Token | and |
Token ID | 290 |
Feature activation | -1.29e-03 |
Pos logit contributions | |
uts | +0.015 |
cartridge | +0.015 |
ate | +0.014 |
ra | +0.014 |
ung | +0.013 |
Neg logit contributions | |
camel | -0.013 |
bus | -0.013 |
joy | -0.012 |
vehicle | -0.012 |
elephants | -0.012 |
Token | both |
Token ID | 1111 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
ra | +0.002 |
cutter | +0.002 |
Neg logit contributions | |
camel | -0.002 |
bus | -0.002 |
joy | -0.002 |
year | -0.002 |
vehicle | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
uts | +0.054 |
connected | +0.051 |
ra | +0.050 |
cartridge | +0.050 |
ung | +0.050 |
Neg logit contributions | |
bus | -0.056 |
camel | -0.055 |
joy | -0.052 |
vehicle | -0.051 |
elephants | -0.050 |
Token | them |
Token ID | 606 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
bus | +0.038 |
camel | +0.037 |
vehicle | +0.034 |
mo | +0.034 |
joy | +0.033 |
Neg logit contributions | |
ate | -0.027 |
uts | -0.027 |
cartridge | -0.026 |
ra | -0.025 |
rap | -0.025 |
Token | were |
Token ID | 547 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
bus | +0.056 |
camel | +0.056 |
joy | +0.053 |
vehicle | +0.051 |
elephants | +0.051 |
Neg logit contributions | |
uts | -0.059 |
cartridge | -0.055 |
ate | -0.053 |
ra | -0.053 |
ung | -0.052 |
Token | merry |
Token ID | 44570 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
bus | +0.058 |
camel | +0.058 |
joy | +0.053 |
elephants | +0.051 |
vehicle | +0.051 |
Neg logit contributions | |
uts | -0.061 |
cartridge | -0.060 |
ate | -0.058 |
ra | -0.055 |
ung | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e-04 |
Pos logit contributions | |
camel | +0.366 |
bus | +0.357 |
elephants | +0.347 |
joy | +0.330 |
hi | +0.329 |
Neg logit contributions | |
uts | -0.238 |
ra | -0.233 |
ate | -0.232 |
ung | -0.228 |
rap | -0.213 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
uts | +0.000 |
cartridge | +0.000 |
ate | +0.000 |
ung | +0.000 |
ra | +0.000 |
Neg logit contributions | |
camel | -0.000 |
bus | -0.000 |
vehicle | -0.000 |
elephants | -0.000 |
joy | -0.000 |
Token | Once |
Token ID | 7454 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
uts | +0.017 |
cartridge | +0.017 |
ate | +0.016 |
ra | +0.015 |
ung | +0.015 |
Neg logit contributions | |
bus | -0.018 |
camel | -0.018 |
joy | -0.016 |
elephants | -0.016 |
vehicle | -0.016 |
Token | upon |
Token ID | 2402 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
uts | +0.008 |
ate | +0.008 |
cartridge | +0.007 |
rap | +0.007 |
ung | +0.007 |
Neg logit contributions | |
camel | -0.008 |
bus | -0.008 |
elephants | -0.008 |
gir | -0.008 |
joy | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
uts | +0.010 |
ate | +0.009 |
cartridge | +0.008 |
ra | +0.008 |
connected | +0.008 |
Neg logit contributions | |
bus | -0.016 |
camel | -0.016 |
joy | -0.015 |
mo | -0.015 |
vehicle | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
uts | +0.008 |
cartridge | +0.008 |
ate | +0.007 |
ra | +0.007 |
rap | +0.007 |
Neg logit contributions | |
bus | -0.008 |
camel | -0.007 |
joy | -0.007 |
elephants | -0.007 |
vehicle | -0.007 |
Token | both |
Token ID | 1111 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
bus | +0.017 |
camel | +0.017 |
joy | +0.016 |
vehicle | +0.015 |
elephants | +0.015 |
Neg logit contributions | |
uts | -0.015 |
cartridge | -0.015 |
ate | -0.015 |
ra | -0.014 |
rap | -0.014 |
Token | went |
Token ID | 1816 |
Feature activation | -6.29e-03 |
Pos logit contributions | |
cartridge | +0.054 |
uts | +0.054 |
ra | +0.052 |
ate | +0.052 |
connected | +0.051 |
Neg logit contributions | |
bus | -0.061 |
joy | -0.059 |
camel | -0.058 |
vehicle | -0.056 |
elephants | -0.055 |
Token | on |
Token ID | 319 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
cartridge | +0.008 |
uts | +0.008 |
ate | +0.008 |
ung | +0.007 |
ra | +0.007 |
Neg logit contributions | |
bus | -0.011 |
camel | -0.011 |
elephants | -0.010 |
joy | -0.010 |
mo | -0.010 |
Token | their |
Token ID | 511 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
bus | +0.045 |
camel | +0.044 |
joy | +0.041 |
elephants | +0.040 |
vehicle | +0.040 |
Neg logit contributions | |
uts | -0.037 |
cartridge | -0.037 |
ate | -0.035 |
ra | -0.033 |
rap | -0.033 |
Token | merry |
Token ID | 44570 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
cartridge | +0.059 |
uts | +0.058 |
ate | +0.056 |
ra | +0.056 |
cutter | +0.054 |
Neg logit contributions | |
camel | -0.045 |
bus | -0.043 |
joy | -0.041 |
elephants | -0.038 |
mo | -0.038 |
Token | way |
Token ID | 835 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
camel | +0.302 |
joy | +0.285 |
bus | +0.283 |
elephants | +0.283 |
mo | +0.273 |
Neg logit contributions | |
ate | -0.299 |
uts | -0.291 |
rap | -0.280 |
ra | -0.275 |
cartridge | -0.266 |
Token | . |
Token ID | 13 |
Feature activation | -3.48e-03 |
Pos logit contributions | |
camel | +0.051 |
bus | +0.050 |
elephants | +0.046 |
joy | +0.045 |
vehicle | +0.045 |
Neg logit contributions | |
uts | -0.048 |
cartridge | -0.045 |
ate | -0.044 |
ung | -0.042 |
ra | -0.042 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
uts | +0.006 |
cartridge | +0.005 |
ate | +0.005 |
ung | +0.005 |
ra | +0.005 |
Neg logit contributions | |
bus | -0.005 |
camel | -0.005 |
joy | -0.005 |
vehicle | -0.005 |
elephants | -0.005 |
Token | N |
Token ID | 45 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
uts | +0.017 |
cartridge | +0.017 |
ate | +0.017 |
ra | +0.015 |
ung | +0.015 |
Neg logit contributions | |
bus | -0.017 |
camel | -0.017 |
joy | -0.015 |
elephants | -0.015 |
vehicle | -0.015 |
Token | ina |
Token ID | 1437 |
Feature activation | -9.32e-03 |
Pos logit contributions | |
bus | +0.042 |
camel | +0.042 |
joy | +0.041 |
year | +0.039 |
desert | +0.038 |
Neg logit contributions | |
cartridge | -0.054 |
uts | -0.051 |
cutter | -0.048 |
issors | -0.045 |
ressing | -0.045 |
Token | But |
Token ID | 1537 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
cartridge | +0.039 |
uts | +0.038 |
ate | +0.035 |
rap | +0.034 |
ra | +0.034 |
Neg logit contributions | |
bus | -0.035 |
camel | -0.034 |
year | -0.032 |
joy | -0.031 |
taxi | -0.031 |
Token | nothing |
Token ID | 2147 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
uts | +0.004 |
cartridge | +0.004 |
ate | +0.003 |
ra | +0.003 |
rap | +0.003 |
Neg logit contributions | |
bus | -0.004 |
camel | -0.004 |
joy | -0.004 |
elephants | -0.004 |
vehicle | -0.004 |
Token | happened |
Token ID | 3022 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
camel | +0.038 |
bus | +0.037 |
joy | +0.036 |
elephants | +0.035 |
vehicle | +0.034 |
Neg logit contributions | |
uts | -0.020 |
cartridge | -0.020 |
ate | -0.018 |
ra | -0.017 |
ung | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -4.71e-05 |
Pos logit contributions | |
uts | +0.143 |
cartridge | +0.139 |
ate | +0.135 |
ra | +0.129 |
rap | +0.127 |
Neg logit contributions | |
bus | -0.115 |
camel | -0.114 |
joy | -0.104 |
elephants | -0.100 |
vehicle | -0.099 |
Token | The |
Token ID | 383 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
uts | +0.000 |
cartridge | +0.000 |
ate | +0.000 |
ra | +0.000 |
ung | +0.000 |
Neg logit contributions | |
camel | -0.000 |
bus | -0.000 |
merry | -0.000 |
joy | -0.000 |
vehicle | -0.000 |
Token | merry |
Token ID | 44570 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
joy | +0.050 |
camel | +0.046 |
mo | +0.046 |
inspection | +0.045 |
enced | +0.042 |
Neg logit contributions | |
ra | -0.059 |
cartridge | -0.058 |
cutter | -0.056 |
uts | -0.056 |
ate | -0.054 |
Token | - |
Token ID | 12 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
joy | +0.368 |
camel | +0.356 |
elephants | +0.352 |
gru | +0.337 |
mo | +0.335 |
Neg logit contributions | |
ra | -0.234 |
ate | -0.207 |
uts | -0.196 |
rap | -0.184 |
ung | -0.172 |
Token | go |
Token ID | 2188 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
uts | +0.034 |
ra | +0.031 |
ate | +0.030 |
cartridge | +0.029 |
ung | +0.028 |
Neg logit contributions | |
joy | -0.036 |
camel | -0.035 |
bus | -0.033 |
desert | -0.033 |
elephants | -0.032 |
Token | - |
Token ID | 12 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
camel | +0.067 |
joy | +0.066 |
bus | +0.062 |
elephants | +0.061 |
desert | +0.059 |
Neg logit contributions | |
ra | -0.054 |
uts | -0.053 |
ate | -0.052 |
ung | -0.049 |
rap | -0.046 |
Token | round |
Token ID | 744 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
uts | +0.040 |
ate | +0.037 |
ra | +0.037 |
cartridge | +0.036 |
rap | +0.035 |
Neg logit contributions | |
camel | -0.026 |
joy | -0.024 |
bus | -0.024 |
elephants | -0.022 |
desert | -0.022 |
Token | did |
Token ID | 750 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
camel | +0.077 |
joy | +0.073 |
bus | +0.073 |
elephants | +0.067 |
vehicle | +0.066 |
Neg logit contributions | |
uts | -0.081 |
cartridge | -0.076 |
ate | -0.075 |
ra | -0.074 |
ung | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-04 |
Pos logit contributions | |
uts | +0.044 |
cartridge | +0.043 |
ate | +0.041 |
ra | +0.040 |
rap | +0.039 |
Neg logit contributions | |
bus | -0.033 |
camel | -0.033 |
joy | -0.030 |
vehicle | -0.029 |
elephants | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
camel | +0.001 |
joy | +0.000 |
bus | +0.000 |
merry | +0.000 |
elephants | +0.000 |
Neg logit contributions | |
uts | -0.001 |
ate | -0.001 |
cartridge | -0.001 |
rap | -0.001 |
issors | -0.001 |
Token | would |
Token ID | 561 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
camel | +0.018 |
joy | +0.018 |
bus | +0.018 |
elephants | +0.017 |
hi | +0.016 |
Neg logit contributions | |
cartridge | -0.020 |
uts | -0.019 |
ate | -0.019 |
ra | -0.018 |
connected | -0.018 |
Token | ride |
Token ID | 6594 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
camel | +0.075 |
joy | +0.075 |
bus | +0.067 |
elephants | +0.065 |
mo | +0.064 |
Neg logit contributions | |
cartridge | -0.068 |
uts | -0.067 |
ate | -0.067 |
ra | -0.066 |
rap | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
camel | +0.089 |
bus | +0.087 |
joy | +0.082 |
elephants | +0.077 |
vehicle | +0.077 |
Neg logit contributions | |
uts | -0.088 |
ate | -0.085 |
cartridge | -0.084 |
ra | -0.080 |
rap | -0.079 |
Token | merry |
Token ID | 44570 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
camel | +0.030 |
joy | +0.028 |
bus | +0.028 |
mo | +0.026 |
elephants | +0.025 |
Neg logit contributions | |
uts | -0.038 |
cartridge | -0.038 |
ate | -0.037 |
ra | -0.035 |
rap | -0.034 |
Token | - |
Token ID | 12 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
camel | +0.316 |
joy | +0.311 |
mo | +0.296 |
elephants | +0.289 |
gru | +0.284 |
Neg logit contributions | |
uts | -0.280 |
ate | -0.278 |
ra | -0.257 |
cartridge | -0.250 |
rap | -0.247 |
Token | go |
Token ID | 2188 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
uts | +0.035 |
ate | +0.033 |
cartridge | +0.033 |
ra | +0.031 |
rap | +0.030 |
Neg logit contributions | |
camel | -0.030 |
joy | -0.029 |
bus | -0.028 |
elephants | -0.026 |
desert | -0.026 |
Token | - |
Token ID | 12 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
camel | +0.059 |
bus | +0.057 |
joy | +0.056 |
elephants | +0.052 |
desert | +0.051 |
Neg logit contributions | |
uts | -0.063 |
ate | -0.059 |
cartridge | -0.058 |
ra | -0.057 |
rap | -0.055 |
Token | round |
Token ID | 744 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
uts | +0.043 |
ate | +0.041 |
cartridge | +0.040 |
ra | +0.039 |
rap | +0.039 |
Neg logit contributions | |
camel | -0.021 |
bus | -0.020 |
joy | -0.019 |
elephants | -0.017 |
vehicle | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
camel | +0.079 |
bus | +0.078 |
joy | +0.074 |
vehicle | +0.069 |
elephants | +0.069 |
Neg logit contributions | |
uts | -0.084 |
cartridge | -0.081 |
ate | -0.079 |
ra | -0.075 |
rap | -0.074 |
Token | swing |
Token ID | 9628 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
joy | +0.025 |
mo | +0.023 |
camel | +0.023 |
gru | +0.022 |
elephants | +0.021 |
Neg logit contributions | |
ate | -0.015 |
fold | -0.015 |
connect | -0.013 |
work | -0.012 |
cooperate | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +3.87e-04 |
Pos logit contributions | |
camel | +0.199 |
joy | +0.193 |
mo | +0.189 |
polar | +0.185 |
bus | +0.177 |
Neg logit contributions | |
uts | -0.130 |
ate | -0.122 |
cartridge | -0.108 |
rap | -0.106 |
ra | -0.101 |
Token | play |
Token ID | 711 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
joy | +0.000 |
camel | +0.000 |
bus | +0.000 |
year | +0.000 |
mo | +0.000 |
Neg logit contributions | |
uts | -0.001 |
cartridge | -0.001 |
ate | -0.001 |
cutter | -0.001 |
ra | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
camel | +0.067 |
mo | +0.067 |
bus | +0.065 |
joy | +0.064 |
polar | +0.064 |
Neg logit contributions | |
ate | -0.031 |
cartridge | -0.027 |
uts | -0.027 |
rap | -0.024 |
cutter | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
camel | +0.058 |
mo | +0.057 |
polar | +0.054 |
joy | +0.053 |
gru | +0.052 |
Neg logit contributions | |
ate | -0.029 |
uts | -0.027 |
rap | -0.024 |
ourselves | -0.023 |
matters | -0.022 |
Token | merry |
Token ID | 44570 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
joy | +0.034 |
mo | +0.033 |
gru | +0.029 |
camel | +0.028 |
polar | +0.028 |
Neg logit contributions | |
ate | -0.027 |
uts | -0.025 |
ourselves | -0.025 |
her | -0.023 |
resses | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
joy | +0.356 |
camel | +0.337 |
mo | +0.335 |
gru | +0.332 |
polar | +0.324 |
Neg logit contributions | |
ate | -0.249 |
uts | -0.243 |
rap | -0.220 |
ra | -0.209 |
ung | -0.198 |
Token | go |
Token ID | 2188 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
uts | +0.034 |
ate | +0.030 |
cartridge | +0.028 |
rap | +0.028 |
ra | +0.028 |
Neg logit contributions | |
joy | -0.033 |
camel | -0.032 |
bus | -0.030 |
vehicle | -0.028 |
elephants | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
joy | +0.069 |
camel | +0.067 |
bus | +0.063 |
gru | +0.061 |
mo | +0.061 |
Neg logit contributions | |
uts | -0.055 |
ate | -0.050 |
ra | -0.048 |
rap | -0.045 |
ung | -0.045 |
Token | round |
Token ID | 744 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
uts | +0.042 |
ate | +0.038 |
cartridge | +0.037 |
rap | +0.036 |
ra | +0.036 |
Neg logit contributions | |
joy | -0.023 |
camel | -0.023 |
bus | -0.022 |
vehicle | -0.020 |
elephants | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +3.27e-03 |
Pos logit contributions | |
camel | +0.082 |
joy | +0.079 |
bus | +0.078 |
vehicle | +0.072 |
mo | +0.071 |
Neg logit contributions | |
uts | -0.084 |
cartridge | -0.077 |
ate | -0.077 |
ra | -0.072 |
rap | -0.072 |
Token | happily |
Token ID | 18177 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
bus | +0.017 |
camel | +0.017 |
joy | +0.016 |
elephants | +0.015 |
vehicle | +0.015 |
Neg logit contributions | |
uts | -0.019 |
cartridge | -0.018 |
ate | -0.018 |
ra | -0.017 |
rap | -0.017 |
Token | ran |
Token ID | 4966 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
cartridge | +0.098 |
uts | +0.097 |
ate | +0.094 |
ra | +0.090 |
cutter | +0.089 |
Neg logit contributions | |
camel | -0.101 |
bus | -0.100 |
joy | -0.098 |
elephants | -0.092 |
vehicle | -0.091 |
Token | back |
Token ID | 736 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
bus | +0.089 |
camel | +0.082 |
joy | +0.081 |
taxi | +0.078 |
vehicle | +0.077 |
Neg logit contributions | |
uts | -0.095 |
cartridge | -0.093 |
ate | -0.088 |
ra | -0.085 |
rap | -0.084 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
bus | +0.090 |
camel | +0.087 |
joy | +0.083 |
vehicle | +0.080 |
taxi | +0.078 |
Neg logit contributions | |
uts | -0.088 |
cartridge | -0.087 |
ate | -0.081 |
ra | -0.078 |
ung | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
camel | +0.018 |
bus | +0.017 |
mo | +0.016 |
elephants | +0.016 |
joy | +0.016 |
Neg logit contributions | |
ate | -0.013 |
cartridge | -0.013 |
uts | -0.013 |
rap | -0.013 |
ra | -0.012 |
Token | merry |
Token ID | 44570 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
bus | +0.019 |
camel | +0.019 |
joy | +0.017 |
elephants | +0.016 |
vehicle | +0.016 |
Neg logit contributions | |
uts | -0.035 |
cartridge | -0.035 |
ate | -0.034 |
ra | -0.032 |
rap | -0.032 |
Token | - |
Token ID | 12 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
camel | +0.309 |
elephants | +0.294 |
joy | +0.294 |
bus | +0.287 |
mo | +0.282 |
Neg logit contributions | |
uts | -0.287 |
ate | -0.287 |
rap | -0.267 |
ra | -0.266 |
cartridge | -0.266 |
Token | go |
Token ID | 2188 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
uts | +0.038 |
cartridge | +0.036 |
ate | +0.036 |
ra | +0.034 |
rap | +0.034 |
Neg logit contributions | |
camel | -0.031 |
bus | -0.031 |
joy | -0.030 |
elephants | -0.027 |
vehicle | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
camel | +0.059 |
bus | +0.058 |
joy | +0.056 |
elephants | +0.054 |
vehicle | +0.051 |
Neg logit contributions | |
uts | -0.061 |
ate | -0.058 |
cartridge | -0.056 |
ra | -0.056 |
rap | -0.054 |
Token | round |
Token ID | 744 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
uts | +0.047 |
cartridge | +0.047 |
ate | +0.045 |
ra | +0.044 |
rap | +0.043 |
Neg logit contributions | |
bus | -0.020 |
camel | -0.019 |
joy | -0.017 |
elephants | -0.016 |
vehicle | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
camel | +0.078 |
bus | +0.076 |
joy | +0.072 |
elephants | +0.069 |
vehicle | +0.069 |
Neg logit contributions | |
uts | -0.084 |
cartridge | -0.079 |
ate | -0.077 |
ra | -0.073 |
ung | -0.072 |
Token | it |
Token ID | 340 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
ra | +0.002 |
cutter | +0.002 |
Neg logit contributions | |
bus | -0.002 |
camel | -0.002 |
joy | -0.002 |
vehicle | -0.002 |
year | -0.002 |
Token | led |
Token ID | 2957 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
uts | +0.017 |
cartridge | +0.017 |
ate | +0.016 |
ra | +0.015 |
rap | +0.015 |
Neg logit contributions | |
bus | -0.015 |
camel | -0.015 |
joy | -0.014 |
elephants | -0.013 |
vehicle | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
bus | +0.025 |
camel | +0.025 |
joy | +0.023 |
vehicle | +0.022 |
elephants | +0.022 |
Neg logit contributions | |
uts | -0.022 |
cartridge | -0.021 |
ate | -0.020 |
ra | -0.019 |
rap | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
cartridge | +0.031 |
uts | +0.031 |
ate | +0.030 |
rap | +0.028 |
ra | +0.028 |
Neg logit contributions | |
bus | -0.029 |
camel | -0.028 |
joy | -0.026 |
vehicle | -0.025 |
elephants | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
bus | +0.034 |
camel | +0.033 |
joy | +0.032 |
year | +0.030 |
elephants | +0.029 |
Neg logit contributions | |
uts | -0.046 |
cartridge | -0.045 |
ate | -0.043 |
ra | -0.041 |
ung | -0.041 |
Token | merry |
Token ID | 44570 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
cartridge | +0.037 |
uts | +0.035 |
cutter | +0.035 |
fold | +0.033 |
rap | +0.032 |
Neg logit contributions | |
joy | -0.036 |
mo | -0.032 |
camel | -0.032 |
elephants | -0.032 |
hi | -0.031 |
Token | chase |
Token ID | 15505 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
joy | +0.308 |
camel | +0.302 |
elephants | +0.299 |
mo | +0.287 |
bus | +0.279 |
Neg logit contributions | |
uts | -0.280 |
ate | -0.276 |
rap | -0.271 |
ra | -0.262 |
cartridge | -0.261 |
Token | around |
Token ID | 1088 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
bus | +0.163 |
camel | +0.162 |
joy | +0.151 |
elephants | +0.146 |
merry | +0.146 |
Neg logit contributions | |
uts | -0.156 |
cartridge | -0.148 |
ung | -0.139 |
ate | -0.137 |
ra | -0.135 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
uts | +0.054 |
cartridge | +0.054 |
ate | +0.051 |
ra | +0.051 |
cutter | +0.050 |
Neg logit contributions | |
bus | -0.073 |
camel | -0.073 |
vehicle | -0.066 |
joy | -0.064 |
mo | -0.064 |
Token | garden |
Token ID | 11376 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
bus | +0.023 |
camel | +0.022 |
joy | +0.021 |
vehicle | +0.019 |
