | +0.128 |
ury | +0.128 |
wo | +0.126 |
ives | +0.126 |
Neg logit contributions | |
flower | -0.137 |
ble | -0.122 |
itating | -0.109 |
ric | -0.108 |
increasingly | -0.104 |
Token | immediately |
Token ID | 3393 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Thank | +0.022 |
vitamins | +0.019 |
ury | +0.018 |
ives | +0.018 |
leaf | +0.018 |
Neg logit contributions | |
flower | -0.029 |
ble | -0.025 |
itating | -0.024 |
increasingly | -0.023 |
ric | -0.023 |
Token | thought |
Token ID | 1807 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Thank | +0.069 |
vitamins | +0.058 |
ury | +0.057 |
leaf | +0.057 |
ives | +0.056 |
Neg logit contributions | |
flower | -0.104 |
ble | -0.094 |
increasingly | -0.086 |
itating | -0.086 |
ric | -0.084 |
Token | she |
Token ID | 673 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Thank | +0.016 |
vitamins | +0.013 |
ury | +0.013 |
leaf | +0.013 |
ives | +0.013 |
Neg logit contributions | |
flower | -0.016 |
ble | -0.015 |
itating | -0.014 |
increasingly | -0.013 |
ric | -0.013 |
Token | must |
Token ID | 1276 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
flower | +0.040 |
ble | +0.035 |
itating | +0.032 |
ric | +0.032 |
increasingly | +0.032 |
Neg logit contributions | |
Thank | -0.035 |
vitamins | -0.030 |
ives | -0.030 |
leaf | -0.030 |
ury | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Thank | +0.023 |
vitamins | +0.021 |
hugs | +0.020 |
Happy | +0.020 |
wo | +0.020 |
Neg logit contributions | |
flower | -0.023 |
ble | -0.019 |
itating | -0.019 |
ric | -0.018 |
packs | -0.017 |
Token | worst |
Token ID | 5290 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
itating | +0.007 |
ric | +0.007 |
packs | +0.007 |
Neg logit contributions | |
Thank | -0.010 |
vitamins | -0.009 |
wo | -0.008 |
leaf | -0.008 |
hugs | -0.008 |
Token | corn |
Token ID | 11676 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
flower | +0.024 |
itating | +0.023 |
ble | +0.022 |
ric | +0.021 |
increasingly | +0.020 |
Neg logit contributions | |
Thank | -0.019 |
vitamins | -0.017 |
wo | -0.017 |
dear | -0.016 |
thank | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
Thank | +0.079 |
ury | +0.066 |
vitamins | +0.066 |
wo | +0.065 |
ives | +0.065 |
Neg logit contributions | |
flower | -0.088 |
ble | -0.079 |
itating | -0.076 |
ric | -0.074 |
increasingly | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
Thank | +0.041 |
vitamins | +0.035 |
hugs | +0.034 |
thank | +0.033 |
Happy | +0.033 |
Neg logit contributions | |
flower | -0.048 |
ble | -0.041 |
itating | -0.041 |
ric | -0.039 |
increasingly | -0.039 |
Token | field |
Token ID | 2214 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Thank | +0.014 |
vitamins | +0.012 |
wo | +0.011 |
hugs | +0.011 |
ury | +0.011 |
Neg logit contributions | |
flower | -0.016 |
ble | -0.015 |
itating | -0.014 |
ric | -0.013 |
els | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
Thank | +0.119 |
ury | +0.098 |
ives | +0.098 |
vitamins | +0.098 |
wo | +0.097 |
Neg logit contributions | |
flower | -0.140 |
ble | -0.126 |
itating | -0.118 |
ric | -0.118 |
increasingly | -0.115 |
Token | You |
Token ID | 921 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Thank | +0.002 |
wo | +0.002 |
ury | +0.002 |
leaf | +0.002 |
vitamins | +0.002 |
Neg logit contributions | |
flower | -0.005 |
ble | -0.004 |
ric | -0.004 |
itating | -0.004 |
increasingly | -0.004 |
Token | have |
Token ID | 423 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Thank | +0.027 |
vitamins | +0.023 |
ury | +0.023 |
wo | +0.022 |
leaf | +0.022 |
Neg logit contributions | |
flower | -0.035 |
ble | -0.031 |
ric | -0.029 |
itating | -0.029 |
increasingly | -0.028 |
Token | wasted |
Token ID | 18359 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Thank | +0.018 |
ury | +0.015 |
ives | +0.015 |
wo | +0.015 |
leaf | +0.015 |
Neg logit contributions | |
flower | -0.023 |
ble | -0.021 |
ric | -0.019 |
itating | -0.019 |
increasingly | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Thank | +0.083 |
ury | +0.072 |
ives | +0.070 |
vitamins | +0.070 |
wo | +0.070 |
Neg logit contributions | |
flower | -0.086 |
ble | -0.077 |
ric | -0.070 |
itating | -0.069 |
increasingly | -0.067 |