elephants | +0.019 |
Neg logit contributions | |
uts | -0.034 |
cartridge | -0.034 |
ate | -0.033 |
ra | -0.032 |
rap | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -8.42e-04 |
Pos logit contributions | |
uts | +0.035 |
cartridge | +0.033 |
ate | +0.031 |
cutter | +0.031 |
ra | +0.030 |
Neg logit contributions | |
camel | -0.034 |
bus | -0.034 |
joy | -0.032 |
vehicle | -0.031 |
merry | -0.030 |
Token | play |
Token ID | 711 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
joy | +0.024 |
camel | +0.024 |
mo | +0.023 |
bus | +0.023 |
year | +0.022 |
Neg logit contributions | |
ate | -0.017 |
cartridge | -0.015 |
fold | -0.014 |
matters | -0.014 |
rap | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
bus | +0.054 |
camel | +0.054 |
joy | +0.051 |
mo | +0.050 |
elephants | +0.049 |
Neg logit contributions | |
uts | -0.041 |
cartridge | -0.040 |
ate | -0.040 |
ung | -0.036 |
cutter | -0.036 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
bus | +0.004 |
camel | +0.004 |
joy | +0.004 |
elephants | +0.003 |
vehicle | +0.003 |
Neg logit contributions | |
uts | -0.005 |
cartridge | -0.005 |
ate | -0.005 |
ra | -0.005 |
rap | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
uts | +0.010 |
cartridge | +0.010 |
ate | +0.010 |
ra | +0.009 |
ung | +0.009 |
Neg logit contributions | |
bus | -0.006 |
camel | -0.006 |
joy | -0.005 |
elephants | -0.005 |
vehicle | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
joy | +0.137 |
camel | +0.136 |
bus | +0.135 |
year | +0.133 |
mo | +0.132 |
Neg logit contributions | |
uts | -0.078 |
ate | -0.073 |
cartridge | -0.072 |
ung | -0.063 |
connected | -0.062 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
cartridge | +0.035 |
uts | +0.034 |
cutter | +0.034 |
ate | +0.033 |
ra | +0.032 |
Neg logit contributions | |
mo | -0.030 |
joy | -0.029 |
camel | -0.027 |
bus | -0.026 |
elephants | -0.026 |
Token | - |
Token ID | 12 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
camel | +0.317 |
joy | +0.309 |
elephants | +0.307 |
mo | +0.298 |
bus | +0.294 |
Neg logit contributions | |
ate | -0.268 |
uts | -0.262 |
rap | -0.257 |
ra | -0.256 |
cartridge | -0.247 |
Token | go |
Token ID | 2188 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
uts | +0.035 |
cartridge | +0.032 |
ate | +0.032 |
ra | +0.031 |
rap | +0.030 |
Neg logit contributions | |
joy | -0.031 |
camel | -0.030 |
bus | -0.030 |
elephants | -0.027 |
vehicle | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
joy | +0.069 |
camel | +0.067 |
bus | +0.063 |
elephants | +0.062 |
mo | +0.061 |
Neg logit contributions | |
uts | -0.048 |
ra | -0.045 |
ate | -0.044 |
ung | -0.041 |
rap | -0.040 |
Token | round |
Token ID | 744 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
uts | +0.043 |
cartridge | +0.041 |
ate | +0.040 |
ra | +0.039 |
rap | +0.038 |
Neg logit contributions | |
camel | -0.022 |
bus | -0.021 |
joy | -0.020 |
elephants | -0.018 |
vehicle | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +5.13e-04 |
Pos logit contributions | |
camel | +0.086 |
joy | +0.083 |
bus | +0.078 |
mo | +0.077 |
polar | +0.075 |
Neg logit contributions | |
uts | -0.077 |
ate | -0.068 |
cartridge | -0.066 |
ung | -0.065 |
ra | -0.065 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
camel | +0.006 |
bus | +0.006 |
joy | +0.005 |
vehicle | +0.005 |
elephants | +0.005 |
Neg logit contributions | |
uts | -0.006 |
cartridge | -0.006 |
ate | -0.006 |
ung | -0.005 |
cutter | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
cartridge | +0.008 |
uts | +0.008 |
ate | +0.007 |
rap | +0.007 |
ra | +0.007 |
Neg logit contributions | |
bus | -0.005 |
camel | -0.005 |
joy | -0.004 |
vehicle | -0.004 |
elephants | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
uts | +0.018 |
cartridge | +0.017 |
ate | +0.016 |
cutter | +0.015 |
ra | +0.015 |
Neg logit contributions | |
camel | -0.025 |
bus | -0.025 |
joy | -0.024 |
mo | -0.023 |
year | -0.023 |
Token | ride |
Token ID | 6594 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
camel | +0.017 |
joy | +0.017 |
bus | +0.016 |
mo | +0.015 |
elephants | +0.015 |
Neg logit contributions | |
uts | -0.017 |
ate | -0.017 |
cartridge | -0.016 |
ra | -0.016 |
rap | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
camel | +0.103 |
bus | +0.099 |
joy | +0.097 |
desert | +0.093 |
mo | +0.093 |
Neg logit contributions | |
uts | -0.064 |
ate | -0.063 |
ra | -0.058 |
cartridge | -0.056 |
rap | -0.056 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
joy | +0.029 |
mo | +0.025 |
camel | +0.024 |
gru | +0.024 |
polar | +0.022 |
Neg logit contributions | |
uts | -0.033 |
ate | -0.032 |
ra | -0.031 |
cartridge | -0.030 |
resses | -0.029 |
Token | - |
Token ID | 12 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
joy | +0.369 |
camel | +0.349 |
elephants | +0.338 |
mo | +0.336 |
gru | +0.334 |
Neg logit contributions | |
uts | -0.244 |
ate | -0.232 |
ra | -0.215 |
rap | -0.201 |
ung | -0.192 |
Token | go |
Token ID | 2188 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
uts | +0.035 |
ate | +0.030 |
ra | +0.029 |
cartridge | +0.028 |
rap | +0.028 |
Neg logit contributions | |
joy | -0.035 |
camel | -0.033 |
bus | -0.031 |
desert | -0.030 |
elephants | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
joy | +0.070 |
camel | +0.068 |
bus | +0.063 |
desert | +0.062 |
elephants | +0.062 |
Neg logit contributions | |
uts | -0.052 |
ra | -0.048 |
ate | -0.047 |
ung | -0.042 |
rap | -0.042 |
Token | round |
Token ID | 744 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
uts | +0.043 |
ate | +0.039 |
ra | +0.037 |
cartridge | +0.037 |
rap | +0.037 |
Neg logit contributions | |
camel | -0.024 |
joy | -0.024 |
bus | -0.022 |
vehicle | -0.020 |
elephants | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-03 |
Pos logit contributions | |
camel | +0.076 |
joy | +0.074 |
bus | +0.072 |
elephants | +0.067 |
vehicle | +0.066 |
Neg logit contributions | |
uts | -0.086 |
ate | -0.078 |
cartridge | -0.077 |
ra | -0.074 |
ung | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
uts | +0.053 |
cartridge | +0.051 |
ate | +0.049 |
ra | +0.047 |
ung | +0.047 |
Neg logit contributions | |
bus | -0.042 |
camel | -0.041 |
joy | -0.037 |
elephants | -0.037 |
vehicle | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
bus | +0.015 |
camel | +0.015 |
joy | +0.014 |
vehicle | +0.013 |
elephants | +0.013 |
Neg logit contributions | |
uts | -0.017 |
cartridge | -0.017 |
ate | -0.016 |
ra | -0.015 |
ung | -0.015 |
Token | got |
Token ID | 1392 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
bus | +0.013 |
camel | +0.012 |
joy | +0.011 |
elephants | +0.011 |
vehicle | +0.011 |
Neg logit contributions | |
uts | -0.017 |
cartridge | -0.016 |
ate | -0.016 |
rap | -0.015 |
ra | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
uts | +0.049 |
cartridge | +0.045 |
rap | +0.045 |
ate | +0.043 |
ressing | +0.043 |
Neg logit contributions | |
bus | -0.037 |
camel | -0.035 |
taxi | -0.034 |
vehicle | -0.034 |
joy | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
bus | +0.034 |
camel | +0.031 |
joy | +0.031 |
taxi | +0.029 |
vehicle | +0.028 |
Neg logit contributions | |
uts | -0.043 |
cartridge | -0.042 |
ate | -0.040 |
ressing | -0.038 |
ung | -0.038 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
joy | +0.036 |
camel | +0.032 |
mo | +0.032 |
year | +0.030 |
inspection | +0.030 |
Neg logit contributions | |
cartridge | -0.034 |
cutter | -0.030 |
ra | -0.030 |
ate | -0.029 |
fold | -0.029 |
Token | - |
Token ID | 12 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
joy | +0.326 |
camel | +0.325 |
elephants | +0.318 |
mo | +0.304 |
bus | +0.296 |
Neg logit contributions | |
uts | -0.265 |
ate | -0.256 |
ra | -0.249 |
cartridge | -0.240 |
rap | -0.234 |
Token | go |
Token ID | 2188 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
uts | +0.038 |
cartridge | +0.035 |
ate | +0.035 |
ra | +0.034 |
rap | +0.033 |
Neg logit contributions | |
camel | -0.034 |
joy | -0.033 |
bus | -0.033 |
elephants | -0.030 |
vehicle | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
camel | +0.063 |
joy | +0.063 |
bus | +0.060 |
elephants | +0.058 |
desert | +0.057 |
Neg logit contributions | |
uts | -0.056 |
ra | -0.054 |
ate | -0.053 |
cartridge | -0.051 |
rap | -0.049 |
Token | round |
Token ID | 744 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
uts | +0.046 |
cartridge | +0.044 |
ate | +0.043 |
ra | +0.042 |
rap | +0.041 |
Neg logit contributions | |
camel | -0.023 |
bus | -0.022 |
joy | -0.021 |
elephants | -0.019 |
vehicle | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
camel | +0.075 |
bus | +0.072 |
joy | +0.071 |
elephants | +0.066 |
vehicle | +0.065 |
Neg logit contributions | |
uts | -0.086 |
cartridge | -0.081 |
ate | -0.078 |
ra | -0.075 |
ung | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
camel | +0.081 |
bus | +0.079 |
joy | +0.079 |
mo | +0.075 |
year | +0.073 |
Neg logit contributions | |
uts | -0.064 |
ate | -0.064 |
cartridge | -0.060 |
rap | -0.058 |
ourselves | -0.057 |
Token | big |
Token ID | 1263 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
camel | +0.030 |
joy | +0.028 |
mo | +0.028 |
inspection | +0.025 |
bus | +0.025 |
Neg logit contributions | |
ate | -0.044 |
uts | -0.044 |
cartridge | -0.043 |
ra | -0.041 |
ourselves | -0.040 |
Token | fountain |
Token ID | 29420 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
mo | +0.021 |
camel | +0.020 |
joy | +0.018 |
gru | +0.017 |
ah | +0.017 |
Neg logit contributions | |
ate | -0.026 |
cartridge | -0.024 |
uts | -0.024 |
matters | -0.023 |
ra | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
camel | +0.108 |
joy | +0.108 |
bus | +0.107 |
vehicle | +0.100 |
mo | +0.097 |
Neg logit contributions | |
uts | -0.094 |
ate | -0.091 |
cartridge | -0.086 |
rap | -0.081 |
ra | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
camel | +0.004 |
bus | +0.004 |
joy | +0.004 |
mo | +0.004 |
year | +0.004 |
Neg logit contributions | |
uts | -0.004 |
cartridge | -0.004 |
ate | -0.004 |
ra | -0.004 |
rap | -0.003 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
camel | +0.033 |
mo | +0.032 |
joy | +0.032 |
bus | +0.030 |
inspection | +0.030 |
Neg logit contributions | |
cartridge | -0.039 |
ate | -0.039 |
uts | -0.038 |
ra | -0.037 |
ourselves | -0.036 |
Token | - |
Token ID | 12 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
joy | +0.331 |
camel | +0.326 |
mo | +0.322 |
gru | +0.316 |
elephants | +0.312 |
Neg logit contributions | |
ate | -0.266 |
uts | -0.245 |
ra | -0.239 |
rap | -0.220 |
ourselves | -0.205 |
Token | go |
Token ID | 2188 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
uts | +0.033 |
ate | +0.031 |
ra | +0.030 |
cartridge | +0.028 |
rap | +0.028 |
Neg logit contributions | |
joy | -0.035 |
camel | -0.033 |
bus | -0.031 |
desert | -0.030 |
vehicle | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
joy | +0.061 |
camel | +0.061 |
bus | +0.058 |
elephants | +0.056 |
mo | +0.054 |
Neg logit contributions | |
uts | -0.053 |
ate | -0.052 |
ra | -0.051 |
rap | -0.047 |
cartridge | -0.046 |
Token | round |
Token ID | 744 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
uts | +0.043 |
ate | +0.041 |
cartridge | +0.040 |
ra | +0.039 |
rap | +0.039 |
Neg logit contributions | |
camel | -0.022 |
joy | -0.022 |
bus | -0.021 |
vehicle | -0.018 |
elephants | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +9.20e-03 |
Pos logit contributions | |
camel | +0.081 |
bus | +0.079 |
joy | +0.078 |
vehicle | +0.072 |
elephants | +0.071 |
Neg logit contributions | |
uts | -0.078 |
ate | -0.074 |
cartridge | -0.073 |
ra | -0.069 |
rap | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
uts | +0.028 |
cartridge | +0.027 |
ate | +0.027 |
rap | +0.025 |
ra | +0.024 |
Neg logit contributions | |
bus | -0.030 |
camel | -0.030 |
joy | -0.028 |
elephants | -0.027 |
vehicle | -0.027 |
Token | After |
Token ID | 3260 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
cartridge | +0.028 |
uts | +0.028 |
ate | +0.025 |
ra | +0.025 |
ung | +0.024 |
Neg logit contributions | |
bus | -0.030 |
camel | -0.029 |
year | -0.028 |
joy | -0.026 |
taxi | -0.026 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
uts | +0.140 |
cartridge | +0.129 |
cutter | +0.121 |
ate | +0.119 |
ra | +0.119 |
Neg logit contributions | |
camel | -0.205 |
bus | -0.200 |
mo | -0.190 |
joy | -0.185 |
vehicle | -0.185 |
Token | on |
Token ID | 319 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
camel | +0.044 |
bus | +0.042 |
joy | +0.042 |
mo | +0.040 |
elephants | +0.039 |
Neg logit contributions | |
cartridge | -0.037 |
ate | -0.036 |
uts | -0.035 |
cutter | -0.034 |
rap | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
bus | +0.036 |
camel | +0.036 |
joy | +0.033 |
elephants | +0.031 |
vehicle | +0.031 |
Neg logit contributions | |
uts | -0.044 |
cartridge | -0.043 |
ate | -0.042 |
ra | -0.040 |
rap | -0.040 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
joy | +0.024 |
camel | +0.023 |
mo | +0.020 |
bus | +0.020 |
hi | +0.020 |
Neg logit contributions | |
cartridge | -0.034 |
ate | -0.034 |
uts | -0.033 |
rap | -0.032 |
cutter | -0.032 |
Token | - |
Token ID | 12 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
joy | +0.349 |
camel | +0.337 |
gru | +0.324 |
elephants | +0.320 |
hi | +0.316 |
Neg logit contributions | |
ate | -0.241 |
uts | -0.237 |
ra | -0.219 |
rap | -0.214 |
ung | -0.200 |
Token | go |
Token ID | 2188 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
uts | +0.032 |
ate | +0.027 |
cartridge | +0.026 |
ra | +0.025 |
rap | +0.025 |
Neg logit contributions | |
joy | -0.039 |
camel | -0.039 |
bus | -0.037 |
vehicle | -0.035 |
elephants | -0.035 |
Token | - |
Token ID | 12 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
joy | +0.072 |
camel | +0.072 |
bus | +0.067 |
elephants | +0.065 |
gru | +0.064 |
Neg logit contributions | |
uts | -0.052 |
ate | -0.048 |
ra | -0.046 |
ung | -0.043 |
ourselves | -0.042 |
Token | round |
Token ID | 744 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
uts | +0.042 |
ate | +0.038 |
cartridge | +0.036 |
ra | +0.036 |
rap | +0.036 |
Neg logit contributions | |
camel | -0.026 |
joy | -0.025 |
bus | -0.024 |
elephants | -0.022 |
vehicle | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
camel | +0.078 |
joy | +0.075 |
bus | +0.069 |
gru | +0.066 |
elephants | +0.066 |
Neg logit contributions | |
uts | -0.085 |
ate | -0.076 |
cartridge | -0.073 |
ung | -0.073 |
ra | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
camel | +0.112 |
joy | +0.111 |
bus | +0.110 |
elephants | +0.105 |
year | +0.102 |
Neg logit contributions | |
ate | -0.109 |
cartridge | -0.109 |
uts | -0.108 |
connected | -0.097 |
rap | -0.096 |
Token | he |
Token ID | 339 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
camel | +0.021 |
bus | +0.019 |
joy | +0.019 |
mo | +0.018 |
desert | +0.018 |
Neg logit contributions | |
uts | -0.024 |
ate | -0.022 |
cartridge | -0.022 |
ra | -0.021 |
cutter | -0.021 |
Token | whist |
Token ID | 32262 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
bus | +0.016 |
camel | +0.016 |
joy | +0.014 |
elephants | +0.014 |
taxi | +0.013 |
Neg logit contributions | |
cartridge | -0.032 |
uts | -0.032 |
ate | -0.032 |
ra | -0.031 |
connected | -0.030 |
Token | led |
Token ID | 992 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
bus | +0.029 |
camel | +0.029 |
joy | +0.027 |
vehicle | +0.026 |
elephants | +0.026 |
Neg logit contributions | |
uts | -0.025 |
cartridge | -0.024 |
ate | -0.023 |
ra | -0.022 |
rap | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
uts | +0.112 |
ate | +0.109 |
cartridge | +0.109 |
ra | +0.102 |
rap | +0.100 |
Neg logit contributions | |
camel | -0.159 |
bus | -0.158 |
joy | -0.146 |
elephants | -0.144 |
taxi | -0.141 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
cartridge | +0.043 |
uts | +0.041 |
ra | +0.040 |
cutter | +0.040 |
connected | +0.038 |
Neg logit contributions | |
camel | -0.033 |
bus | -0.032 |
joy | -0.032 |
mo | -0.031 |
elephants | -0.030 |
Token | tune |
Token ID | 14009 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
joy | +0.350 |
elephants | +0.345 |
camel | +0.344 |
mo | +0.328 |
bus | +0.314 |
Neg logit contributions | |
ra | -0.228 |
ate | -0.221 |
rap | -0.217 |
uts | -0.217 |
cartridge | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-03 |
Pos logit contributions | |
camel | +0.069 |
bus | +0.068 |
joy | +0.065 |
elephants | +0.061 |
vehicle | +0.060 |
Neg logit contributions | |
uts | -0.078 |
cartridge | -0.075 |
ate | -0.071 |
ra | -0.069 |
ung | -0.068 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
camel | +0.003 |
bus | +0.003 |
joy | +0.003 |
desert | +0.003 |
mo | +0.003 |
Neg logit contributions | |
uts | -0.004 |
cartridge | -0.004 |
ate | -0.004 |
ra | -0.004 |
rap | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
camel | +0.019 |
bus | +0.019 |
joy | +0.018 |
merry | +0.016 |
elephants | +0.016 |
Neg logit contributions | |
uts | -0.029 |
cartridge | -0.028 |
ate | -0.027 |
ra | -0.027 |
ung | -0.026 |
Token | heard |
Token ID | 2982 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
bus | +0.016 |
camel | +0.015 |
joy | +0.014 |
elephants | +0.013 |
taxi | +0.013 |
Neg logit contributions | |
uts | -0.032 |
cartridge | -0.031 |
ate | -0.031 |
ra | -0.031 |
ung | -0.030 |
Token | Then |
Token ID | 3244 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
bus | +0.009 |
camel | +0.009 |
vehicle | +0.008 |
elephants | +0.008 |
joy | +0.008 |
Neg logit contributions | |
uts | -0.014 |
cartridge | -0.013 |
ate | -0.013 |
ung | -0.012 |
ra | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
uts | +0.155 |
cartridge | +0.149 |
ate | +0.145 |
ra | +0.142 |
ung | +0.139 |
Neg logit contributions | |
bus | -0.110 |
camel | -0.108 |
joy | -0.102 |
elephants | -0.097 |
vehicle | -0.096 |
Token | ran |
Token ID | 4966 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
camel | +0.023 |
bus | +0.023 |
joy | +0.022 |
vehicle | +0.020 |
elephants | +0.020 |
Neg logit contributions | |
cartridge | -0.028 |
uts | -0.028 |
ate | -0.027 |
ra | -0.027 |
cutter | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
bus | +0.083 |
camel | +0.074 |
joy | +0.073 |
taxi | +0.069 |
vehicle | +0.068 |
Neg logit contributions | |
uts | -0.102 |
cartridge | -0.101 |
ate | -0.098 |
ra | -0.095 |
rap | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
camel | +0.017 |
bus | +0.016 |
joy | +0.016 |
elephants | +0.015 |
mo | +0.015 |
Neg logit contributions | |
ate | -0.015 |
uts | -0.014 |
rap | -0.014 |
cartridge | -0.014 |
ra | -0.014 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
mo | +0.030 |
joy | +0.029 |
inspection | +0.027 |
year | +0.027 |
camel | +0.026 |
Neg logit contributions | |
cartridge | -0.037 |
ra | -0.036 |
ate | -0.036 |
cutter | -0.035 |
check | -0.035 |
Token | - |
Token ID | 12 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
joy | +0.336 |
camel | +0.324 |
mo | +0.315 |
elephants | +0.313 |
gru | +0.311 |
Neg logit contributions | |
uts | -0.252 |
ate | -0.249 |
ra | -0.239 |
rap | -0.229 |
cartridge | -0.215 |
Token | go |
Token ID | 2188 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
uts | +0.036 |
ate | +0.033 |
cartridge | +0.033 |
ra | +0.032 |
rap | +0.031 |
Neg logit contributions | |
joy | -0.032 |
camel | -0.032 |
bus | -0.031 |
elephants | -0.029 |
desert | -0.029 |
Token | - |
Token ID | 12 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
camel | +0.059 |
joy | +0.058 |
bus | +0.056 |
elephants | +0.053 |
desert | +0.052 |
Neg logit contributions | |
uts | -0.057 |
ate | -0.053 |
ra | -0.052 |
cartridge | -0.051 |
ung | -0.049 |
Token | round |
Token ID | 744 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
uts | +0.044 |
ate | +0.041 |
cartridge | +0.041 |
ra | +0.040 |
rap | +0.039 |
Neg logit contributions | |
camel | -0.023 |
joy | -0.022 |
bus | -0.022 |
elephants | -0.020 |
vehicle | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
camel | +0.072 |
bus | +0.070 |
joy | +0.067 |
elephants | +0.063 |
vehicle | +0.063 |
Neg logit contributions | |
uts | -0.086 |
cartridge | -0.082 |
ate | -0.080 |
ra | -0.076 |
ung | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | -3.47e-03 |
Pos logit contributions | |
camel | +0.016 |
bus | +0.016 |
joy | +0.015 |
vehicle | +0.015 |
gru | +0.015 |
Neg logit contributions | |
cartridge | -0.015 |
uts | -0.015 |
ra | -0.014 |
connected | -0.014 |
cutter | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
cartridge | +0.005 |
uts | +0.005 |
ate | +0.004 |
ra | +0.004 |
cutter | +0.004 |
Neg logit contributions | |
bus | -0.006 |
camel | -0.006 |
joy | -0.005 |
vehicle | -0.005 |
year | -0.005 |
Token | sun |
Token ID | 4252 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
joy | +0.024 |
camel | +0.022 |
inspection | +0.021 |
bus | +0.021 |
parking | +0.020 |
Neg logit contributions | |
ra | -0.029 |
cartridge | -0.028 |
cutter | -0.028 |
ate | -0.027 |
connected | -0.027 |
Token | had |
Token ID | 550 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
uts | +0.078 |
cartridge | +0.076 |
ate | +0.073 |
ra | +0.070 |
rap | +0.069 |
Neg logit contributions | |
bus | -0.068 |
camel | -0.067 |
joy | -0.062 |
elephants | -0.060 |
vehicle | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
uts | +0.008 |
cartridge | +0.008 |
ate | +0.008 |
ra | +0.007 |
ung | +0.007 |
Neg logit contributions | |
bus | -0.008 |
camel | -0.008 |
joy | -0.008 |
vehicle | -0.008 |
mo | -0.007 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
cartridge | +0.040 |
uts | +0.040 |
cutter | +0.039 |
ra | +0.037 |
ate | +0.037 |
Neg logit contributions | |
camel | -0.036 |
bus | -0.036 |
mo | -0.036 |
joy | -0.035 |
elephants | -0.033 |
Token | lunch |
Token ID | 9965 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
camel | +0.339 |
elephants | +0.337 |
mo | +0.325 |
joy | +0.315 |
gru | +0.314 |
Neg logit contributions | |
ate | -0.241 |
ra | -0.232 |
rap | -0.228 |
uts | -0.217 |
ung | -0.207 |
Token | of |
Token ID | 286 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
uts | +0.046 |
cartridge | +0.045 |
ate | +0.045 |
rap | +0.043 |
ra | +0.042 |
Neg logit contributions | |
bus | -0.037 |
camel | -0.036 |
joy | -0.033 |
year | -0.032 |
elephants | -0.032 |
Token | sandwiches |
Token ID | 29777 |
Feature activation | -9.62e-04 |
Pos logit contributions | |
camel | +0.027 |
bus | +0.027 |
joy | +0.026 |
mo | +0.026 |
vehicle | +0.025 |
Neg logit contributions | |
uts | -0.030 |
ate | -0.029 |
cartridge | -0.029 |
ra | -0.027 |
cutter | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
ra | +0.002 |
rap | +0.002 |
Neg logit contributions | |
bus | -0.001 |
camel | -0.001 |
joy | -0.001 |
elephants | -0.001 |
vehicle | -0.001 |
Token | fruit |
Token ID | 8234 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
uts | +0.005 |
cartridge | +0.005 |
ate | +0.005 |
ra | +0.004 |
cutter | +0.004 |
Neg logit contributions | |
bus | -0.005 |
camel | -0.005 |
joy | -0.004 |
vehicle | -0.004 |
mo | -0.004 |
Token | playground |
Token ID | 24817 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
bus | +0.020 |
camel | +0.019 |
joy | +0.016 |
vehicle | +0.015 |
elephants | +0.015 |
Neg logit contributions | |
uts | -0.050 |
cartridge | -0.049 |
ate | -0.047 |
ra | -0.046 |
ung | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
camel | +0.143 |
mo | +0.135 |
polar | +0.131 |
elephants | +0.129 |
vehicle | +0.129 |
Neg logit contributions | |
uts | -0.064 |
ate | -0.055 |
cartridge | -0.051 |
cutter | -0.051 |
ung | -0.048 |
Token | went |
Token ID | 1816 |
Feature activation | -6.00e-03 |
Pos logit contributions | |
uts | +0.004 |
cartridge | +0.004 |
ate | +0.004 |
ra | +0.004 |
rap | +0.003 |
Neg logit contributions | |
bus | -0.002 |
camel | -0.002 |
joy | -0.002 |
elephants | -0.002 |
vehicle | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
cartridge | +0.007 |
uts | +0.007 |
ate | +0.006 |
cutter | +0.006 |
rap | +0.006 |
Neg logit contributions | |
camel | -0.011 |
joy | -0.011 |
bus | -0.010 |
year | -0.010 |
mo | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
camel | +0.044 |
bus | +0.044 |
joy | +0.040 |
elephants | +0.040 |
vehicle | +0.039 |
Neg logit contributions | |
uts | -0.040 |
cartridge | -0.039 |
ate | -0.038 |
rap | -0.036 |
ra | -0.035 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
joy | +0.024 |
mo | +0.023 |
camel | +0.023 |
gru | +0.019 |
polar | +0.019 |
Neg logit contributions | |
uts | -0.030 |
ate | -0.030 |
cartridge | -0.029 |
ourselves | -0.028 |
connected | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
camel | +0.327 |
joy | +0.326 |
mo | +0.314 |
elephants | +0.312 |
gru | +0.309 |
Neg logit contributions | |
ate | -0.262 |
uts | -0.257 |
rap | -0.235 |
ra | -0.233 |
ung | -0.223 |
Token | go |
Token ID | 2188 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
uts | +0.037 |
cartridge | +0.034 |
ate | +0.034 |
ra | +0.032 |
rap | +0.032 |
Neg logit contributions | |
camel | -0.031 |
bus | -0.030 |
joy | -0.030 |
elephants | -0.027 |
vehicle | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
camel | +0.062 |
joy | +0.060 |
bus | +0.058 |
elephants | +0.056 |
mo | +0.055 |
Neg logit contributions | |
uts | -0.057 |
ate | -0.054 |
ra | -0.051 |
ung | -0.049 |
cartridge | -0.049 |
Token | round |
Token ID | 744 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
uts | +0.044 |
cartridge | +0.043 |
ate | +0.042 |
ra | +0.040 |
rap | +0.040 |
Neg logit contributions | |
camel | -0.022 |
bus | -0.021 |
joy | -0.020 |
elephants | -0.018 |
vehicle | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -7.27e-05 |
Pos logit contributions | |
camel | +0.078 |
bus | +0.075 |
joy | +0.073 |
vehicle | +0.068 |
elephants | +0.068 |
Neg logit contributions | |
uts | -0.084 |
cartridge | -0.079 |
ate | -0.078 |
ung | -0.073 |
ra | -0.073 |
Token | when |
Token ID | 618 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
uts | +0.000 |
cartridge | +0.000 |
ate | +0.000 |
rap | +0.000 |
ressing | +0.000 |
Neg logit contributions | |
bus | -0.000 |
camel | -0.000 |
joy | -0.000 |
vehicle | -0.000 |
desert | -0.000 |
Token | they |
Token ID | 484 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
uts | +0.125 |
cartridge | +0.123 |
ate | +0.114 |
rap | +0.111 |
ressing | +0.110 |
Neg logit contributions | |
camel | -0.109 |
bus | -0.108 |
joy | -0.098 |
elephants | -0.095 |
vehicle | -0.093 |
Token | got |
Token ID | 1392 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
camel | +0.012 |
bus | +0.012 |
elephants | +0.011 |
joy | +0.011 |
vehicle | +0.011 |
Neg logit contributions | |
uts | -0.014 |
cartridge | -0.013 |
ate | -0.013 |
ra | -0.013 |
ung | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
uts | +0.046 |
cartridge | +0.046 |
ate | +0.044 |
rap | +0.042 |
ra | +0.042 |
Neg logit contributions | |
bus | -0.035 |
camel | -0.034 |
joy | -0.032 |
vehicle | -0.030 |
elephants | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
camel | +0.018 |
bus | +0.017 |
joy | +0.016 |
mo | +0.016 |
year | +0.016 |
Neg logit contributions | |
ate | -0.016 |
cartridge | -0.016 |
uts | -0.016 |
rap | -0.015 |
ra | -0.015 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
joy | +0.029 |
camel | +0.028 |
mo | +0.026 |
inspection | +0.025 |
year | +0.024 |
Neg logit contributions | |
ate | -0.046 |
cartridge | -0.045 |
uts | -0.042 |
rap | -0.042 |
ra | -0.042 |
Token | - |
Token ID | 12 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
joy | +0.320 |
camel | +0.317 |
elephants | +0.311 |
gru | +0.305 |
mo | +0.299 |
Neg logit contributions | |
ate | -0.258 |
uts | -0.255 |
ra | -0.236 |
ung | -0.227 |
rap | -0.226 |
Token | go |
Token ID | 2188 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
uts | +0.037 |
ate | +0.033 |
cartridge | +0.033 |
ra | +0.031 |
rap | +0.030 |
Neg logit contributions | |
joy | -0.033 |
camel | -0.032 |
bus | -0.031 |
desert | -0.028 |
elephants | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
camel | +0.063 |
joy | +0.062 |
bus | +0.059 |
elephants | +0.057 |
desert | +0.055 |
Neg logit contributions | |
uts | -0.055 |
ate | -0.052 |
ra | -0.049 |
ung | -0.047 |
cartridge | -0.046 |
Token | round |
Token ID | 744 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
uts | +0.044 |
ate | +0.042 |
cartridge | +0.040 |
rap | +0.039 |
ra | +0.039 |
Neg logit contributions | |
camel | -0.024 |
joy | -0.023 |
bus | -0.022 |
elephants | -0.019 |
vehicle | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
camel | +0.074 |
joy | +0.071 |
bus | +0.065 |
mo | +0.064 |
elephants | +0.064 |
Neg logit contributions | |
uts | -0.084 |
ate | -0.079 |
cartridge | -0.076 |
ung | -0.074 |
ra | -0.073 |
Token | a |
Token ID | 257 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
camel | +0.026 |
mo | +0.025 |
joy | +0.024 |
vehicle | +0.023 |
hotel | +0.023 |
Neg logit contributions | |
uts | -0.022 |
connected | -0.021 |
ate | -0.019 |
tied | -0.019 |
cartridge | -0.019 |
Token | swing |
Token ID | 9628 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
cutter | +0.035 |
cartridge | +0.034 |
uts | +0.034 |
ra | +0.032 |
connected | +0.032 |
Neg logit contributions | |
mo | -0.029 |
joy | -0.027 |
camel | -0.025 |
Other | -0.025 |
est | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
joy | +0.195 |
camel | +0.192 |
polar | +0.172 |
mo | +0.171 |
desert | +0.161 |
Neg logit contributions | |
uts | -0.139 |
ate | -0.129 |
ung | -0.125 |
cutter | -0.123 |
ra | -0.120 |
Token | and |
Token ID | 290 |
Feature activation | -4.83e-04 |
Pos logit contributions | |
camel | +0.030 |
mo | +0.029 |
joy | +0.028 |
polar | +0.027 |
vehicle | +0.027 |
Neg logit contributions | |
uts | -0.017 |
ate | -0.016 |
connected | -0.015 |
cartridge | -0.015 |
ends | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
uts | +0.000 |
cartridge | +0.000 |
connected | +0.000 |
ate | +0.000 |
printed | +0.000 |
Neg logit contributions | |
camel | -0.001 |
joy | -0.001 |
mo | -0.001 |
bus | -0.001 |
vehicle | -0.001 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
cutter | +0.038 |
uts | +0.037 |
cartridge | +0.037 |
ra | +0.035 |
fold | +0.034 |
Neg logit contributions | |
mo | -0.027 |
joy | -0.024 |
enced | -0.023 |
camel | -0.023 |
est | -0.022 |
Token | - |
Token ID | 12 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
camel | +0.331 |
elephants | +0.328 |
mo | +0.325 |
joy | +0.325 |
ze | +0.308 |
Neg logit contributions | |
ate | -0.252 |
ra | -0.243 |
rap | -0.228 |
uts | -0.217 |
ung | -0.212 |
Token | go |
Token ID | 2188 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
uts | +0.033 |
ate | +0.028 |
ra | +0.028 |
cartridge | +0.027 |
ung | +0.026 |
Neg logit contributions | |
joy | -0.040 |
camel | -0.036 |
desert | -0.034 |
mo | -0.033 |
bus | -0.033 |
Token | - |
Token ID | 12 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
joy | +0.077 |
camel | +0.074 |
desert | +0.069 |
mo | +0.069 |
polar | +0.069 |
Neg logit contributions | |
uts | -0.043 |
ate | -0.040 |
ra | -0.040 |
ung | -0.036 |
uckle | -0.034 |
Token | round |
Token ID | 744 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
uts | +0.042 |
ate | +0.038 |
cartridge | +0.037 |
ra | +0.037 |
rap | +0.036 |
Neg logit contributions | |
camel | -0.025 |
joy | -0.025 |
bus | -0.023 |
vehicle | -0.021 |
elephants | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
camel | +0.084 |
joy | +0.081 |
bus | +0.077 |
mo | +0.074 |
vehicle | +0.073 |
Neg logit contributions | |
uts | -0.080 |
ate | -0.072 |
ung | -0.068 |
cartridge | -0.068 |
ra | -0.068 |
Token | aters |
Token ID | 8605 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
uts | +0.064 |
cartridge | +0.060 |
ate | +0.054 |
cutter | +0.053 |
connected | +0.053 |
Neg logit contributions | |
bus | -0.089 |
camel | -0.086 |
vehicle | -0.086 |
joy | -0.085 |
taxi | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
cartridge | +0.259 |
uts | +0.258 |
ate | +0.255 |
rap | +0.249 |
ra | +0.246 |
Neg logit contributions | |
bus | -0.147 |
camel | -0.137 |
vehicle | -0.122 |
taxi | -0.122 |
elephants | -0.117 |
Token | ran |
Token ID | 4966 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
bus | +0.002 |
camel | +0.002 |
joy | +0.002 |
elephants | +0.002 |
vehicle | +0.002 |
Neg logit contributions | |
uts | -0.003 |
cartridge | -0.003 |
ate | -0.003 |
ra | -0.003 |
rap | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
bus | +0.097 |
camel | +0.095 |
joy | +0.089 |
vehicle | +0.086 |
elephants | +0.085 |
Neg logit contributions | |
uts | -0.089 |
cartridge | -0.087 |
ate | -0.084 |
ra | -0.080 |
rap | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
camel | +0.017 |
bus | +0.016 |
joy | +0.016 |
year | +0.015 |
elephants | +0.015 |
Neg logit contributions | |
cartridge | -0.015 |
ate | -0.014 |
uts | -0.014 |
rap | -0.014 |
ra | -0.013 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
camel | +0.029 |
joy | +0.029 |
bus | +0.028 |
mo | +0.026 |
year | +0.026 |
Neg logit contributions | |
cartridge | -0.043 |
uts | -0.041 |
ate | -0.040 |
cutter | -0.039 |
ra | -0.038 |
Token | - |
Token ID | 12 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
joy | +0.328 |
camel | +0.322 |
elephants | +0.313 |
gru | +0.298 |
mo | +0.298 |
Neg logit contributions | |
uts | -0.254 |
ate | -0.253 |
ra | -0.241 |
rap | -0.235 |
cartridge | -0.234 |
Token | go |
Token ID | 2188 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
uts | +0.035 |
cartridge | +0.032 |
ate | +0.031 |
ra | +0.030 |
ung | +0.029 |
Neg logit contributions | |
joy | -0.034 |
camel | -0.034 |
bus | -0.033 |
elephants | -0.030 |
merry | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
camel | +0.057 |
bus | +0.057 |
joy | +0.055 |
elephants | +0.051 |
vehicle | +0.050 |
Neg logit contributions | |
uts | -0.063 |
cartridge | -0.060 |
ate | -0.059 |
ra | -0.057 |
ung | -0.055 |
Token | round |
Token ID | 744 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
uts | +0.044 |
cartridge | +0.041 |
ate | +0.041 |
rap | +0.039 |
ra | +0.039 |
Neg logit contributions | |
camel | -0.023 |
joy | -0.022 |
bus | -0.021 |
merry | -0.019 |
elephants | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
camel | +0.072 |
bus | +0.071 |
joy | +0.068 |
vehicle | +0.063 |
elephants | +0.063 |
Neg logit contributions | |
uts | -0.086 |
cartridge | -0.083 |
ate | -0.080 |
ra | -0.076 |
ung | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
uts | +0.050 |
cartridge | +0.045 |
ate | +0.043 |
ung | +0.043 |
cutter | +0.043 |
Neg logit contributions | |
bus | -0.046 |
camel | -0.045 |
desert | -0.042 |
elephants | -0.041 |
joy | -0.040 |
Token | " |
Token ID | 366 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
camel | +0.017 |
bus | +0.017 |
joy | +0.015 |
desert | +0.015 |
vehicle | +0.015 |
Neg logit contributions | |
uts | -0.019 |
cartridge | -0.018 |
ate | -0.017 |
cutter | -0.016 |
ra | -0.016 |
Token | It |
Token ID | 1026 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
bus | +0.010 |
camel | +0.009 |
joy | +0.009 |
elephants | +0.009 |
vehicle | +0.009 |
Neg logit contributions | |
uts | -0.008 |
cartridge | -0.008 |
ate | -0.008 |
rap | -0.007 |
ra | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
uts | +0.042 |
cartridge | +0.041 |
ate | +0.037 |
rap | +0.037 |
ung | +0.037 |
Neg logit contributions | |
bus | -0.029 |
camel | -0.027 |
elephants | -0.025 |
vehicle | -0.025 |
hello | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
uts | +0.088 |
cartridge | +0.084 |
ressing | +0.076 |
ung | +0.076 |
ate | +0.076 |
Neg logit contributions | |
bus | -0.058 |
camel | -0.055 |
elephants | -0.051 |
vehicle | -0.050 |
joy | -0.049 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
cartridge | +0.040 |
uts | +0.039 |
ra | +0.038 |
ate | +0.038 |
cutter | +0.038 |
Neg logit contributions | |
camel | -0.038 |
bus | -0.037 |
joy | -0.036 |
mo | -0.034 |
elephants | -0.033 |
Token | - |
Token ID | 12 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
camel | +0.353 |
elephants | +0.351 |
joy | +0.338 |
mo | +0.337 |
ze | +0.332 |
Neg logit contributions | |
ate | -0.235 |
ra | -0.226 |
rap | -0.218 |
uts | -0.216 |
cartridge | -0.197 |
Token | go |
Token ID | 2188 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
uts | +0.036 |
cartridge | +0.035 |
ate | +0.033 |
ra | +0.032 |
rap | +0.032 |
Neg logit contributions | |
bus | -0.030 |
camel | -0.030 |
joy | -0.029 |
vehicle | -0.027 |
elephants | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
camel | +0.057 |
bus | +0.056 |
joy | +0.054 |
elephants | +0.051 |
desert | +0.050 |
Neg logit contributions | |
uts | -0.059 |
ate | -0.056 |
cartridge | -0.056 |
ra | -0.056 |
rap | -0.053 |
Token | round |
Token ID | 744 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
uts | +0.038 |
cartridge | +0.038 |
ate | +0.037 |
ra | +0.035 |
rap | +0.035 |
Neg logit contributions | |
bus | -0.027 |
camel | -0.026 |
joy | -0.024 |
elephants | -0.023 |
vehicle | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-04 |
Pos logit contributions | |
camel | +0.078 |
bus | +0.076 |
joy | +0.074 |
vehicle | +0.068 |
elephants | +0.068 |
Neg logit contributions | |
uts | -0.081 |
cartridge | -0.077 |
ate | -0.075 |
ra | -0.072 |
rap | -0.071 |
Token | continued |
Token ID | 3767 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
joy | +0.041 |
bus | +0.040 |
camel | +0.040 |
merry | +0.036 |
hi | +0.035 |
Neg logit contributions | |
cartridge | -0.086 |
ate | -0.085 |
uts | -0.085 |
ra | -0.085 |
cutter | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -3.69e-04 |
Pos logit contributions | |
uts | +0.076 |
cartridge | +0.074 |
ate | +0.069 |
cutter | +0.066 |
connected | +0.065 |
Neg logit contributions | |
camel | -0.100 |
bus | -0.096 |
joy | -0.091 |
elephants | -0.089 |
mo | -0.088 |
Token | get |
Token ID | 651 |
Feature activation | -9.99e-03 |
Pos logit contributions | |
uts | +0.001 |
cartridge | +0.001 |
ate | +0.001 |
ra | +0.001 |
rap | +0.001 |
Neg logit contributions | |
camel | -0.001 |
bus | -0.001 |
joy | -0.001 |
elephants | -0.000 |
vehicle | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | -8.24e-03 |
Pos logit contributions | |
uts | +0.016 |
cartridge | +0.016 |
ate | +0.015 |
ra | +0.015 |
rap | +0.014 |
Neg logit contributions | |
bus | -0.014 |
camel | -0.014 |
joy | -0.013 |
vehicle | -0.013 |
elephants | -0.013 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
uts | +0.012 |
cartridge | +0.012 |
ate | +0.012 |
ra | +0.012 |
cutter | +0.011 |
Neg logit contributions | |
camel | -0.012 |
bus | -0.012 |
joy | -0.011 |
elephants | -0.011 |
mo | -0.010 |
Token | uts |
Token ID | 5500 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
cartridge | +0.019 |
ate | +0.015 |
cutter | +0.011 |
rap | +0.011 |
matters | +0.010 |
Neg logit contributions | |
bus | -0.096 |
camel | -0.091 |
year | -0.089 |
taxi | -0.089 |
joy | -0.089 |
Token | at |
Token ID | 379 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
uts | +0.336 |
cartridge | +0.330 |
ate | +0.317 |
ra | +0.303 |
rap | +0.300 |
Neg logit contributions | |
bus | -0.272 |
camel | -0.268 |
joy | -0.249 |
elephants | -0.237 |
vehicle | -0.236 |
Token | the |
Token ID | 262 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
uts | +0.075 |
cartridge | +0.073 |
ate | +0.071 |
ra | +0.067 |
rap | +0.067 |
Neg logit contributions | |
bus | -0.066 |
camel | -0.065 |
joy | -0.061 |
elephants | -0.058 |
vehicle | -0.058 |
Token | same |
Token ID | 976 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
camel | +0.023 |
bus | +0.022 |
joy | +0.021 |
mo | +0.019 |
elephants | +0.019 |
Neg logit contributions | |
cartridge | -0.034 |
uts | -0.034 |
ate | -0.034 |
ra | -0.032 |
rap | -0.032 |
Token | bar |
Token ID | 2318 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
camel | +0.071 |
bus | +0.067 |
mo | +0.064 |
elephants | +0.064 |
hi | +0.063 |
Neg logit contributions | |
ate | -0.061 |
cartridge | -0.059 |
ra | -0.056 |
rap | -0.056 |
uts | -0.055 |
Token | ber |
Token ID | 527 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
uts | +0.033 |
cartridge | +0.030 |
ate | +0.029 |
ra | +0.029 |
cutter | +0.028 |
Neg logit contributions | |
camel | -0.044 |
bus | -0.044 |
joy | -0.042 |
elephants | -0.041 |
vehicle | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-03 |
Pos logit contributions | |
camel | +0.073 |
bus | +0.072 |
joy | +0.068 |
merry | +0.065 |
elephants | +0.064 |
Neg logit contributions | |
uts | -0.073 |
cartridge | -0.066 |
ate | -0.063 |
ung | -0.061 |
cutter | -0.060 |
Token | They |
Token ID | 1119 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
bus | +0.004 |
camel | +0.004 |
joy | +0.003 |
elephants | +0.003 |
vehicle | +0.003 |
Neg logit contributions | |
uts | -0.005 |
cartridge | -0.005 |
ate | -0.005 |
ra | -0.005 |
rap | -0.005 |
Token | liked |
Token ID | 8288 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
uts | +0.011 |
cartridge | +0.011 |
ate | +0.010 |
ra | +0.010 |
rap | +0.010 |
Neg logit contributions | |
bus | -0.010 |
camel | -0.010 |
joy | -0.009 |
elephants | -0.009 |
vehicle | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
uts | +0.013 |
cartridge | +0.013 |
ate | +0.012 |
ra | +0.011 |
rap | +0.011 |
Neg logit contributions | |
bus | -0.013 |
camel | -0.013 |
joy | -0.012 |
elephants | -0.012 |
vehicle | -0.012 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
uts | +0.059 |
cartridge | +0.057 |
ate | +0.055 |
ra | +0.052 |
rap | +0.052 |
Neg logit contributions | |
bus | -0.057 |
camel | -0.056 |
joy | -0.052 |
elephants | -0.050 |
vehicle | -0.050 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
cartridge | +0.013 |
ate | +0.009 |
rap | +0.006 |
cutter | +0.006 |
ra | +0.005 |
Neg logit contributions | |
bus | -0.093 |
camel | -0.091 |
year | -0.088 |
joy | -0.088 |
merry | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +4.58e-03 |
Pos logit contributions | |
uts | +0.319 |
cartridge | +0.310 |
ate | +0.297 |
ra | +0.281 |
ung | +0.279 |
Neg logit contributions | |
bus | -0.275 |
camel | -0.273 |
joy | -0.254 |
vehicle | -0.240 |
elephants | -0.240 |
Token | They |
Token ID | 1119 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
bus | +0.007 |
camel | +0.007 |
joy | +0.006 |
elephants | +0.006 |
vehicle | +0.006 |
Neg logit contributions | |
uts | -0.007 |
cartridge | -0.007 |
ate | -0.007 |
ra | -0.006 |
rap | -0.006 |
Token | think |
Token ID | 892 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
uts | +0.005 |
cartridge | +0.005 |
ate | +0.004 |
ra | +0.004 |
cutter | +0.004 |
Neg logit contributions | |
camel | -0.004 |
bus | -0.004 |
joy | -0.004 |
vehicle | -0.004 |
elephants | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
camel | +0.040 |
bus | +0.040 |
joy | +0.039 |
vehicle | +0.036 |
elephants | +0.036 |
Neg logit contributions | |
uts | -0.035 |
cartridge | -0.032 |
ate | -0.031 |
ra | -0.029 |
cutter | -0.029 |
Token | bar |
Token ID | 2318 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
camel | +0.033 |
joy | +0.033 |
mo | +0.032 |
inspection | +0.030 |
bus | +0.030 |
Neg logit contributions | |
cartridge | -0.037 |
uts | -0.036 |
ate | -0.036 |
ra | -0.035 |
cutter | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
uts | +0.042 |
ate | +0.040 |
cartridge | +0.039 |
rap | +0.037 |
ra | +0.036 |
Neg logit contributions | |
bus | -0.049 |
camel | -0.048 |
joy | -0.045 |
elephants | -0.044 |
vehicle | -0.044 |
Token | " |
Token ID | 1 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
cartridge | +0.044 |
uts | +0.044 |
ate | +0.041 |
ra | +0.039 |
ung | +0.039 |
Neg logit contributions | |
bus | -0.040 |
camel | -0.039 |
joy | -0.036 |
year | -0.036 |
taxi | -0.035 |
Token | Those |
Token ID | 9627 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
uts | +0.154 |
cartridge | +0.145 |
rap | +0.141 |
ate | +0.141 |
ung | +0.138 |
Neg logit contributions | |
bus | -0.124 |
camel | -0.121 |
joy | -0.112 |
elephants | -0.111 |
year | -0.108 |
Token | are |
Token ID | 389 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
camel | +0.066 |
joy | +0.066 |
bus | +0.065 |
mo | +0.059 |
year | +0.057 |
Neg logit contributions | |
uts | -0.064 |
cartridge | -0.061 |
ate | -0.059 |
ra | -0.056 |
matters | -0.055 |
Token | don |
Token ID | 836 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
bus | +0.051 |
camel | +0.050 |
elephants | +0.046 |
gir | +0.044 |
vehicle | +0.043 |
Neg logit contributions | |
uts | -0.064 |
cartridge | -0.063 |
ate | -0.060 |
ung | -0.058 |
ra | -0.057 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
cartridge | +0.113 |
ate | +0.108 |
ra | +0.106 |
ressing | +0.101 |
check | +0.100 |
Neg logit contributions | |
year | -0.127 |
bus | -0.125 |
taxi | -0.120 |
vehicle | -0.108 |
parking | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-04 |
Pos logit contributions | |
cartridge | +0.343 |
uts | +0.343 |
ate | +0.330 |
ra | +0.317 |
rap | +0.315 |
Neg logit contributions | |
bus | -0.243 |
camel | -0.235 |
joy | -0.209 |
elephants | -0.207 |
vehicle | -0.206 |
Token | They |
Token ID | 1119 |
Feature activation | +6.47e-04 |
Pos logit contributions | |
bus | +0.000 |
camel | +0.000 |
joy | +0.000 |
vehicle | +0.000 |
elephants | +0.000 |
Neg logit contributions | |
uts | -0.000 |
cartridge | -0.000 |
ate | -0.000 |
ra | -0.000 |
rap | -0.000 |
Token | are |
Token ID | 389 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
bus | +0.001 |
camel | +0.001 |
elephants | +0.001 |
vehicle | +0.001 |
taxi | +0.001 |
Neg logit contributions | |
uts | -0.001 |
cartridge | -0.001 |
ate | -0.001 |
rap | -0.001 |
ung | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
bus | +0.049 |
camel | +0.048 |
elephants | +0.046 |
hipp | +0.042 |
gir | +0.042 |
Neg logit contributions | |
uts | -0.072 |
cartridge | -0.068 |
ung | -0.066 |
ressing | -0.066 |
ate | -0.066 |
Token | tasty |
Token ID | 25103 |
Feature activation | +6.25e-04 |
Pos logit contributions | |
bus | +0.032 |
camel | +0.032 |
joy | +0.029 |
elephants | +0.028 |
vehicle | +0.028 |
Neg logit contributions | |
uts | -0.041 |
cartridge | -0.041 |
ate | -0.039 |
ra | -0.037 |
rap | -0.037 |
Token | salon |
Token ID | 46608 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
uts | +0.039 |
cartridge | +0.037 |
ate | +0.036 |
cutter | +0.035 |
ra | +0.035 |
Neg logit contributions | |
camel | -0.035 |
joy | -0.033 |
gru | -0.032 |
polar | -0.031 |
bus | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
camel | +0.153 |
bus | +0.141 |
joy | +0.139 |
elephants | +0.135 |
vehicle | +0.135 |
Neg logit contributions | |
uts | -0.127 |
cartridge | -0.116 |
ate | -0.116 |
rap | -0.106 |
ra | -0.103 |
Token | getting |
Token ID | 1972 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
uts | +0.010 |
cartridge | +0.010 |
ate | +0.009 |
ra | +0.009 |
rap | +0.009 |
Neg logit contributions | |
camel | -0.011 |
bus | -0.011 |
joy | -0.010 |
vehicle | -0.010 |
elephants | -0.010 |
Token | different |
Token ID | 1180 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
uts | +0.028 |
cartridge | +0.027 |
ate | +0.026 |
ra | +0.025 |
rap | +0.025 |
Neg logit contributions | |
bus | -0.028 |
camel | -0.027 |
joy | -0.026 |
elephants | -0.024 |
vehicle | -0.024 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
uts | +0.014 |
ate | +0.014 |
cartridge | +0.013 |
ra | +0.013 |
rap | +0.012 |
Neg logit contributions | |
camel | -0.018 |
bus | -0.017 |
joy | -0.016 |
vehicle | -0.016 |
elephants | -0.016 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
cartridge | +0.016 |
ate | +0.012 |
matters | +0.010 |
rap | +0.009 |
connected | +0.008 |
Neg logit contributions | |
bus | -0.095 |
camel | -0.090 |
joy | -0.089 |
year | -0.088 |
merry | -0.088 |
Token | with |
Token ID | 351 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
uts | +0.337 |
cartridge | +0.333 |
ate | +0.323 |
ra | +0.311 |
rap | +0.308 |
Neg logit contributions | |
bus | -0.248 |
camel | -0.242 |
joy | -0.222 |
elephants | -0.213 |
vehicle | -0.212 |
Token | colorful |
Token ID | 20239 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
ra | +0.002 |
rap | +0.001 |
Neg logit contributions | |
bus | -0.002 |
camel | -0.002 |
joy | -0.002 |
elephants | -0.002 |
vehicle | -0.002 |
Token | clips |
Token ID | 19166 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
uts | +0.096 |
cartridge | +0.093 |
ate | +0.088 |
ra | +0.086 |
cutter | +0.082 |
Neg logit contributions | |
camel | -0.110 |
bus | -0.109 |
joy | -0.102 |
vehicle | -0.099 |
elephants | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -7.68e-03 |
Pos logit contributions | |
cartridge | +0.160 |
ate | +0.158 |
uts | +0.157 |
rap | +0.154 |
ra | +0.149 |
Neg logit contributions | |
bus | -0.099 |
camel | -0.093 |
joy | -0.085 |
elephants | -0.082 |
taxi | -0.080 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
uts | +0.012 |
cartridge | +0.012 |
ate | +0.011 |
rap | +0.010 |
ra | +0.010 |
Neg logit contributions | |
bus | -0.012 |
camel | -0.012 |
joy | -0.011 |
elephants | -0.010 |
vehicle | -0.010 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
camel | +0.012 |
bus | +0.011 |
year | +0.010 |
joy | +0.010 |
merry | +0.010 |
Neg logit contributions | |
uts | -0.014 |
cartridge | -0.014 |
ate | -0.013 |
connected | -0.013 |
ra | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -3.60e-04 |
Pos logit contributions | |
bus | +0.041 |
camel | +0.041 |
joy | +0.039 |
elephants | +0.037 |
vehicle | +0.037 |
Neg logit contributions | |
uts | -0.029 |
cartridge | -0.029 |
ate | -0.028 |
ra | -0.026 |
rap | -0.025 |
Token | some |
Token ID | 617 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
uts | +0.000 |
cartridge | +0.000 |
ate | +0.000 |
ra | +0.000 |
rap | +0.000 |
Neg logit contributions | |
camel | -0.001 |
bus | -0.001 |
joy | -0.001 |
mo | -0.001 |
year | -0.001 |
Token | coc |
Token ID | 8954 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
camel | +0.048 |
joy | +0.047 |
bus | +0.046 |
mo | +0.043 |
vehicle | +0.041 |
Neg logit contributions | |
uts | -0.064 |
cutter | -0.061 |
cartridge | -0.060 |
ate | -0.060 |
ra | -0.058 |
Token | on |
Token ID | 261 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
cartridge | +0.144 |
ra | +0.136 |
ate | +0.132 |
uts | +0.128 |
check | +0.125 |
Neg logit contributions | |
camel | -0.206 |
bus | -0.205 |
year | -0.198 |
joy | -0.189 |
mo | -0.186 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ate | +0.122 |
cartridge | +0.121 |
rap | +0.114 |
ra | +0.110 |
uts | +0.108 |
Neg logit contributions | |
bus | -0.091 |
camel | -0.086 |
year | -0.077 |
gir | -0.075 |
joy | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -5.34e-03 |
Pos logit contributions | |
uts | +0.331 |
cartridge | +0.328 |
ate | +0.316 |
ra | +0.303 |
rap | +0.300 |
Neg logit contributions | |
bus | -0.253 |
camel | -0.247 |
joy | -0.229 |
vehicle | -0.218 |
elephants | -0.218 |
Token | Max |
Token ID | 5436 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
cartridge | +0.010 |
uts | +0.010 |
ra | +0.010 |
ate | +0.010 |
rap | +0.009 |
Neg logit contributions | |
bus | -0.006 |
joy | -0.006 |
camel | -0.006 |
vehicle | -0.005 |
elephants | -0.005 |
Token | continued |
Token ID | 3767 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
cartridge | +0.106 |
uts | +0.106 |
ate | +0.101 |
rap | +0.098 |
ra | +0.097 |
Neg logit contributions | |
bus | -0.063 |
camel | -0.062 |
joy | -0.054 |
elephants | -0.053 |
gir | -0.052 |
Token | on |
Token ID | 319 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
uts | +0.103 |
cartridge | +0.101 |
ate | +0.096 |
ra | +0.092 |
rap | +0.091 |
Neg logit contributions | |
bus | -0.101 |
camel | -0.100 |
joy | -0.093 |
elephants | -0.089 |
vehicle | -0.089 |
Token | his |
Token ID | 465 |
Feature activation | -4.75e-03 |
Pos logit contributions | |
bus | +0.027 |
camel | +0.027 |
joy | +0.024 |
elephants | +0.023 |
vehicle | +0.023 |
Neg logit contributions | |
uts | -0.035 |
cartridge | -0.034 |
ate | -0.033 |
ra | -0.032 |
rap | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
uts | +0.012 |
ate | +0.011 |
cartridge | +0.011 |
rap | +0.010 |
issors | +0.010 |
Neg logit contributions | |
camel | -0.009 |
bus | -0.008 |
joy | -0.007 |
elephants | -0.007 |
merry | -0.007 |
Token | didn |
Token ID | 1422 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
camel | +0.006 |
bus | +0.006 |
joy | +0.006 |
elephants | +0.005 |
vehicle | +0.005 |
Neg logit contributions | |
cartridge | -0.006 |
uts | -0.006 |
ate | -0.006 |
ra | -0.006 |
rap | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
cartridge | +0.145 |
ra | +0.132 |
ressing | +0.132 |
cutter | +0.128 |
ate | +0.126 |
Neg logit contributions | |
bus | -0.124 |
taxi | -0.113 |
year | -0.112 |
vehicle | -0.105 |
parking | -0.101 |
Token | like |
Token ID | 588 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
uts | +0.098 |
cartridge | +0.095 |
ate | +0.092 |
ra | +0.088 |
rap | +0.087 |
Neg logit contributions | |
bus | -0.088 |
camel | -0.085 |
year | -0.076 |
vehicle | -0.076 |
joy | -0.076 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
uts | +0.039 |
cartridge | +0.039 |
ate | +0.037 |
ra | +0.035 |
rap | +0.035 |
Neg logit contributions | |
bus | -0.038 |
camel | -0.038 |
joy | -0.035 |
elephants | -0.034 |
vehicle | -0.034 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
cartridge | +0.018 |
ate | +0.014 |
cutter | +0.011 |
matters | +0.011 |
connected | +0.010 |
Neg logit contributions | |
bus | -0.093 |
joy | -0.088 |
camel | -0.086 |
parking | -0.086 |
year | -0.086 |
Token | because |
Token ID | 780 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
uts | +0.359 |
cartridge | +0.359 |
ate | +0.350 |
ra | +0.336 |
rap | +0.333 |
Neg logit contributions | |
bus | -0.223 |
camel | -0.214 |
joy | -0.195 |
vehicle | -0.187 |
elephants | -0.185 |
Token | they |
Token ID | 484 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
uts | +0.076 |
cartridge | +0.074 |
ate | +0.071 |
ra | +0.068 |
rap | +0.067 |
Neg logit contributions | |
bus | -0.064 |
camel | -0.064 |
joy | -0.060 |
elephants | -0.056 |
vehicle | -0.056 |
Token | made |
Token ID | 925 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
bus | +0.003 |
camel | +0.003 |
vehicle | +0.003 |
joy | +0.003 |
year | +0.003 |
Neg logit contributions | |
uts | -0.005 |
cartridge | -0.005 |
ate | -0.005 |
rap | -0.005 |
ra | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
uts | +0.021 |
cartridge | +0.021 |
ate | +0.020 |
ra | +0.019 |
rap | +0.019 |
Neg logit contributions | |
bus | -0.019 |
camel | -0.019 |
joy | -0.017 |
vehicle | -0.017 |
elephants | -0.017 |
Token | feel |
Token ID | 1254 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
uts | +0.041 |
cartridge | +0.038 |
ate | +0.038 |
ra | +0.037 |
ung | +0.036 |
Neg logit contributions | |
camel | -0.030 |
joy | -0.029 |
bus | -0.029 |
elephants | -0.027 |
vehicle | -0.025 |
Token | who |
Token ID | 508 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
camel | +0.014 |
bus | +0.014 |
joy | +0.014 |
mo | +0.012 |
vehicle | +0.012 |
Neg logit contributions | |
uts | -0.021 |
cartridge | -0.021 |
ate | -0.019 |
ra | -0.019 |
cutter | -0.018 |
Token | always |
Token ID | 1464 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
bus | +0.161 |
camel | +0.147 |
year | +0.137 |
vehicle | +0.133 |
taxi | +0.132 |
Neg logit contributions | |
uts | -0.241 |
cartridge | -0.236 |
ung | -0.222 |
ate | -0.219 |
ressing | -0.218 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
uts | +0.030 |
cartridge | +0.030 |
ate | +0.029 |
ra | +0.027 |
rap | +0.027 |
Neg logit contributions | |
bus | -0.030 |
camel | -0.030 |
joy | -0.028 |
elephants | -0.026 |
vehicle | -0.026 |
Token | good |
Token ID | 922 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
uts | +0.032 |
cartridge | +0.031 |
ate | +0.030 |
ra | +0.029 |
rap | +0.028 |
Neg logit contributions | |
bus | -0.042 |
camel | -0.041 |
joy | -0.039 |
elephants | -0.037 |
vehicle | -0.037 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
uts | +0.045 |
cartridge | +0.044 |
ate | +0.042 |
ra | +0.041 |
ung | +0.039 |
Neg logit contributions | |
bus | -0.061 |
camel | -0.061 |
joy | -0.057 |
vehicle | -0.056 |
elephants | -0.055 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
cartridge | +0.020 |
ate | +0.012 |
rap | +0.011 |
connected | +0.011 |
cutter | +0.010 |
Neg logit contributions | |
bus | -0.093 |
camel | -0.092 |
joy | -0.088 |
year | -0.086 |
taxi | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
cartridge | +0.335 |
uts | +0.334 |
ate | +0.322 |
ra | +0.312 |
rap | +0.309 |
Neg logit contributions | |
bus | -0.242 |
camel | -0.237 |
joy | -0.215 |
vehicle | -0.206 |
elephants | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
ung | +0.001 |
rap | +0.001 |
Neg logit contributions | |
camel | -0.002 |
bus | -0.002 |
joy | -0.002 |
vehicle | -0.002 |
elephants | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
uts | +0.030 |
ate | +0.028 |
cartridge | +0.027 |
rap | +0.026 |
ung | +0.025 |
Neg logit contributions | |
bus | -0.038 |
camel | -0.038 |
joy | -0.036 |
elephants | -0.035 |
vehicle | -0.034 |
Token | As |
Token ID | 1722 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
uts | +0.031 |
cartridge | +0.030 |
ate | +0.029 |
ra | +0.027 |
rap | +0.027 |
Neg logit contributions | |
bus | -0.037 |
camel | -0.037 |
joy | -0.035 |
vehicle | -0.033 |
elephants | -0.033 |
Token | they |
Token ID | 484 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
uts | +0.022 |
cartridge | +0.022 |
ate | +0.021 |
ra | +0.020 |
rap | +0.020 |
Neg logit contributions | |
bus | -0.026 |
camel | -0.026 |
joy | -0.024 |
elephants | -0.023 |
vehicle | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
bus | +0.063 |
camel | +0.060 |
joy | +0.055 |
taxi | +0.053 |
elephants | +0.053 |
Neg logit contributions | |
uts | -0.076 |
cartridge | -0.076 |
ate | -0.073 |
ra | -0.071 |
rap | -0.070 |
Token | pictures |
Token ID | 5986 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
bus | +0.007 |
camel | +0.007 |
joy | +0.007 |
vehicle | +0.007 |
elephants | +0.006 |
Neg logit contributions | |
uts | -0.008 |
cartridge | -0.008 |
ate | -0.007 |
ra | -0.007 |
rap | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
cartridge | +0.087 |
uts | +0.087 |
ate | +0.086 |
ra | +0.084 |
rap | +0.083 |
Neg logit contributions | |
bus | -0.051 |
camel | -0.046 |
elephants | -0.042 |
taxi | -0.041 |
joy | -0.041 |
Token | different |
Token ID | 1180 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
camel | +0.029 |
bus | +0.028 |
joy | +0.027 |
mo | +0.026 |
vehicle | +0.026 |
Neg logit contributions | |
uts | -0.026 |
cartridge | -0.025 |
ate | -0.025 |
ra | -0.023 |
rap | -0.023 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
uts | +0.005 |
ate | +0.005 |
cartridge | +0.005 |
ra | +0.004 |
rap | +0.004 |
Neg logit contributions | |
camel | -0.007 |
bus | -0.007 |
joy | -0.006 |
vehicle | -0.006 |
taxi | -0.006 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
cartridge | +0.016 |
ate | +0.010 |
matters | +0.009 |
connected | +0.009 |
rap | +0.008 |
Neg logit contributions | |
bus | -0.084 |
camel | -0.080 |
joy | -0.078 |
elephants | -0.077 |
year | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
cartridge | +0.367 |
ate | +0.357 |
uts | +0.356 |
ra | +0.350 |
rap | +0.348 |
Neg logit contributions | |
bus | -0.203 |
camel | -0.192 |
elephants | -0.168 |
joy | -0.166 |
vehicle | -0.163 |
Token | She |
Token ID | 1375 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
camel | +0.006 |
bus | +0.006 |
vehicle | +0.005 |
joy | +0.005 |
merry | +0.005 |
Neg logit contributions | |
uts | -0.007 |
cartridge | -0.007 |
ate | -0.007 |
ung | -0.006 |
cutter | -0.006 |
Token | asks |
Token ID | 7893 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
bus | +0.012 |
camel | +0.011 |
joy | +0.010 |
elephants | +0.010 |
merry | +0.010 |
Neg logit contributions | |
uts | -0.014 |
cartridge | -0.014 |
ate | -0.013 |
ung | -0.013 |
rap | -0.013 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.28e-03 |
Pos logit contributions | |
rap | +0.027 |
ate | +0.026 |
uts | +0.026 |
cartridge | +0.025 |
cutter | +0.024 |
Neg logit contributions | |
camel | -0.055 |
bus | -0.054 |
merry | -0.052 |
vehicle | -0.050 |
desert | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
uts | +0.007 |
cartridge | +0.007 |
ate | +0.006 |
rap | +0.006 |
ra | +0.006 |
Neg logit contributions | |
bus | -0.006 |
camel | -0.006 |
joy | -0.006 |
vehicle | -0.006 |
merry | -0.006 |
Token | lot |
Token ID | 1256 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
cartridge | +0.049 |
cutter | +0.049 |
uts | +0.045 |
ate | +0.044 |
ra | +0.044 |
Neg logit contributions | |
mo | -0.033 |
joy | -0.032 |
camel | -0.031 |
inspection | -0.029 |
elephants | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
bus | +0.025 |
camel | +0.025 |
joy | +0.022 |
elephants | +0.021 |
vehicle | +0.021 |
Neg logit contributions | |
uts | -0.050 |
cartridge | -0.049 |
ate | -0.047 |
ra | -0.046 |
rap | -0.045 |
Token | people |
Token ID | 661 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
camel | +0.025 |
joy | +0.023 |
bus | +0.023 |
mo | +0.023 |
elephants | +0.021 |
Neg logit contributions | |
ate | -0.023 |
cartridge | -0.022 |
uts | -0.022 |
matters | -0.022 |
ra | -0.021 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
camel | +0.025 |
bus | +0.024 |
joy | +0.024 |
merry | +0.022 |
vehicle | +0.022 |
Neg logit contributions | |
uts | -0.031 |
cartridge | -0.030 |
ate | -0.030 |
ra | -0.028 |
connected | -0.028 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
uts | +0.021 |
cartridge | +0.021 |
ate | +0.020 |
ra | +0.019 |
rap | +0.018 |
Neg logit contributions | |
camel | -0.026 |
bus | -0.026 |
joy | -0.024 |
vehicle | -0.023 |
elephants | -0.023 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
cartridge | +0.014 |
ate | +0.009 |
rap | +0.007 |
ra | +0.007 |
cutter | +0.006 |
Neg logit contributions | |
bus | -0.091 |
camel | -0.088 |
year | -0.085 |
joy | -0.085 |
elephants | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
uts | +0.301 |
cartridge | +0.292 |
ate | +0.281 |
ra | +0.266 |
rap | +0.264 |
Neg logit contributions | |
bus | -0.267 |
camel | -0.264 |
joy | -0.247 |
elephants | -0.234 |
vehicle | -0.234 |
Token | The |
Token ID | 383 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
cutter | +0.002 |
ra | +0.002 |
Neg logit contributions | |
camel | -0.002 |
bus | -0.002 |
joy | -0.002 |
merry | -0.002 |
mo | -0.002 |
Token | bar |
Token ID | 2318 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
camel | +0.040 |
bus | +0.038 |
joy | +0.038 |
mo | +0.036 |
elephants | +0.035 |
Neg logit contributions | |
uts | -0.048 |
cartridge | -0.047 |
ate | -0.047 |
ra | -0.045 |
cutter | -0.043 |
Token | ber |
Token ID | 527 |
Feature activation | -3.36e-04 |
Pos logit contributions | |
uts | +0.039 |
cartridge | +0.036 |
ate | +0.036 |
ra | +0.034 |
cutter | +0.033 |
Neg logit contributions | |
bus | -0.054 |
camel | -0.054 |
joy | -0.053 |
elephants | -0.049 |
vehicle | -0.049 |
Token | was |
Token ID | 373 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
uts | +0.001 |
cartridge | +0.000 |
ate | +0.000 |
ra | +0.000 |
cutter | +0.000 |
Neg logit contributions | |
camel | -0.000 |
bus | -0.000 |
joy | -0.000 |
vehicle | -0.000 |
elephants | -0.000 |
Token | bar |
Token ID | 2318 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
ra | +0.027 |
ate | +0.026 |
uts | +0.026 |
cutter | +0.026 |
cartridge | +0.026 |
Neg logit contributions | |
camel | -0.031 |
elephants | -0.029 |
bus | -0.028 |
mo | -0.028 |
hi | -0.027 |
Token | ber |
Token ID | 527 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
uts | +0.028 |
ate | +0.025 |
ra | +0.024 |
cartridge | +0.023 |
cutter | +0.023 |
Neg logit contributions | |
camel | -0.046 |
bus | -0.045 |
elephants | -0.044 |
joy | -0.043 |
hi | -0.043 |
Token | for |
Token ID | 329 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
camel | +0.004 |
bus | +0.004 |
joy | +0.004 |
merry | +0.004 |
elephants | +0.004 |
Neg logit contributions | |
cartridge | -0.004 |
uts | -0.004 |
ate | -0.004 |
ra | -0.004 |
cutter | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | +3.35e-03 |
Pos logit contributions | |
uts | +0.028 |
cartridge | +0.028 |
ate | +0.027 |
ra | +0.026 |
rap | +0.025 |
Neg logit contributions | |
camel | -0.029 |
bus | -0.029 |
joy | -0.027 |
vehicle | -0.026 |
elephants | -0.025 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
camel | +0.005 |
bus | +0.005 |
joy | +0.004 |
mo | +0.004 |
elephants | +0.004 |
Neg logit contributions | |
uts | -0.005 |
ra | -0.005 |
cartridge | -0.005 |
ate | -0.005 |
cutter | -0.005 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
uts | +0.009 |
cartridge | +0.009 |
ate | +0.007 |
ra | +0.005 |
rap | +0.004 |
Neg logit contributions | |
bus | -0.085 |
camel | -0.084 |
joy | -0.081 |
vehicle | -0.079 |
elephants | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
uts | +0.286 |
cartridge | +0.269 |
ate | +0.252 |
ra | +0.238 |
cutter | +0.238 |
Neg logit contributions | |
camel | -0.284 |
bus | -0.282 |
joy | -0.263 |
elephants | -0.255 |
merry | -0.251 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
bus | +0.002 |
camel | +0.002 |
joy | +0.001 |
elephants | +0.001 |
vehicle | +0.001 |
Neg logit contributions | |
uts | -0.002 |
cartridge | -0.001 |
ate | -0.001 |
rap | -0.001 |
ra | -0.001 |
Token | Once |
Token ID | 7454 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
uts | +0.019 |
cartridge | +0.018 |
ate | +0.018 |
ra | +0.017 |
ung | +0.017 |
Neg logit contributions | |
bus | -0.021 |
camel | -0.021 |
joy | -0.019 |
elephants | -0.019 |
vehicle | -0.019 |
Token | upon |
Token ID | 2402 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
uts | +0.012 |
ate | +0.011 |
cartridge | +0.011 |
rap | +0.011 |
ung | +0.011 |
Neg logit contributions | |
camel | -0.011 |
bus | -0.011 |
elephants | -0.010 |
gir | -0.010 |
joy | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
uts | +0.011 |
ate | +0.011 |
cartridge | +0.010 |
ra | +0.009 |
ung | +0.009 |
Neg logit contributions | |
bus | -0.017 |
camel | -0.017 |
joy | -0.016 |
vehicle | -0.016 |
elephants | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
uts | +0.110 |
cartridge | +0.108 |
ate | +0.104 |
ra | +0.099 |
rap | +0.098 |
Neg logit contributions | |
bus | -0.090 |
camel | -0.088 |
joy | -0.081 |
elephants | -0.078 |
vehicle | -0.078 |
Token | used |
Token ID | 973 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
bus | +0.021 |
camel | +0.021 |
joy | +0.019 |
vehicle | +0.018 |
elephants | +0.018 |
Neg logit contributions | |
uts | -0.026 |
cartridge | -0.025 |
ate | -0.024 |
ra | -0.024 |
rap | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
uts | +0.119 |
cartridge | +0.118 |
ate | +0.114 |
ra | +0.108 |
rap | +0.108 |
Neg logit contributions | |
bus | -0.099 |
camel | -0.094 |
joy | -0.090 |
year | -0.085 |
vehicle | -0.085 |
Token | give |
Token ID | 1577 |
Feature activation | -3.51e-03 |
Pos logit contributions | |
camel | +0.019 |
bus | +0.019 |
joy | +0.018 |
elephants | +0.018 |
mo | +0.017 |
Neg logit contributions | |
uts | -0.014 |
cartridge | -0.014 |
ate | -0.014 |
ra | -0.013 |
rap | -0.013 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
uts | +0.005 |
cartridge | +0.005 |
ate | +0.005 |
ra | +0.005 |
rap | +0.005 |
Neg logit contributions | |
bus | -0.005 |
camel | -0.005 |
joy | -0.005 |
vehicle | -0.005 |
elephants | -0.005 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
cartridge | +0.014 |
ate | +0.010 |
rap | +0.008 |
cutter | +0.008 |
matters | +0.007 |
Neg logit contributions | |
bus | -0.079 |
camel | -0.076 |
joy | -0.075 |
taxi | -0.073 |
mo | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
cartridge | +0.324 |
uts | +0.322 |
ate | +0.311 |
ra | +0.301 |
rap | +0.298 |
Neg logit contributions | |
bus | -0.236 |
camel | -0.230 |
joy | -0.211 |
vehicle | -0.203 |
elephants | -0.202 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
ra | +0.002 |
ung | +0.002 |
Neg logit contributions | |
bus | -0.002 |
camel | -0.002 |
joy | -0.002 |
elephants | -0.002 |
vehicle | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
uts | +0.033 |
cartridge | +0.032 |
ate | +0.031 |
ra | +0.029 |
rap | +0.029 |
Neg logit contributions | |
bus | -0.029 |
camel | -0.029 |
joy | -0.027 |
vehicle | -0.025 |
elephants | -0.025 |
Token | The |
Token ID | 464 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
uts | +0.033 |
cartridge | +0.033 |
ate | +0.031 |
ra | +0.030 |
ung | +0.030 |
Neg logit contributions | |
bus | -0.028 |
camel | -0.027 |
year | -0.026 |
joy | -0.025 |
taxi | -0.025 |
Token | dad |
Token ID | 9955 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
camel | +0.031 |
elephants | +0.027 |
inspection | +0.026 |
mo | +0.026 |
bus | +0.026 |
Neg logit contributions | |
ra | -0.041 |
cartridge | -0.041 |
cutter | -0.041 |
ate | -0.041 |
connected | -0.040 |
Token | threw |
Token ID | 9617 |
Feature activation | +8.84e-03 |
Pos logit contributions | |
uts | +0.006 |
cartridge | +0.005 |
ate | +0.005 |
issors | +0.005 |
rap | +0.005 |
Neg logit contributions | |
bus | -0.004 |
camel | -0.004 |
joy | -0.003 |
elephants | -0.003 |
gir | -0.003 |
Token | down |
Token ID | 866 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
bus | +0.013 |
camel | +0.013 |
joy | +0.012 |
vehicle | +0.012 |
elephants | +0.011 |
Neg logit contributions | |
uts | -0.014 |
cartridge | -0.013 |
ate | -0.013 |
ra | -0.012 |
rap | -0.012 |
Token | some |
Token ID | 617 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
bus | +0.025 |
camel | +0.025 |
joy | +0.023 |
vehicle | +0.022 |
merry | +0.022 |
Neg logit contributions | |
uts | -0.025 |
cartridge | -0.024 |
ate | -0.023 |
ra | -0.022 |
cutter | -0.022 |
Token | coc |
Token ID | 8954 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
bus | +0.064 |
camel | +0.063 |
joy | +0.060 |
vehicle | +0.056 |
merry | +0.055 |
Neg logit contributions | |
uts | -0.069 |
cartridge | -0.068 |
ate | -0.065 |
cutter | -0.064 |
ra | -0.063 |
Token | on |
Token ID | 261 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
cartridge | +0.144 |
ate | +0.134 |
ra | +0.134 |
uts | +0.130 |
check | +0.127 |
Neg logit contributions | |
camel | -0.189 |
bus | -0.182 |
year | -0.174 |
joy | -0.171 |
mo | -0.169 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ate | +0.104 |
cartridge | +0.104 |
rap | +0.098 |
check | +0.092 |
ra | +0.092 |
Neg logit contributions | |
bus | -0.090 |
camel | -0.088 |
joy | -0.081 |
gir | -0.078 |
vehicle | -0.077 |
Token | for |
Token ID | 329 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
cartridge | +0.303 |
uts | +0.302 |
ate | +0.295 |
ra | +0.280 |
rap | +0.280 |
Neg logit contributions | |
bus | -0.256 |
camel | -0.249 |
joy | -0.233 |
vehicle | -0.222 |
elephants | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
uts | +0.026 |
cartridge | +0.025 |
ate | +0.024 |
ra | +0.024 |
rap | +0.024 |
Neg logit contributions | |
bus | -0.034 |
camel | -0.033 |
vehicle | -0.031 |
mo | -0.030 |
joy | -0.030 |
Token | sailor |
Token ID | 43272 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
bus | +0.023 |
camel | +0.022 |
joy | +0.021 |
vehicle | +0.020 |
mo | +0.020 |
Neg logit contributions | |
cartridge | -0.035 |
uts | -0.034 |
ra | -0.033 |
cutter | -0.032 |
ate | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +8.85e-03 |
Pos logit contributions | |
uts | +0.016 |
cartridge | +0.015 |
ate | +0.015 |
ra | +0.014 |
ung | +0.014 |
Neg logit contributions | |
bus | -0.013 |
camel | -0.013 |
joy | -0.012 |
elephants | -0.011 |
vehicle | -0.011 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
bus | +0.015 |
camel | +0.015 |
joy | +0.014 |
vehicle | +0.014 |
mo | +0.013 |
Neg logit contributions | |
uts | -0.012 |
ate | -0.012 |
cartridge | -0.011 |
rap | -0.011 |
ra | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
uts | +0.020 |
cartridge | +0.019 |
ate | +0.018 |
ra | +0.017 |
ung | +0.017 |
Neg logit contributions | |
bus | -0.016 |
camel | -0.015 |
joy | -0.014 |
vehicle | -0.014 |
elephants | -0.013 |
Token | fruits |
Token ID | 15921 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
bus | +0.005 |
camel | +0.005 |
joy | +0.005 |
mo | +0.005 |
year | +0.005 |
Neg logit contributions | |
uts | -0.007 |
ate | -0.006 |
cartridge | -0.006 |
ra | -0.006 |
connected | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
cartridge | +0.061 |
uts | +0.060 |
ate | +0.059 |
ra | +0.058 |
rap | +0.057 |
Neg logit contributions | |
bus | -0.035 |
camel | -0.034 |
joy | -0.030 |
elephants | -0.029 |
vehicle | -0.028 |
Token | coc |
Token ID | 8954 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
joy | +0.002 |
bus | +0.002 |
taxi | +0.002 |
year | +0.002 |
vehicle | +0.002 |
Neg logit contributions | |
uts | -0.002 |
connected | -0.002 |
ourselves | -0.002 |
themselves | -0.002 |
ate | -0.002 |
Token | on |
Token ID | 261 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
cartridge | +0.146 |
ra | +0.139 |
check | +0.132 |
ate | +0.131 |
uts | +0.129 |
Neg logit contributions | |
camel | -0.190 |
bus | -0.180 |
year | -0.172 |
joy | -0.170 |
mo | -0.169 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
cartridge | +0.110 |
ate | +0.107 |
rap | +0.104 |
ra | +0.099 |
ressing | +0.099 |
Neg logit contributions | |
camel | -0.089 |
bus | -0.087 |
elephants | -0.078 |
gir | -0.074 |
joy | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
cartridge | +0.335 |
uts | +0.330 |
ate | +0.323 |
ra | +0.313 |
rap | +0.312 |
Neg logit contributions | |
bus | -0.229 |
camel | -0.223 |
joy | -0.201 |
elephants | -0.196 |
vehicle | -0.193 |
Token | There |
Token ID | 1318 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
bus | +0.004 |
camel | +0.004 |
vehicle | +0.004 |
merry | +0.004 |
joy | +0.004 |
Neg logit contributions | |
uts | -0.005 |
cartridge | -0.005 |
ate | -0.005 |
ung | -0.004 |
ra | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
uts | +0.014 |
cartridge | +0.014 |
ate | +0.014 |
ra | +0.013 |
rap | +0.013 |
Neg logit contributions | |
bus | -0.008 |
camel | -0.008 |
joy | -0.007 |
elephants | -0.007 |
vehicle | -0.007 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
joy | +0.053 |
bus | +0.050 |
vehicle | +0.048 |
mo | +0.048 |
year | +0.047 |
Neg logit contributions | |
uts | -0.049 |
ate | -0.047 |
themselves | -0.046 |
connected | -0.046 |
ourselves | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +7.94e-04 |
Pos logit contributions | |
bus | +0.025 |
camel | +0.024 |
joy | +0.023 |
vehicle | +0.022 |
elephants | +0.022 |
Neg logit contributions | |
uts | -0.030 |
cartridge | -0.029 |
ate | -0.028 |
ra | -0.027 |
ung | -0.026 |
Token | night |
Token ID | 1755 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
uts | +0.001 |
cartridge | +0.001 |
ate | +0.001 |
ung | +0.001 |
rap | +0.001 |
Neg logit contributions | |
bus | -0.001 |
camel | -0.001 |
joy | -0.001 |
elephants | -0.001 |
vehicle | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
uts | +0.070 |
cartridge | +0.070 |
ate | +0.068 |
rap | +0.065 |
ra | +0.065 |
Neg logit contributions | |
bus | -0.048 |
camel | -0.047 |
joy | -0.044 |
year | -0.042 |
elephants | -0.041 |
Token | build |
Token ID | 1382 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
bus | +0.016 |
camel | +0.015 |
joy | +0.014 |
vehicle | +0.014 |
elephants | +0.014 |
Neg logit contributions | |
uts | -0.014 |
cartridge | -0.014 |
ate | -0.013 |
ra | -0.012 |
ung | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
camel | +0.026 |
bus | +0.026 |
joy | +0.023 |
mo | +0.023 |
hi | +0.023 |
Neg logit contributions | |
ate | -0.022 |
uts | -0.021 |
cartridge | -0.020 |
rap | -0.019 |
ra | -0.019 |
Token | h |
Token ID | 289 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
camel | +0.025 |
bus | +0.024 |
joy | +0.024 |
hi | +0.022 |
mo | +0.022 |
Neg logit contributions | |
ate | -0.032 |
cartridge | -0.031 |
uts | -0.029 |
connected | -0.029 |
rap | -0.027 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
bus | +0.012 |
camel | +0.012 |
joy | +0.011 |
elephants | +0.011 |
vehicle | +0.011 |
Neg logit contributions | |
uts | -0.010 |
cartridge | -0.010 |
ate | -0.009 |
ra | -0.009 |
rap | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-03 |
Pos logit contributions | |
uts | +0.318 |
cartridge | +0.316 |
ate | +0.304 |
ra | +0.294 |
rap | +0.290 |
Neg logit contributions | |
bus | -0.244 |
camel | -0.238 |
joy | -0.217 |
vehicle | -0.211 |
elephants | -0.210 |
Token | When |
Token ID | 1649 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
camel | +0.002 |
bus | +0.002 |
joy | +0.002 |
merry | +0.002 |
vehicle | +0.002 |
Neg logit contributions | |
uts | -0.003 |
cartridge | -0.003 |
ate | -0.003 |
ra | -0.002 |
ung | -0.002 |
Token | they |
Token ID | 484 |
Feature activation | +8.20e-03 |
Pos logit contributions | |
uts | +0.135 |
cartridge | +0.132 |
ate | +0.126 |
ra | +0.120 |
rap | +0.119 |
Neg logit contributions | |
bus | -0.126 |
camel | -0.124 |
joy | -0.116 |
elephants | -0.111 |
vehicle | -0.111 |
Token | had |
Token ID | 550 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
bus | +0.009 |
camel | +0.009 |
year | +0.008 |
vehicle | +0.008 |
hotel | +0.008 |
Neg logit contributions | |
uts | -0.017 |
cartridge | -0.015 |
ate | -0.015 |
ressing | -0.015 |
ung | -0.015 |
Token | finished |
Token ID | 5201 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
uts | +0.010 |
cartridge | +0.009 |
ate | +0.009 |
ra | +0.009 |
rap | +0.009 |
Neg logit contributions | |
bus | -0.010 |
joy | -0.010 |
camel | -0.009 |
year | -0.009 |
parking | -0.009 |
Token | my |
Token ID | 1820 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
bus | +0.033 |
camel | +0.033 |
joy | +0.030 |
elephants | +0.029 |
vehicle | +0.028 |
Neg logit contributions | |
uts | -0.054 |
cartridge | -0.053 |
ate | -0.053 |
ra | -0.050 |
rap | -0.050 |
Token | did |
Token ID | 750 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
bus | +0.047 |
camel | +0.045 |
joy | +0.039 |
vehicle | +0.038 |
year | +0.038 |
Neg logit contributions | |
uts | -0.093 |
cartridge | -0.091 |
ate | -0.086 |
rap | -0.085 |
cutter | -0.083 |
Token | not |
Token ID | 407 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
uts | +0.012 |
ate | +0.010 |
ung | +0.009 |
ra | +0.009 |
rap | +0.009 |
Neg logit contributions | |
camel | -0.027 |
bus | -0.026 |
elephants | -0.026 |
joy | -0.026 |
mo | -0.025 |
Token | like |
Token ID | 588 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
cartridge | +0.106 |
uts | +0.102 |
ra | +0.096 |
ate | +0.096 |
cutter | +0.095 |
Neg logit contributions | |
bus | -0.081 |
camel | -0.074 |
taxi | -0.066 |
year | -0.066 |
vehicle | -0.065 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
uts | +0.027 |
cartridge | +0.025 |
ate | +0.024 |
ra | +0.023 |
rap | +0.023 |
Neg logit contributions | |
camel | -0.030 |
bus | -0.030 |
joy | -0.028 |
vehicle | -0.027 |
elephants | -0.027 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
cartridge | +0.013 |
ate | +0.008 |
cutter | +0.005 |
rap | +0.005 |
matters | +0.005 |
Neg logit contributions | |
bus | -0.083 |
camel | -0.081 |
year | -0.078 |
joy | -0.077 |
taxi | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
uts | +0.314 |
cartridge | +0.304 |
ate | +0.292 |
ra | +0.278 |
rap | +0.277 |
Neg logit contributions | |
bus | -0.252 |
camel | -0.250 |
joy | -0.234 |
elephants | -0.219 |
vehicle | -0.219 |
Token | They |
Token ID | 1119 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
camel | +0.004 |
bus | +0.004 |
joy | +0.004 |
elephants | +0.004 |
vehicle | +0.004 |
Neg logit contributions | |
uts | -0.006 |
ate | -0.006 |
cartridge | -0.005 |
ung | -0.005 |
ra | -0.005 |
Token | made |
Token ID | 925 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
camel | +0.006 |
bus | +0.006 |
joy | +0.006 |
elephants | +0.006 |
vehicle | +0.006 |
Neg logit contributions | |
uts | -0.007 |
cartridge | -0.007 |
ate | -0.006 |
ra | -0.006 |
ung | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
uts | +0.012 |
cartridge | +0.012 |
ate | +0.011 |
ra | +0.011 |
rap | +0.011 |
Neg logit contributions | |
bus | -0.012 |
camel | -0.012 |
joy | -0.011 |
elephants | -0.010 |
vehicle | -0.010 |
Token | head |
Token ID | 1182 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
joy | +0.006 |
camel | +0.006 |
bus | +0.005 |
elephants | +0.005 |
hi | +0.005 |
Neg logit contributions | |
uts | -0.004 |
ra | -0.004 |
ate | -0.004 |
cartridge | -0.004 |
cutter | -0.004 |
Token | gathered |
Token ID | 9272 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
bus | +0.128 |
camel | +0.127 |
joy | +0.124 |
vehicle | +0.111 |
merry | +0.108 |
Neg logit contributions | |
uts | -0.182 |
cartridge | -0.173 |
ate | -0.169 |
ra | -0.165 |
cutter | -0.162 |
Token | all |
Token ID | 477 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
bus | +0.056 |
camel | +0.055 |
joy | +0.051 |
vehicle | +0.049 |
desert | +0.048 |
Neg logit contributions | |
uts | -0.040 |
ate | -0.039 |
cartridge | -0.039 |
ra | -0.037 |
ung | -0.036 |
Token | their |
Token ID | 511 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
camel | +0.098 |
bus | +0.098 |
joy | +0.092 |
vehicle | +0.085 |
elephants | +0.085 |
Neg logit contributions | |
uts | -0.093 |
cartridge | -0.091 |
ate | -0.091 |
ra | -0.083 |
cutter | -0.083 |
Token | coc |
Token ID | 8954 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
uts | +0.051 |
cartridge | +0.050 |
ate | +0.048 |
ra | +0.046 |
rap | +0.045 |
Neg logit contributions | |
bus | -0.051 |
camel | -0.050 |
joy | -0.047 |
vehicle | -0.045 |
elephants | -0.044 |
Token | on |
Token ID | 261 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
cartridge | +0.129 |
uts | +0.120 |
ra | +0.119 |
ate | +0.118 |
rap | +0.111 |
Neg logit contributions | |
camel | -0.203 |
bus | -0.201 |
year | -0.191 |
joy | -0.188 |
mo | -0.185 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
cartridge | +0.101 |
ate | +0.099 |
rap | +0.095 |
uts | +0.094 |
ra | +0.092 |
Neg logit contributions | |
bus | -0.088 |
camel | -0.086 |
joy | -0.077 |
vehicle | -0.075 |
year | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | -6.47e-04 |
Pos logit contributions | |
uts | +0.303 |
cartridge | +0.298 |
ate | +0.286 |
ra | +0.273 |
rap | +0.270 |
Neg logit contributions | |
bus | -0.259 |
camel | -0.255 |
joy | -0.237 |
elephants | -0.226 |
vehicle | -0.226 |
Token | put |
Token ID | 1234 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
uts | +0.001 |
cartridge | +0.001 |
ate | +0.001 |
ra | +0.001 |
rap | +0.001 |
Neg logit contributions | |
bus | -0.001 |
camel | -0.001 |
joy | -0.001 |
elephants | -0.001 |
vehicle | -0.001 |
Token | them |
Token ID | 606 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
cartridge | +0.018 |
uts | +0.017 |
ate | +0.017 |
ra | +0.016 |
cutter | +0.016 |
Neg logit contributions | |
bus | -0.020 |
camel | -0.020 |
joy | -0.019 |
year | -0.018 |
vehicle | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -9.76e-04 |
Pos logit contributions | |
bus | +0.055 |
camel | +0.054 |
joy | +0.051 |
elephants | +0.049 |
vehicle | +0.049 |
Neg logit contributions | |
uts | -0.054 |
cartridge | -0.053 |
ate | -0.051 |
ra | -0.048 |
rap | -0.048 |
Token | another |
Token ID | 1194 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
uts | +0.001 |
cartridge | +0.001 |
ate | +0.001 |
ra | +0.001 |
rap | +0.001 |
Neg logit contributions | |
bus | -0.002 |
camel | -0.002 |
joy | -0.001 |
vehicle | -0.001 |
elephants | -0.001 |
Token | wasn |
Token ID | 2492 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
bus | +0.051 |
camel | +0.049 |
joy | +0.045 |
year | +0.043 |
gir | +0.043 |
Neg logit contributions | |
uts | -0.078 |
cartridge | -0.077 |
issors | -0.072 |
ate | -0.072 |
rap | -0.070 |
Token | 't |
Token ID | 470 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
cartridge | +0.086 |
uts | +0.082 |
ate | +0.082 |
ra | +0.074 |
rap | +0.072 |
Neg logit contributions | |
bus | -0.186 |
camel | -0.181 |
taxi | -0.171 |
joy | -0.170 |
year | -0.170 |
Token | anxious |
Token ID | 18116 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
uts | +0.094 |
cartridge | +0.090 |
cutter | +0.084 |
connected | +0.084 |
ung | +0.083 |
Neg logit contributions | |
bus | -0.072 |
camel | -0.070 |
vehicle | -0.064 |
taxi | -0.061 |
elephants | -0.060 |
Token | about |
Token ID | 546 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
camel | +0.006 |
bus | +0.006 |
merry | +0.005 |
vehicle | +0.005 |
sandbox | +0.005 |
Neg logit contributions | |
uts | -0.006 |
cartridge | -0.006 |
ressing | -0.005 |
ung | -0.005 |
ate | -0.005 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
uts | +0.023 |
ate | +0.021 |
cartridge | +0.021 |
ra | +0.020 |
rap | +0.020 |
Neg logit contributions | |
camel | -0.026 |
bus | -0.026 |
joy | -0.023 |
vehicle | -0.023 |
taxi | -0.023 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
cartridge | +0.014 |
ate | +0.009 |
matters | +0.007 |
cutter | +0.007 |
rap | +0.006 |
Neg logit contributions | |
bus | -0.085 |
joy | -0.082 |
camel | -0.081 |
year | -0.079 |
mo | -0.078 |
Token | anymore |
Token ID | 7471 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
uts | +0.318 |
cartridge | +0.306 |
ate | +0.292 |
ra | +0.279 |
rap | +0.278 |
Neg logit contributions | |
camel | -0.250 |
bus | -0.249 |
joy | -0.229 |
elephants | -0.217 |
vehicle | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
bus | +0.043 |
camel | +0.042 |
joy | +0.039 |
elephants | +0.037 |
year | +0.037 |
Neg logit contributions | |
cartridge | -0.068 |
uts | -0.066 |
ate | -0.065 |
ra | -0.062 |
rap | -0.061 |
Token | He |
Token ID | 679 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
uts | +0.008 |
ate | +0.008 |
cartridge | +0.008 |
rap | +0.007 |
ung | +0.007 |
Neg logit contributions | |
camel | -0.006 |
bus | -0.006 |
joy | -0.005 |
merry | -0.005 |
taxi | -0.005 |
Token | knew |
Token ID | 2993 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
bus | +0.013 |
camel | +0.013 |
joy | +0.012 |
elephants | +0.012 |
vehicle | +0.012 |
Neg logit contributions | |
uts | -0.018 |
cartridge | -0.017 |
ate | -0.017 |
ra | -0.016 |
rap | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
uts | +0.042 |
cartridge | +0.041 |
ate | +0.040 |
ra | +0.037 |
rap | +0.037 |
Neg logit contributions | |
bus | -0.042 |
camel | -0.041 |
joy | -0.039 |
elephants | -0.037 |
merry | -0.036 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
bus | +0.013 |
camel | +0.013 |
joy | +0.011 |
vehicle | +0.011 |
taxi | +0.011 |
Neg logit contributions | |
uts | -0.015 |
cartridge | -0.014 |
ate | -0.014 |
ra | -0.013 |
rap | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
uts | +0.049 |
cartridge | +0.049 |
ate | +0.048 |
ra | +0.046 |
rap | +0.046 |
Neg logit contributions | |
camel | -0.025 |
bus | -0.025 |
joy | -0.022 |
taxi | -0.021 |
elephants | -0.021 |
Token | liked |
Token ID | 8288 |
Feature activation | -3.28e-03 |
Pos logit contributions | |
bus | +0.054 |
camel | +0.052 |
joy | +0.048 |
year | +0.046 |
vehicle | +0.046 |
Neg logit contributions | |
uts | -0.078 |
cartridge | -0.076 |
ate | -0.071 |
issors | -0.070 |
rap | -0.070 |
Token | getting |
Token ID | 1972 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
uts | +0.005 |
cartridge | +0.005 |
ate | +0.004 |
ra | +0.004 |
rap | +0.004 |
Neg logit contributions | |
bus | -0.005 |
camel | -0.005 |
joy | -0.005 |
vehicle | -0.005 |
elephants | -0.005 |
Token | hairc |
Token ID | 37363 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
uts | +0.021 |
cartridge | +0.020 |
ate | +0.019 |
ra | +0.019 |
rap | +0.018 |
Neg logit contributions | |
bus | -0.016 |
camel | -0.015 |
joy | -0.014 |
elephants | -0.014 |
vehicle | -0.014 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
cartridge | +0.016 |
ate | +0.013 |
matters | +0.012 |
cutter | +0.010 |
rap | +0.010 |
Neg logit contributions | |
bus | -0.073 |
joy | -0.069 |
camel | -0.069 |
taxi | -0.067 |
year | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
uts | +0.288 |
cartridge | +0.279 |
ate | +0.262 |
ra | +0.245 |
ung | +0.244 |
Neg logit contributions | |
camel | -0.280 |
bus | -0.276 |
joy | -0.259 |
elephants | -0.247 |
vehicle | -0.243 |
Token | always |
Token ID | 1464 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
uts | +0.009 |
cartridge | +0.008 |
ate | +0.008 |
ra | +0.008 |
cutter | +0.007 |
Neg logit contributions | |
camel | -0.009 |
bus | -0.008 |
joy | -0.008 |
taxi | -0.008 |
year | -0.008 |
Token | looked |
Token ID | 3114 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
cartridge | +0.019 |
ate | +0.019 |
uts | +0.019 |
ra | +0.019 |
connected | +0.018 |
Neg logit contributions | |
camel | -0.024 |
bus | -0.023 |
elephants | -0.021 |
joy | -0.021 |
taxi | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
camel | +0.167 |
bus | +0.165 |
year | +0.151 |
joy | +0.151 |
merry | +0.149 |
Neg logit contributions | |
cartridge | -0.112 |
ate | -0.111 |
uts | -0.111 |
rap | -0.102 |
ra | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
ate | +0.021 |
ra | +0.020 |
uts | +0.020 |
knots | +0.019 |
matters | +0.019 |
Neg logit contributions | |
camel | -0.029 |
bus | -0.028 |
mo | -0.026 |
sandbox | -0.026 |
enced | -0.026 |
Token | secret |
Token ID | 3200 |
Feature activation | +5.01e-04 |
Pos logit contributions | |
cartridge | +0.038 |
uts | +0.038 |
cutter | +0.036 |
ra | +0.035 |
ate | +0.035 |
Neg logit contributions | |
camel | -0.033 |
bus | -0.032 |
joy | -0.031 |
elephants | -0.030 |
mo | -0.030 |
Token | place |
Token ID | 1295 |
Feature activation | -8.32e-03 |
Pos logit contributions | |
bus | +0.001 |
camel | +0.001 |
joy | +0.001 |
elephants | +0.001 |
mo | +0.001 |
Neg logit contributions | |
uts | -0.001 |
cartridge | -0.001 |
ate | -0.001 |
cutter | -0.001 |
ra | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
uts | +0.013 |
cartridge | +0.012 |
ate | +0.012 |
ra | +0.011 |
cutter | +0.011 |
Neg logit contributions | |
camel | -0.012 |
bus | -0.012 |
joy | -0.011 |
elephants | -0.011 |
vehicle | -0.011 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
uts | +0.019 |
rap | +0.019 |
cartridge | +0.018 |
ate | +0.018 |
ung | +0.018 |
Neg logit contributions | |
bus | -0.011 |
camel | -0.010 |
vehicle | -0.009 |
elephants | -0.009 |
merry | -0.009 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
uts | +0.027 |
cartridge | +0.026 |
ate | +0.025 |
ung | +0.023 |
ra | +0.023 |
Neg logit contributions | |
bus | -0.027 |
camel | -0.027 |
joy | -0.025 |
elephants | -0.025 |
vehicle | -0.024 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
cartridge | +0.015 |
ate | +0.009 |
cutter | +0.008 |
matters | +0.007 |
rap | +0.007 |
Neg logit contributions | |
camel | -0.077 |
bus | -0.077 |
joy | -0.074 |
year | -0.073 |
mo | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
uts | +0.305 |
cartridge | +0.298 |
ate | +0.287 |
ra | +0.274 |
rap | +0.271 |
Neg logit contributions | |
bus | -0.256 |
camel | -0.252 |
joy | -0.234 |
elephants | -0.223 |
vehicle | -0.222 |
Token | Max |
Token ID | 5436 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
bus | +0.005 |
joy | +0.005 |
camel | +0.004 |
vehicle | +0.004 |
elephants | +0.004 |
Neg logit contributions | |
cartridge | -0.006 |
uts | -0.006 |
ra | -0.005 |
ate | -0.005 |
rap | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
uts | +0.092 |
cartridge | +0.090 |
ate | +0.086 |
ra | +0.083 |
rap | +0.083 |
Neg logit contributions | |
bus | -0.062 |
camel | -0.061 |
joy | -0.056 |
vehicle | -0.053 |
elephants | -0.053 |
Token | so |
Token ID | 523 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
uts | +0.003 |
cartridge | +0.003 |
ate | +0.003 |
ra | +0.003 |
ung | +0.003 |
Neg logit contributions | |
bus | -0.002 |
camel | -0.002 |
joy | -0.002 |
vehicle | -0.002 |
elephants | -0.002 |
Token | excited |
Token ID | 6568 |
Feature activation | -9.46e-03 |
Pos logit contributions | |
camel | +0.043 |
bus | +0.041 |
joy | +0.037 |
hello | +0.035 |
year | +0.035 |
Neg logit contributions | |
cartridge | -0.102 |
uts | -0.095 |
rap | -0.094 |
ate | -0.093 |
ra | -0.092 |
Token | other |
Token ID | 584 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
camel | +0.122 |
bus | +0.119 |
joy | +0.117 |
mo | +0.111 |
year | +0.110 |
Neg logit contributions | |
uts | -0.093 |
ate | -0.091 |
cartridge | -0.086 |
connected | -0.077 |
ung | -0.077 |
Token | kids |
Token ID | 3988 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
camel | +0.091 |
joy | +0.083 |
mo | +0.082 |
bus | +0.081 |
elephants | +0.078 |
Neg logit contributions | |
ate | -0.087 |
uts | -0.086 |
ra | -0.082 |
rap | -0.078 |
cartridge | -0.078 |
Token | getting |
Token ID | 1972 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
uts | +0.033 |
cartridge | +0.030 |
ate | +0.029 |
ra | +0.027 |
connected | +0.027 |
Neg logit contributions | |
camel | -0.035 |
bus | -0.033 |
joy | -0.031 |
elephants | -0.031 |
vehicle | -0.030 |
Token | their |
Token ID | 511 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
uts | +0.022 |
cartridge | +0.021 |
ate | +0.020 |
rap | +0.020 |
ra | +0.020 |
Neg logit contributions | |
bus | -0.019 |
camel | -0.018 |
joy | -0.017 |
taxi | -0.016 |
elephants | -0.016 |
Token | hairc |
Token ID | 37363 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
uts | +0.059 |
cartridge | +0.058 |
ate | +0.056 |
rap | +0.053 |
ung | +0.053 |
Neg logit contributions | |
bus | -0.052 |
camel | -0.050 |
joy | -0.047 |
vehicle | -0.045 |
elephants | -0.045 |
Token | uts |
Token ID | 5500 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
cartridge | +0.013 |
ate | +0.010 |
rap | +0.007 |
matters | +0.007 |
cutter | +0.006 |
Neg logit contributions | |
bus | -0.082 |
camel | -0.079 |
year | -0.077 |
taxi | -0.076 |
joy | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
uts | +0.311 |
cartridge | +0.303 |
ate | +0.289 |
ra | +0.275 |
ung | +0.273 |
Neg logit contributions | |
bus | -0.249 |
camel | -0.249 |
joy | -0.230 |
elephants | -0.219 |
vehicle | -0.216 |
Token | they |
Token ID | 484 |
Feature activation | +8.48e-03 |
Pos logit contributions | |
uts | +0.004 |
cartridge | +0.004 |
ate | +0.004 |
ra | +0.004 |
cutter | +0.004 |
Neg logit contributions | |
camel | -0.004 |
bus | -0.004 |
joy | -0.004 |
year | -0.004 |
mo | -0.004 |
Token | looked |
Token ID | 3114 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
camel | +0.013 |
joy | +0.013 |
bus | +0.012 |
vehicle | +0.011 |
desert | +0.011 |
Neg logit contributions | |
uts | -0.012 |
connected | -0.012 |
cartridge | -0.012 |
ate | -0.011 |
printed | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
camel | +0.146 |
bus | +0.140 |
elephants | +0.126 |
vehicle | +0.125 |
mo | +0.125 |
Neg logit contributions | |
cartridge | -0.125 |
uts | -0.125 |
connected | -0.122 |
ate | -0.121 |
ung | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
bus | +0.011 |
camel | +0.011 |
joy | +0.010 |
elephants | +0.010 |
vehicle | +0.010 |
Neg logit contributions | |
uts | -0.015 |
cartridge | -0.015 |
ate | -0.014 |
ra | -0.014 |
rap | -0.013 |
Token | 've |
Token ID | 1053 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
bus | +0.033 |
camel | +0.033 |
year | +0.030 |
joy | +0.028 |
mo | +0.028 |
Neg logit contributions | |
uts | -0.046 |
cartridge | -0.045 |
ate | -0.042 |
rap | -0.042 |
issors | -0.041 |
Token | seen |
Token ID | 1775 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
bus | +0.101 |
camel | +0.097 |
year | +0.094 |
joy | +0.093 |
merry | +0.088 |
Neg logit contributions | |
cartridge | -0.103 |
uts | -0.102 |
ate | -0.096 |
issors | -0.094 |
rap | -0.094 |
Token | so |
Token ID | 523 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
bus | +0.058 |
camel | +0.058 |
joy | +0.054 |
vehicle | +0.052 |
taxi | +0.051 |
Neg logit contributions | |
uts | -0.047 |
cartridge | -0.045 |
ate | -0.044 |
ra | -0.041 |
rap | -0.041 |
Token | far |
Token ID | 1290 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
bus | +0.062 |
camel | +0.061 |
joy | +0.056 |
vehicle | +0.054 |
elephants | +0.054 |
Neg logit contributions | |
uts | -0.081 |
cartridge | -0.079 |
ate | -0.076 |
ra | -0.073 |
rap | -0.072 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.83e-03 |
Pos logit contributions | |
bus | +0.087 |
camel | +0.086 |
joy | +0.081 |
elephants | +0.078 |
vehicle | +0.078 |
Neg logit contributions | |
uts | -0.069 |
cartridge | -0.068 |
ate | -0.065 |
ra | -0.062 |
rap | -0.060 |
Token | |
Token ID | 220 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
camel | +0.005 |
bus | +0.005 |
elephants | +0.004 |
joy | +0.004 |
vehicle | +0.004 |
Neg logit contributions | |
uts | -0.007 |
cartridge | -0.007 |
ate | -0.007 |
ra | -0.006 |
ung | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
joy | +0.101 |
bus | +0.097 |
camel | +0.095 |
hi | +0.087 |
taxi | +0.087 |
Neg logit contributions | |
cartridge | -0.282 |
cutter | -0.257 |
ra | -0.255 |
uts | -0.246 |
ressing | -0.245 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
cartridge | +0.034 |
uts | +0.034 |
ate | +0.032 |
ra | +0.031 |
rap | +0.031 |
Neg logit contributions | |
bus | -0.026 |
camel | -0.025 |
joy | -0.024 |
year | -0.023 |
taxi | -0.022 |
Token | Mom |
Token ID | 29252 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
cartridge | +0.031 |
uts | +0.030 |
ate | +0.028 |
ressing | +0.027 |
rap | +0.027 |
Neg logit contributions | |
bus | -0.029 |
camel | -0.028 |
year | -0.027 |
taxi | -0.026 |
joy | -0.026 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
uts | +0.097 |
cartridge | +0.095 |
ate | +0.094 |
ra | +0.093 |
rap | +0.090 |
Neg logit contributions | |
camel | -0.073 |
bus | -0.071 |
joy | -0.068 |
desert | -0.063 |
vehicle | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
bus | +0.016 |
camel | +0.016 |
elephants | +0.015 |
vehicle | +0.014 |
desert | +0.014 |
Neg logit contributions | |
uts | -0.015 |
cartridge | -0.015 |
ate | -0.015 |
ung | -0.014 |
ra | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
uts | +0.032 |
cartridge | +0.031 |
ate | +0.030 |
ra | +0.028 |
rap | +0.028 |
Neg logit contributions | |
bus | -0.032 |
camel | -0.031 |
joy | -0.029 |
elephants | -0.028 |
vehicle | -0.028 |
Token | The |
Token ID | 464 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
cartridge | +0.033 |
uts | +0.032 |
ra | +0.030 |
ate | +0.030 |
cutter | +0.029 |
Neg logit contributions | |
camel | -0.031 |
bus | -0.031 |
year | -0.029 |
joy | -0.029 |
vehicle | -0.027 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
camel | +0.036 |
bus | +0.036 |
joy | +0.034 |
elephants | +0.032 |
vehicle | +0.032 |
Neg logit contributions | |
cartridge | -0.041 |
uts | -0.040 |
ate | -0.038 |
ra | -0.037 |
cutter | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
uts | +0.053 |
cartridge | +0.052 |
ate | +0.051 |
ra | +0.048 |
ung | +0.048 |
Neg logit contributions | |
bus | -0.032 |
camel | -0.032 |
joy | -0.029 |
elephants | -0.028 |
vehicle | -0.027 |
Token | this |
Token ID | 428 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
bus | +0.028 |
camel | +0.027 |
joy | +0.025 |
year | +0.024 |
vehicle | +0.024 |
Neg logit contributions | |
uts | -0.034 |
cartridge | -0.033 |
ate | -0.031 |
ra | -0.030 |
ung | -0.030 |
Token | story |
Token ID | 1621 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
bus | +0.007 |
camel | +0.007 |
joy | +0.006 |
elephants | +0.006 |
vehicle | +0.005 |
Neg logit contributions | |
uts | -0.015 |
cartridge | -0.014 |
ate | -0.014 |
ra | -0.013 |
rap | -0.013 |
Token | is |
Token ID | 318 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
year | +0.090 |
bus | +0.089 |
vehicle | +0.074 |
camel | +0.072 |
hello | +0.070 |
Neg logit contributions | |
cartridge | -0.219 |
uts | -0.210 |
cutter | -0.194 |
ra | -0.194 |
check | -0.194 |
Token | that |
Token ID | 326 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
bus | +0.006 |
camel | +0.006 |
year | +0.005 |
joy | +0.005 |
vehicle | +0.005 |
Neg logit contributions | |
uts | -0.008 |
cartridge | -0.008 |
ate | -0.007 |
ra | -0.007 |
cutter | -0.007 |
Token | even |
Token ID | 772 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
uts | +0.016 |
cartridge | +0.016 |
ate | +0.015 |
ung | +0.014 |
issors | +0.014 |
Neg logit contributions | |
bus | -0.015 |
joy | -0.015 |
year | -0.015 |
camel | -0.014 |
hello | -0.014 |
Token | when |
Token ID | 618 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
bus | +0.019 |
camel | +0.018 |
joy | +0.017 |
elephants | +0.016 |
vehicle | +0.016 |
Neg logit contributions | |
uts | -0.017 |
cartridge | -0.017 |
ate | -0.016 |
ra | -0.015 |
rap | -0.015 |
Token | things |
Token ID | 1243 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
uts | +0.103 |
cartridge | +0.101 |
ate | +0.093 |
rap | +0.090 |
ung | +0.089 |
Neg logit contributions | |
bus | -0.128 |
camel | -0.126 |
joy | -0.122 |
year | -0.117 |
elephants | -0.116 |
Token | he |
Token ID | 339 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
bus | +0.011 |
camel | +0.011 |
joy | +0.010 |
vehicle | +0.009 |
elephants | +0.009 |
Neg logit contributions | |
uts | -0.020 |
cartridge | -0.020 |
ate | -0.019 |
ra | -0.018 |
rap | -0.018 |
Token | saw |
Token ID | 2497 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
bus | +0.022 |
joy | +0.021 |
camel | +0.021 |
elephants | +0.020 |
vehicle | +0.019 |
Neg logit contributions | |
cartridge | -0.025 |
uts | -0.024 |
ate | -0.024 |
ra | -0.024 |
sealed | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
bus | +0.126 |
camel | +0.124 |
joy | +0.120 |
mo | +0.115 |
year | +0.114 |
Neg logit contributions | |
ate | -0.093 |
uts | -0.091 |
cartridge | -0.089 |
connected | -0.081 |
sealed | -0.079 |
Token | birds |
Token ID | 10087 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
camel | +0.019 |
bus | +0.019 |
joy | +0.019 |
mo | +0.018 |
hi | +0.018 |
Neg logit contributions | |
cartridge | -0.025 |
uts | -0.024 |
ra | -0.024 |
ate | -0.024 |
cutter | -0.023 |
Token | flying |
Token ID | 7348 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
bus | +0.035 |
camel | +0.035 |
joy | +0.034 |
vehicle | +0.032 |
merry | +0.031 |
Neg logit contributions | |
uts | -0.031 |
cartridge | -0.027 |
connected | -0.027 |
ung | -0.025 |
ate | -0.025 |
Token | again |
Token ID | 757 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
camel | +0.074 |
bus | +0.074 |
joy | +0.070 |
elephants | +0.066 |
vehicle | +0.066 |
Neg logit contributions | |
uts | -0.049 |
cartridge | -0.046 |
ate | -0.045 |
ung | -0.042 |
ra | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
bus | +0.140 |
camel | +0.138 |
joy | +0.126 |
vehicle | +0.122 |
elephants | +0.122 |
Neg logit contributions | |
uts | -0.171 |
cartridge | -0.165 |
ate | -0.161 |
ra | -0.154 |
rap | -0.152 |
Token | He |
Token ID | 679 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
uts | +0.004 |
cartridge | +0.003 |
ate | +0.003 |
ung | +0.003 |
issors | +0.003 |
Neg logit contributions | |
camel | -0.003 |
bus | -0.003 |
merry | -0.002 |
joy | -0.002 |
year | -0.002 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
bus | +0.018 |
camel | +0.018 |
joy | +0.018 |
vehicle | +0.016 |
elephants | +0.016 |
Neg logit contributions | |
uts | -0.020 |
ate | -0.019 |
ra | -0.019 |
cartridge | -0.019 |
connected | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
bus | +0.017 |
camel | +0.017 |
joy | +0.015 |
elephants | +0.015 |
year | +0.015 |
Neg logit contributions | |
uts | -0.018 |
cartridge | -0.018 |
ate | -0.017 |
ung | -0.016 |
ra | -0.016 |
Token | ran |
Token ID | 4966 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
uts | +0.005 |
cartridge | +0.005 |
ate | +0.005 |
ra | +0.005 |
ung | +0.005 |
Neg logit contributions | |
bus | -0.005 |
camel | -0.005 |
joy | -0.004 |
vehicle | -0.004 |
elephants | -0.004 |
Token | vowed |
Token ID | 19982 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
uts | +0.007 |
cartridge | +0.006 |
ate | +0.006 |
ra | +0.006 |
ung | +0.006 |
Neg logit contributions | |
bus | -0.007 |
camel | -0.007 |
joy | -0.006 |
elephants | -0.006 |
vehicle | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
cartridge | +0.065 |
uts | +0.062 |
ate | +0.060 |
rap | +0.059 |
ra | +0.058 |
Neg logit contributions | |
bus | -0.060 |
camel | -0.057 |
joy | -0.055 |
vehicle | -0.053 |
taxi | -0.053 |
Token | never |
Token ID | 1239 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
bus | +0.016 |
camel | +0.016 |
joy | +0.015 |
vehicle | +0.014 |
elephants | +0.014 |
Neg logit contributions | |
uts | -0.016 |
cartridge | -0.016 |
ate | -0.015 |
ra | -0.014 |
ung | -0.014 |
Token | hurt |
Token ID | 5938 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
bus | +0.062 |
camel | +0.062 |
joy | +0.058 |
vehicle | +0.055 |
elephants | +0.055 |
Neg logit contributions | |
uts | -0.060 |
cartridge | -0.059 |
ate | -0.056 |
ra | -0.054 |
rap | -0.053 |
Token | anyone |
Token ID | 2687 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
uts | +0.095 |
cartridge | +0.089 |
ate | +0.088 |
ra | +0.084 |
rap | +0.082 |
Neg logit contributions | |
bus | -0.108 |
camel | -0.107 |
joy | -0.097 |
elephants | -0.094 |
vehicle | -0.094 |
Token | again |
Token ID | 757 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
camel | +0.066 |
bus | +0.066 |
joy | +0.058 |
elephants | +0.058 |
vehicle | +0.058 |
Neg logit contributions | |
uts | -0.068 |
cartridge | -0.061 |
ressing | -0.057 |
ate | -0.057 |
connected | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
bus | +0.153 |
camel | +0.150 |
vehicle | +0.134 |
elephants | +0.134 |
taxi | +0.133 |
Neg logit contributions | |
uts | -0.161 |
ate | -0.151 |
cartridge | -0.151 |
ra | -0.142 |
ung | -0.142 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.001 |
ung | +0.001 |
ra | +0.001 |
Neg logit contributions | |
bus | -0.002 |
camel | -0.002 |
elephants | -0.002 |
merry | -0.002 |
joy | -0.002 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
uts | +0.014 |
cartridge | +0.013 |
ate | +0.013 |
ra | +0.012 |
rap | +0.012 |
Neg logit contributions | |
bus | -0.015 |
camel | -0.014 |
joy | -0.013 |
vehicle | -0.013 |
elephants | -0.013 |
Token | upon |
Token ID | 2402 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
uts | +0.004 |
cartridge | +0.003 |
ate | +0.003 |
rap | +0.003 |
ung | +0.003 |
Neg logit contributions | |
bus | -0.003 |
camel | -0.003 |
elephants | -0.003 |
gir | -0.003 |
merry | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
uts | +0.009 |
ate | +0.009 |
cartridge | +0.008 |
ra | +0.007 |
ung | +0.007 |
Neg logit contributions | |
bus | -0.014 |
camel | -0.014 |
joy | -0.013 |
vehicle | -0.013 |
mo | -0.013 |
Token | I |
Token ID | 314 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
bus | +0.002 |
camel | +0.002 |
joy | +0.002 |
elephants | +0.002 |
vehicle | +0.002 |
Neg logit contributions | |
uts | -0.002 |
cartridge | -0.002 |
ate | -0.002 |
ra | -0.002 |
ung | -0.002 |
Token | lock |
Token ID | 5793 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
bus | +0.031 |
camel | +0.030 |
year | +0.028 |
taxi | +0.027 |
vehicle | +0.027 |
Neg logit contributions | |
uts | -0.040 |
cartridge | -0.039 |
ate | -0.037 |
rap | -0.035 |
ressing | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
uts | +0.027 |
cartridge | +0.027 |
ate | +0.025 |
ung | +0.024 |
cutter | +0.023 |
Neg logit contributions | |
bus | -0.029 |
camel | -0.027 |
vehicle | -0.026 |
elephants | -0.025 |
joy | -0.025 |
Token | door |
Token ID | 3420 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
bus | +0.019 |
camel | +0.018 |
joy | +0.016 |
vehicle | +0.016 |
elephants | +0.016 |
Neg logit contributions | |
uts | -0.035 |
cartridge | -0.034 |
ate | -0.033 |
rap | -0.032 |
ra | -0.032 |
Token | so |
Token ID | 523 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
camel | +0.047 |
bus | +0.046 |
joy | +0.043 |
elephants | +0.041 |
vehicle | +0.040 |
Neg logit contributions | |
uts | -0.054 |
cartridge | -0.053 |
ate | -0.052 |
ra | -0.049 |
rap | -0.049 |
Token | no |
Token ID | 645 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
bus | +0.064 |
camel | +0.062 |
joy | +0.058 |
vehicle | +0.056 |
taxi | +0.056 |
Neg logit contributions | |
uts | -0.063 |
cartridge | -0.063 |
ate | -0.060 |
rap | -0.057 |
ra | -0.057 |
Token | one |
Token ID | 530 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
joy | +0.145 |
camel | +0.141 |
bus | +0.136 |
mo | +0.133 |
merry | +0.125 |
Neg logit contributions | |
uts | -0.150 |
cartridge | -0.150 |
ate | -0.140 |
matters | -0.136 |
ourselves | -0.134 |
Token | can |
Token ID | 460 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
bus | +0.130 |
camel | +0.126 |
year | +0.112 |
elephants | +0.112 |
taxi | +0.110 |
Neg logit contributions | |
uts | -0.144 |
cartridge | -0.144 |
ate | -0.137 |
rap | -0.133 |
ung | -0.133 |
Token | come |
Token ID | 1282 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
cartridge | +0.120 |
uts | +0.116 |
ate | +0.112 |
cutter | +0.108 |
ressing | +0.106 |
Neg logit contributions | |
bus | -0.092 |
camel | -0.082 |
taxi | -0.078 |
year | -0.077 |
vehicle | -0.073 |
Token | in |
Token ID | 287 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
bus | +0.083 |
camel | +0.080 |
vehicle | +0.074 |
joy | +0.074 |
taxi | +0.073 |
Neg logit contributions | |
cartridge | -0.080 |
uts | -0.079 |
ate | -0.073 |
cutter | -0.071 |
ra | -0.069 |
Token | ." |
Token ID | 526 |
Feature activation | +1.00e-03 |
Pos logit contributions | |
uts | +0.008 |
cartridge | +0.008 |
ate | +0.008 |
ra | +0.007 |
rap | +0.007 |
Neg logit contributions | |
bus | -0.009 |
camel | -0.009 |
joy | -0.009 |
elephants | -0.008 |
vehicle | -0.008 |
Token | there |
Token ID | 612 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
bus | +0.027 |
camel | +0.027 |
joy | +0.025 |
elephants | +0.025 |
desert | +0.024 |
Neg logit contributions | |
ate | -0.020 |
cartridge | -0.020 |
uts | -0.020 |
ra | -0.019 |
ung | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +1.07e-03 |
Pos logit contributions | |
uts | +0.014 |
ate | +0.014 |
cartridge | +0.013 |
ra | +0.013 |
rap | +0.013 |
Neg logit contributions | |
bus | -0.012 |
camel | -0.012 |
joy | -0.011 |
elephants | -0.011 |
vehicle | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
bus | +0.001 |
camel | +0.001 |
joy | +0.001 |
elephants | +0.001 |
year | +0.001 |
Neg logit contributions | |
uts | -0.002 |
cartridge | -0.002 |
ate | -0.002 |
ra | -0.002 |
rap | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
cartridge | +0.039 |
cutter | +0.037 |
ate | +0.037 |
fold | +0.037 |
ra | +0.037 |
Neg logit contributions | |
mo | -0.026 |
inspection | -0.025 |
joy | -0.025 |
bus | -0.024 |
elephants | -0.023 |
Token | boy |
Token ID | 2933 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
joy | +0.041 |
inspection | +0.039 |
bus | +0.037 |
hi | +0.037 |
mo | +0.036 |
Neg logit contributions | |
cartridge | -0.075 |
cutter | -0.072 |
ra | -0.069 |
uts | -0.067 |
fold | -0.066 |
Token | named |
Token ID | 3706 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
joy | +0.042 |
bus | +0.040 |
camel | +0.040 |
merry | +0.036 |
hi | +0.035 |
Neg logit contributions | |
uts | -0.077 |
ate | -0.077 |
ra | -0.076 |
cartridge | -0.074 |
cutter | -0.073 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
camel | +0.145 |
bus | +0.143 |
joy | +0.139 |
elephants | +0.127 |
merry | +0.127 |
Neg logit contributions | |
uts | -0.150 |
cartridge | -0.147 |
ate | -0.141 |
rap | -0.136 |
ra | -0.134 |
Token | my |
Token ID | 1820 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
ate | +0.041 |
uts | +0.039 |
cartridge | +0.038 |
rap | +0.037 |
ra | +0.037 |
Neg logit contributions | |
camel | -0.028 |
bus | -0.027 |
joy | -0.026 |
elephants | -0.024 |
hi | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +5.99e-04 |
Pos logit contributions | |
bus | +0.066 |
camel | +0.065 |
joy | +0.062 |
elephants | +0.058 |
merry | +0.057 |
Neg logit contributions | |
uts | -0.076 |
cartridge | -0.073 |
ate | -0.072 |
ra | -0.068 |
rap | -0.067 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
camel | +0.001 |
bus | +0.001 |
joy | +0.001 |
merry | +0.001 |
taxi | +0.001 |
Neg logit contributions | |
uts | -0.001 |
ate | -0.001 |
cartridge | -0.001 |
rap | -0.001 |
issors | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
uts | +0.048 |
ate | +0.048 |
cartridge | +0.048 |
ra | +0.045 |
rap | +0.045 |
Neg logit contributions | |
bus | -0.021 |
camel | -0.021 |
joy | -0.019 |
elephants | -0.017 |
taxi | -0.017 |
Token | € |
Token ID | 26391 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
camel | +0.041 |
bus | +0.039 |
joy | +0.038 |
elephants | +0.037 |
vehicle | +0.036 |
Neg logit contributions | |
uts | -0.032 |
cartridge | -0.032 |
ate | -0.031 |
ra | -0.029 |
rap | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
bus | +0.019 |
camel | +0.019 |
joy | +0.018 |
elephants | +0.017 |
vehicle | +0.017 |
Neg logit contributions | |
uts | -0.019 |
cartridge | -0.019 |
ate | -0.018 |
ra | -0.017 |
rap | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
uts | +0.029 |
cartridge | +0.027 |
ate | +0.026 |
ung | +0.024 |
rap | +0.024 |
Neg logit contributions | |
bus | -0.036 |
camel | -0.036 |
elephants | -0.034 |
joy | -0.033 |
vehicle | -0.033 |
Token | Alice |
Token ID | 44484 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
uts | +0.032 |
cartridge | +0.031 |
ate | +0.030 |
ra | +0.028 |
rap | +0.028 |
Neg logit contributions | |
bus | -0.033 |
camel | -0.033 |
joy | -0.031 |
elephants | -0.030 |
vehicle | -0.030 |
Token | â |
Token ID | 22940 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
bus | +0.105 |
camel | +0.103 |
joy | +0.097 |
elephants | +0.093 |
vehicle | +0.092 |
Neg logit contributions | |
uts | -0.114 |
cartridge | -0.111 |
ate | -0.107 |
ra | -0.104 |
ung | -0.101 |
Token | € |
Token ID | 26391 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
camel | +0.039 |
bus | +0.039 |
joy | +0.036 |
elephants | +0.035 |
vehicle | +0.035 |
Neg logit contributions | |
uts | -0.034 |
cartridge | -0.034 |
ate | -0.033 |
ra | -0.031 |
ung | -0.030 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
camel | +0.017 |
bus | +0.017 |
joy | +0.015 |
elephants | +0.015 |
vehicle | +0.015 |
Neg logit contributions | |
uts | -0.020 |
cartridge | -0.019 |
ate | -0.019 |
ra | -0.018 |
ung | -0.018 |
Token | s |
Token ID | 82 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
camel | +0.144 |
bus | +0.135 |
elephants | +0.133 |
vehicle | +0.129 |
desert | +0.128 |
Neg logit contributions | |
uts | -0.134 |
ung | -0.117 |
rap | -0.107 |
issors | -0.105 |
ra | -0.105 |
Token | dad |
Token ID | 9955 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
uts | +0.117 |
ra | +0.112 |
ate | +0.108 |
cartridge | +0.108 |
ung | +0.102 |
Neg logit contributions | |
camel | -0.120 |
bus | -0.112 |
joy | -0.111 |
elephants | -0.111 |
mo | -0.108 |
Token | shook |
Token ID | 14682 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
uts | +0.062 |
cartridge | +0.061 |
ra | +0.060 |
ate | +0.059 |
cutter | +0.055 |
Neg logit contributions | |
camel | -0.078 |
bus | -0.075 |
joy | -0.074 |
elephants | -0.070 |
desert | -0.069 |
Token | his |
Token ID | 465 |
Feature activation | -2.43e-04 |
Pos logit contributions | |
ate | +0.040 |
uts | +0.040 |
ra | +0.039 |
cartridge | +0.037 |
ung | +0.037 |
Neg logit contributions | |
camel | -0.063 |
bus | -0.060 |
elephants | -0.059 |
gir | -0.056 |
desert | -0.055 |
Token | spin |
Token ID | 7906 |
Feature activation | -7.59e-03 |
Pos logit contributions | |
camel | +0.002 |
bus | +0.002 |
joy | +0.002 |
elephants | +0.002 |
desert | +0.002 |
Neg logit contributions | |
uts | -0.002 |
cartridge | -0.002 |
ate | -0.002 |
ra | -0.002 |
rap | -0.002 |
Token | fast |
Token ID | 3049 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
uts | +0.011 |
cartridge | +0.010 |
ate | +0.010 |
ra | +0.010 |
rap | +0.010 |
Neg logit contributions | |
camel | -0.012 |
bus | -0.012 |
joy | -0.011 |
elephants | -0.011 |
desert | -0.011 |
Token | today |
Token ID | 1909 |
Feature activation | -2.34e-04 |
Pos logit contributions | |
camel | +0.018 |
bus | +0.017 |
joy | +0.017 |
elephants | +0.016 |
desert | +0.015 |
Neg logit contributions | |
uts | -0.019 |
cartridge | -0.019 |
ate | -0.019 |
ra | -0.018 |
cutter | -0.018 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
uts | +0.000 |
ate | +0.000 |
cartridge | +0.000 |
rap | +0.000 |
cutter | +0.000 |
Neg logit contributions | |
camel | -0.000 |
joy | -0.000 |
bus | -0.000 |
elephants | -0.000 |
mo | -0.000 |
Token | asked |
Token ID | 1965 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
bus | +0.017 |
camel | +0.017 |
joy | +0.015 |
elephants | +0.015 |
vehicle | +0.015 |
Neg logit contributions | |
uts | -0.017 |
cartridge | -0.017 |
ate | -0.016 |
rap | -0.015 |
ra | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
uts | +0.072 |
cartridge | +0.071 |
ate | +0.069 |
ra | +0.065 |
ung | +0.064 |
Neg logit contributions | |
bus | -0.067 |
camel | -0.067 |
joy | -0.062 |
vehicle | -0.058 |
elephants | -0.058 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
bus | +0.005 |
camel | +0.005 |
joy | +0.004 |
elephants | +0.004 |
year | +0.004 |
Neg logit contributions | |
uts | -0.005 |
cartridge | -0.005 |
ate | -0.005 |
ra | -0.004 |
cutter | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
bus | +0.022 |
camel | +0.022 |
joy | +0.021 |
merry | +0.020 |
desert | +0.020 |
Neg logit contributions | |
uts | -0.025 |
cartridge | -0.024 |
ate | -0.024 |
cutter | -0.023 |
ung | -0.023 |
Token | Ball |
Token ID | 6932 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
bus | +0.026 |
camel | +0.025 |
year | +0.024 |
vehicle | +0.023 |
joy | +0.023 |
Neg logit contributions | |
cartridge | -0.022 |
uts | -0.021 |
ate | -0.020 |
cutter | -0.020 |
connected | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +5.06e-03 |
Pos logit contributions | |
uts | +0.067 |
ate | +0.063 |
cartridge | +0.063 |
rap | +0.059 |
ung | +0.058 |
Neg logit contributions | |
camel | -0.053 |
bus | -0.053 |
joy | -0.050 |
elephants | -0.047 |
merry | -0.046 |
Token | " |
Token ID | 366 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
bus | +0.006 |
camel | +0.005 |
joy | +0.005 |
elephants | +0.005 |
vehicle | +0.005 |
Neg logit contributions | |
cartridge | -0.010 |
uts | -0.010 |
ate | -0.009 |
rap | -0.009 |
ra | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
uts | +0.003 |
ate | +0.003 |
cartridge | +0.003 |
ung | +0.003 |
issors | +0.003 |
Neg logit contributions | |
camel | -0.003 |
bus | -0.003 |
merry | -0.003 |
joy | -0.003 |
elephants | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
camel | +0.017 |
bus | +0.016 |
joy | +0.016 |
elephants | +0.015 |
vehicle | +0.014 |
Neg logit contributions | |
uts | -0.019 |
cartridge | -0.018 |
ate | -0.018 |
ra | -0.017 |
ung | -0.017 |
Token | so |
Token ID | 523 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
uts | +0.009 |
cartridge | +0.009 |
ate | +0.008 |
ra | +0.008 |
rap | +0.008 |
Neg logit contributions | |
bus | -0.009 |
camel | -0.009 |
joy | -0.008 |
elephants | -0.008 |
vehicle | -0.008 |
Token | much |
Token ID | 881 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
camel | +0.074 |
bus | +0.071 |
elephants | +0.065 |
joy | +0.063 |
vehicle | +0.062 |
Neg logit contributions | |
uts | -0.074 |
ate | -0.068 |
ung | -0.065 |
matters | -0.062 |
cartridge | -0.062 |
Token | fun |
Token ID | 1257 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
bus | +0.012 |
joy | +0.011 |
camel | +0.011 |
vehicle | +0.011 |
year | +0.011 |
Neg logit contributions | |
uts | -0.014 |
cartridge | -0.014 |
ra | -0.014 |
rap | -0.013 |
ate | -0.013 |
Token | recording |
Token ID | 8296 |
Feature activation | -7.39e-05 |
Pos logit contributions | |
uts | +0.066 |
cartridge | +0.065 |
ate | +0.062 |
ra | +0.059 |
rap | +0.059 |
Neg logit contributions | |
bus | -0.063 |
camel | -0.061 |
joy | -0.058 |
vehicle | -0.055 |
elephants | -0.055 |
Token | his |
Token ID | 465 |
Feature activation | +9.23e-04 |
Pos logit contributions | |
uts | +0.000 |
cartridge | +0.000 |
ate | +0.000 |
ung | +0.000 |
ra | +0.000 |
Neg logit contributions | |
bus | -0.000 |
camel | -0.000 |
joy | -0.000 |
vehicle | -0.000 |
elephants | -0.000 |
Token | voice |
Token ID | 3809 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
bus | +0.001 |
vehicle | +0.001 |
camel | +0.001 |
merry | +0.001 |
year | +0.001 |
Neg logit contributions | |
uts | -0.002 |
cartridge | -0.002 |
ung | -0.002 |
ate | -0.002 |
ressing | -0.001 |
Token | over |
Token ID | 625 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
camel | +0.110 |
bus | +0.108 |
joy | +0.102 |
elephants | +0.095 |
vehicle | +0.095 |
Neg logit contributions | |
uts | -0.130 |
cartridge | -0.125 |
ate | -0.120 |
ra | -0.116 |
ung | -0.114 |
Token | and |
Token ID | 290 |
Feature activation | -9.88e-04 |
Pos logit contributions | |
uts | +0.020 |
cartridge | +0.019 |
ate | +0.019 |
ra | +0.018 |
cutter | +0.018 |
Neg logit contributions | |
camel | -0.021 |
bus | -0.020 |
elephants | -0.018 |
merry | -0.018 |
taxi | -0.018 |
Token | over |
Token ID | 625 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
ra | +0.001 |
rap | +0.001 |
Neg logit contributions | |
bus | -0.001 |
camel | -0.001 |
joy | -0.001 |
elephants | -0.001 |
vehicle | -0.001 |
Token | completely |
Token ID | 3190 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
cartridge | +0.007 |
ra | +0.007 |
uts | +0.007 |
sealed | +0.007 |
connected | +0.006 |
Neg logit contributions | |
camel | -0.009 |
joy | -0.008 |
bus | -0.008 |
desert | -0.008 |
elephants | -0.008 |
Token | disappeared |
Token ID | 12120 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
uts | +0.069 |
cartridge | +0.067 |
ate | +0.064 |
ra | +0.061 |
ung | +0.061 |
Neg logit contributions | |
bus | -0.064 |
camel | -0.063 |
joy | -0.058 |
elephants | -0.057 |
vehicle | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
uts | +0.044 |
cartridge | +0.042 |
ate | +0.040 |
ung | +0.039 |
ra | +0.039 |
Neg logit contributions | |
bus | -0.051 |
camel | -0.050 |
elephants | -0.046 |
vehicle | -0.046 |
joy | -0.045 |
Token | Then |
Token ID | 3244 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
uts | +0.023 |
cartridge | +0.022 |
ate | +0.021 |
ra | +0.021 |
ung | +0.020 |
Neg logit contributions | |
bus | -0.019 |
camel | -0.019 |
joy | -0.017 |
elephants | -0.017 |
vehicle | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -2.85e-03 |
Pos logit contributions | |
uts | +0.156 |
cartridge | +0.154 |
ate | +0.147 |
ra | +0.143 |
ung | +0.140 |
Neg logit contributions | |
bus | -0.137 |
camel | -0.136 |
joy | -0.126 |
elephants | -0.121 |
vehicle | -0.119 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
uts | +0.004 |
cartridge | +0.004 |
ate | +0.004 |
ra | +0.004 |
ung | +0.004 |
Neg logit contributions | |
bus | -0.004 |
camel | -0.004 |
joy | -0.004 |
elephants | -0.004 |
vehicle | -0.004 |
Token | fairy |
Token ID | 25607 |
Feature activation | +9.60e-04 |
Pos logit contributions | |
camel | +0.014 |
bus | +0.014 |
joy | +0.014 |
inspection | +0.012 |
merry | +0.012 |
Neg logit contributions | |
cartridge | -0.022 |
ra | -0.021 |
ate | -0.021 |
uts | -0.021 |
cutter | -0.021 |
Token | waved |
Token ID | 26834 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
bus | +0.001 |
camel | +0.001 |
joy | +0.001 |
vehicle | +0.001 |
merry | +0.001 |
Neg logit contributions | |
cartridge | -0.001 |
uts | -0.001 |
ate | -0.001 |
ra | -0.001 |
ung | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
bus | +0.102 |
camel | +0.100 |
elephants | +0.093 |
desert | +0.092 |
sandbox | +0.092 |
Neg logit contributions | |
cartridge | -0.105 |
uts | -0.104 |
ra | -0.100 |
ung | -0.097 |
ate | -0.095 |
Token | wand |
Token ID | 11569 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
uts | +0.030 |
cartridge | +0.030 |
ate | +0.028 |
ra | +0.027 |
rap | +0.026 |
Neg logit contributions | |
bus | -0.036 |
camel | -0.035 |
joy | -0.033 |
elephants | -0.032 |
vehicle | -0.032 |
Token | once |
Token ID | 1752 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
uts | +0.070 |
cartridge | +0.069 |
ate | +0.065 |
ra | +0.062 |
ung | +0.062 |
Neg logit contributions | |
bus | -0.067 |
camel | -0.066 |
joy | -0.062 |
elephants | -0.059 |
vehicle | -0.059 |
Token | It |
Token ID | 632 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
uts | +0.015 |
cartridge | +0.014 |
ate | +0.014 |
ra | +0.013 |
ung | +0.013 |
Neg logit contributions | |
bus | -0.016 |
camel | -0.016 |
joy | -0.015 |
vehicle | -0.014 |
year | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
uts | +0.020 |
cartridge | +0.020 |
ate | +0.019 |
rap | +0.018 |
ra | +0.018 |
Neg logit contributions | |
bus | -0.016 |
camel | -0.016 |
joy | -0.015 |
elephants | -0.014 |
vehicle | -0.014 |
Token | so |
Token ID | 523 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
uts | +0.005 |
cartridge | +0.004 |
ate | +0.004 |
ressing | +0.004 |
check | +0.004 |
Neg logit contributions | |
camel | -0.002 |
bus | -0.002 |
elephants | -0.002 |
merry | -0.002 |
desert | -0.002 |
Token | pretty |
Token ID | 2495 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
bus | +0.051 |
camel | +0.051 |
joy | +0.046 |
elephants | +0.044 |
merry | +0.044 |
Neg logit contributions | |
cartridge | -0.068 |
uts | -0.068 |
ate | -0.064 |
ra | -0.062 |
rap | -0.062 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
cartridge | +0.078 |
uts | +0.076 |
ate | +0.073 |
ra | +0.071 |
rap | +0.070 |
Neg logit contributions | |
bus | -0.070 |
camel | -0.069 |
joy | -0.062 |
elephants | -0.062 |
vehicle | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
camel | +0.004 |
bus | +0.004 |
mo | +0.004 |
vehicle | +0.004 |
joy | +0.004 |
Neg logit contributions | |
uts | -0.003 |
cartridge | -0.003 |
ate | -0.003 |
ung | -0.003 |
ra | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
cartridge | +0.041 |
uts | +0.040 |
ate | +0.037 |
ra | +0.037 |
rap | +0.036 |
Neg logit contributions | |
bus | -0.029 |
camel | -0.028 |
joy | -0.025 |
year | -0.025 |
vehicle | -0.025 |
Token | Sam |
Token ID | 16305 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
cartridge | +0.038 |
uts | +0.037 |
ate | +0.034 |
rap | +0.034 |
ra | +0.033 |
Neg logit contributions | |
bus | -0.033 |
camel | -0.032 |
sandbox | -0.029 |
year | -0.029 |
taxi | -0.029 |
Token | came |
Token ID | 1625 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
uts | +0.004 |
cartridge | +0.004 |
ate | +0.004 |
ra | +0.004 |
rap | +0.004 |
Neg logit contributions | |
bus | -0.003 |
camel | -0.003 |
joy | -0.003 |
elephants | -0.002 |
vehicle | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +5.07e-03 |
Pos logit contributions | |
bus | +0.052 |
camel | +0.052 |
joy | +0.048 |
elephants | +0.047 |
vehicle | +0.047 |
Neg logit contributions | |
uts | -0.042 |
ate | -0.040 |
cartridge | -0.040 |
ra | -0.038 |
rap | -0.038 |
Token | see |
Token ID | 766 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
camel | +0.009 |
bus | +0.009 |
mo | +0.009 |
year | +0.008 |
vehicle | +0.008 |
Neg logit contributions | |
ate | -0.006 |
cartridge | -0.006 |
ra | -0.005 |
rap | -0.005 |
fold | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -7.92e-04 |
Pos logit contributions | |
bus | +0.022 |
camel | +0.022 |
joy | +0.021 |
elephants | +0.020 |
vehicle | +0.020 |
Neg logit contributions | |
uts | -0.022 |
cartridge | -0.021 |
ate | -0.020 |
ra | -0.020 |
cutter | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
uts | +0.001 |
cartridge | +0.001 |
ate | +0.001 |
ra | +0.001 |
rap | +0.001 |
Neg logit contributions | |
bus | -0.001 |
camel | -0.001 |
joy | -0.001 |
elephants | -0.001 |
vehicle | -0.001 |
Token | family |
Token ID | 1641 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
camel | +0.029 |
mo | +0.026 |
polar | +0.026 |
joy | +0.025 |
enced | +0.025 |
Neg logit contributions | |
ra | -0.025 |
ate | -0.025 |
cutter | -0.023 |
cartridge | -0.023 |
connected | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.51e-04 |
Pos logit contributions | |
uts | +0.012 |
cartridge | +0.012 |
ate | +0.012 |
ra | +0.011 |
rap | +0.011 |
Neg logit contributions | |
bus | -0.010 |
camel | -0.010 |
joy | -0.009 |
elephants | -0.009 |
vehicle | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
bus | +0.000 |
camel | +0.000 |
joy | +0.000 |
elephants | +0.000 |
year | +0.000 |
Neg logit contributions | |
uts | -0.001 |
cartridge | -0.001 |
ate | -0.001 |
ra | -0.001 |
rap | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
cartridge | +0.035 |
uts | +0.034 |
ra | +0.032 |
cutter | +0.032 |
ressing | +0.031 |
Neg logit contributions | |
bus | -0.021 |
camel | -0.021 |
year | -0.021 |
joy | -0.020 |
taxi | -0.019 |
Token | When |
Token ID | 2215 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
cartridge | +0.031 |
uts | +0.030 |
cutter | +0.027 |
ra | +0.027 |
rap | +0.026 |
Neg logit contributions | |
year | -0.027 |
bus | -0.026 |
camel | -0.025 |
joy | -0.025 |
taxi | -0.024 |
Token | they |
Token ID | 484 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
uts | +0.141 |
cartridge | +0.137 |
ate | +0.130 |
rap | +0.123 |
ra | +0.123 |
Neg logit contributions | |
bus | -0.138 |
camel | -0.135 |
joy | -0.129 |
year | -0.122 |
taxi | -0.121 |
Token | got |
Token ID | 1392 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
bus | +0.012 |
camel | +0.011 |
joy | +0.010 |
taxi | +0.010 |
vehicle | +0.010 |
Neg logit contributions | |
uts | -0.021 |
cartridge | -0.020 |
ate | -0.020 |
ra | -0.019 |
rap | -0.019 |
Token | home |
Token ID | 1363 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
uts | +0.044 |
cartridge | +0.043 |
ate | +0.041 |
ra | +0.039 |
rap | +0.039 |
Neg logit contributions | |
bus | -0.039 |
camel | -0.038 |
joy | -0.037 |
taxi | -0.035 |
vehicle | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
uts | +0.051 |
ate | +0.049 |
cartridge | +0.048 |
ung | +0.046 |
ra | +0.045 |
Neg logit contributions | |
camel | -0.046 |
bus | -0.044 |
elephants | -0.043 |
gir | -0.041 |
mo | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
uts | +0.008 |
ate | +0.008 |
cartridge | +0.008 |
rap | +0.007 |
ung | +0.007 |
Neg logit contributions | |
camel | -0.009 |
bus | -0.009 |
joy | -0.008 |
elephants | -0.008 |
mo | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
uts | +0.002 |
cartridge | +0.002 |
ate | +0.002 |
cutter | +0.002 |
ung | +0.002 |
Neg logit contributions | |
camel | -0.002 |
bus | -0.002 |
joy | -0.002 |
merry | -0.002 |
vehicle | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
joy | +0.041 |
mo | +0.036 |
merry | +0.035 |
camel | +0.034 |
hi | +0.033 |
Neg logit contributions | |
cartridge | -0.051 |
ate | -0.049 |
connected | -0.045 |
ra | -0.044 |
cutter | -0.044 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
joy | +0.038 |
bus | +0.036 |
merry | +0.035 |
mo | +0.035 |
hi | +0.035 |
Neg logit contributions | |
cartridge | -0.068 |
cutter | -0.061 |
ate | -0.060 |
ra | -0.057 |
connected | -0.057 |
Token | was |
Token ID | 373 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
bus | +0.052 |
camel | +0.051 |
joy | +0.045 |
vehicle | +0.043 |
elephants | +0.043 |
Neg logit contributions | |
uts | -0.097 |
cartridge | -0.096 |
ate | -0.092 |
rap | -0.089 |
ra | -0.088 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
uts | +0.005 |
cartridge | +0.004 |
ate | +0.004 |
ra | +0.004 |
ung | +0.004 |
Neg logit contributions | |
bus | -0.003 |
camel | -0.003 |
joy | -0.003 |
vehicle | -0.003 |
elephants | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
uts | +0.019 |
cartridge | +0.017 |
ate | +0.017 |
ra | +0.015 |
rap | +0.015 |
Neg logit contributions | |
camel | -0.023 |
bus | -0.023 |
joy | -0.021 |
mo | -0.021 |
vehicle | -0.021 |
Token | She |
Token ID | 1375 |
Feature activation | +6.55e-03 |
Pos logit contributions | |
uts | +0.021 |
cartridge | +0.021 |
ate | +0.020 |
ra | +0.019 |
rap | +0.019 |
Neg logit contributions | |
bus | -0.012 |
camel | -0.012 |
joy | -0.011 |
elephants | -0.010 |
vehicle | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
bus | +0.008 |
camel | +0.008 |
joy | +0.007 |
vehicle | +0.007 |
year | +0.006 |
Neg logit contributions | |
uts | -0.013 |
cartridge | -0.012 |
ate | -0.012 |
rap | -0.011 |
ung | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
joy | +0.125 |
mo | +0.120 |
bus | +0.119 |
camel | +0.116 |
year | +0.115 |
Neg logit contributions | |
ate | -0.087 |
uts | -0.087 |
cartridge | -0.079 |
connected | -0.075 |
ourselves | -0.073 |
Token | many |
Token ID | 867 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
bus | +0.052 |
camel | +0.051 |
joy | +0.048 |
vehicle | +0.045 |
elephants | +0.045 |
Neg logit contributions | |
uts | -0.079 |
ate | -0.075 |
cartridge | -0.074 |
rap | -0.070 |
ra | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | -4.75e-03 |
Pos logit contributions | |
uts | +0.003 |
cartridge | +0.003 |
ate | +0.003 |
ra | +0.003 |
rap | +0.003 |
Neg logit contributions | |
camel | -0.003 |
bus | -0.003 |
joy | -0.003 |
elephants | -0.002 |
vehicle | -0.002 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
uts | +0.009 |
cartridge | +0.008 |
ate | +0.008 |
ung | +0.008 |
rap | +0.008 |
Neg logit contributions | |
bus | -0.006 |
camel | -0.006 |
taxi | -0.005 |
vehicle | -0.005 |
joy | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
bus | +0.018 |
camel | +0.018 |
joy | +0.016 |
elephants | +0.016 |
vehicle | +0.016 |
Neg logit contributions | |
uts | -0.020 |
cartridge | -0.020 |
ate | -0.019 |
ra | -0.018 |
ung | -0.018 |
Token | new |
Token ID | 649 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
cartridge | +0.041 |
uts | +0.040 |
ate | +0.038 |
cutter | +0.037 |
ra | +0.036 |
Neg logit contributions | |
camel | -0.033 |
bus | -0.032 |
joy | -0.032 |
mo | -0.030 |
elephants | -0.030 |
Token | navy |
Token ID | 23956 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
camel | +0.047 |
bus | +0.044 |
joy | +0.044 |
mo | +0.043 |
elephants | +0.041 |
Neg logit contributions | |
cartridge | -0.053 |
ate | -0.051 |
uts | -0.051 |
cutter | -0.049 |
ra | -0.048 |
Token | blue |
Token ID | 4171 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
camel | +0.014 |
bus | +0.014 |
joy | +0.014 |
mo | +0.012 |
elephants | +0.012 |
Neg logit contributions | |
cartridge | -0.018 |
uts | -0.018 |
ate | -0.018 |
ra | -0.017 |
cutter | -0.016 |
Token | boat |
Token ID | 8848 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
uts | +0.008 |
cartridge | +0.008 |
ate | +0.008 |
ra | +0.008 |
cutter | +0.007 |
Neg logit contributions | |
camel | -0.007 |
bus | -0.006 |
joy | -0.006 |
elephants | -0.006 |
merry | -0.006 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
bus | +0.022 |
camel | +0.020 |
vehicle | +0.018 |
taxi | +0.018 |
elephants | +0.018 |
Neg logit contributions | |
cartridge | -0.032 |
uts | -0.031 |
ate | -0.031 |
rap | -0.030 |
ra | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
bus | +0.004 |
camel | +0.003 |
joy | +0.003 |
elephants | +0.003 |
mo | +0.003 |
Neg logit contributions | |
uts | -0.003 |
cartridge | -0.003 |
ate | -0.003 |
ra | -0.003 |
ung | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
uts | +0.036 |
cartridge | +0.035 |
ate | +0.033 |
ra | +0.032 |
rap | +0.032 |
Neg logit contributions | |
bus | -0.031 |
camel | -0.031 |
joy | -0.029 |
vehicle | -0.027 |
elephants | -0.027 |
Token | Tim |
Token ID | 14967 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
uts | +0.038 |
cartridge | +0.038 |
ate | +0.035 |
ung | +0.034 |
ra | +0.034 |
Neg logit contributions | |
bus | -0.028 |
camel | -0.028 |
vehicle | -0.025 |
year | -0.025 |
joy | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
uts | +0.025 |
cartridge | +0.024 |
ate | +0.023 |
ra | +0.022 |
rap | +0.022 |
Neg logit contributions | |
bus | -0.027 |
camel | -0.027 |
joy | -0.025 |
elephants | -0.024 |
vehicle | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +6.57e-03 |
Pos logit contributions | |
uts | +0.005 |
cartridge | +0.004 |
ate | +0.004 |
ra | +0.004 |
rap | +0.004 |
Neg logit contributions | |
camel | -0.004 |
bus | -0.004 |
joy | -0.004 |
elephants | -0.004 |
vehicle | -0.004 |
Token | bin |
Token ID | 9874 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
camel | +0.008 |
joy | +0.008 |
hi | +0.008 |
bus | +0.008 |
inspection | +0.008 |
Neg logit contributions | |
cartridge | -0.011 |
ate | -0.010 |
ra | -0.010 |
cutter | -0.010 |
connected | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -9.51e-03 |
Pos logit contributions | |
camel | +0.099 |
joy | +0.094 |
bus | +0.092 |
merry | +0.088 |
mo | +0.087 |
Neg logit contributions | |
uts | -0.086 |
ate | -0.079 |
ung | -0.075 |
cartridge | -0.073 |
connected | -0.071 |
Token | never |
Token ID | 1239 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
uts | +0.015 |
cartridge | +0.015 |
ate | +0.014 |
ra | +0.014 |
rap | +0.013 |
Neg logit contributions | |
bus | -0.014 |
camel | -0.014 |
joy | -0.013 |
vehicle | -0.012 |
elephants | -0.012 |
Token | tried |
Token ID | 3088 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
bus | +0.053 |
camel | +0.052 |
vehicle | +0.050 |
joy | +0.049 |
taxi | +0.048 |
Neg logit contributions | |
uts | -0.045 |
cartridge | -0.042 |
connected | -0.040 |
ra | -0.040 |
cutter | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | +8.68e-03 |
Pos logit contributions | |
uts | +0.053 |
cartridge | +0.049 |
ate | +0.048 |
rap | +0.045 |
ra | +0.044 |
Neg logit contributions | |
bus | -0.066 |
camel | -0.065 |
joy | -0.059 |
vehicle | -0.058 |
year | -0.058 |
Token | cook |
Token ID | 4255 |
Feature activation | +3.58e-03 |
Pos logit contributions | |
bus | +0.014 |
camel | +0.014 |
joy | +0.014 |
elephants | +0.013 |
vehicle | +0.012 |
Neg logit contributions | |
uts | -0.012 |
cartridge | -0.012 |
ate | -0.012 |
ra | -0.011 |
rap | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
bus | +0.006 |
camel | +0.005 |
joy | +0.005 |
elephants | +0.005 |
vehicle | +0.005 |
Neg logit contributions | |
uts | -0.005 |
cartridge | -0.005 |
ate | -0.005 |
ra | -0.005 |
rap | -0.005 |
Token | le |
Token ID | 443 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
bus | +0.006 |
camel | +0.006 |
joy | +0.005 |
elephants | +0.005 |
vehicle | +0.005 |
Neg logit contributions | |
uts | -0.005 |
cartridge | -0.005 |
ate | -0.005 |
ra | -0.005 |
rap | -0.005 |
Token | mons |
Token ID | 11567 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
uts | +0.041 |
cartridge | +0.039 |
ate | +0.034 |
ra | +0.029 |
rap | +0.028 |
Neg logit contributions | |
bus | -0.191 |
camel | -0.189 |
joy | -0.182 |
elephants | -0.177 |
vehicle | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
uts | +0.031 |
cartridge | +0.030 |
ate | +0.029 |
ra | +0.028 |
rap | +0.028 |
Neg logit contributions | |
bus | -0.030 |
camel | -0.030 |
joy | -0.028 |
elephants | -0.027 |
vehicle | -0.026 |
Token | He |
Token ID | 1544 |
Feature activation | -3.14e-04 |
Pos logit contributions | |
uts | +0.030 |
cartridge | +0.030 |
ate | +0.028 |
ra | +0.027 |
rap | +0.026 |
Neg logit contributions | |
bus | -0.031 |
camel | -0.031 |
joy | -0.029 |
vehicle | -0.028 |
year | -0.027 |
Token | ran |
Token ID | 4966 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
uts | +0.000 |
cartridge | +0.000 |
ate | +0.000 |
ra | +0.000 |
cutter | +0.000 |
Neg logit contributions | |
bus | -0.000 |
camel | -0.000 |
joy | -0.000 |
elephants | -0.000 |
vehicle | -0.000 |
Token | as |
Token ID | 355 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
bus | +0.093 |
camel | +0.089 |
joy | +0.084 |
vehicle | +0.081 |
taxi | +0.081 |
Neg logit contributions | |
uts | -0.091 |
cartridge | -0.091 |
ate | -0.086 |
ra | -0.082 |
rap | -0.081 |
Token | fast |
Token ID | 3049 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
uts | +0.185 |
cartridge | +0.183 |
ate | +0.174 |
ra | +0.165 |
rap | +0.165 |
Neg logit contributions | |
bus | -0.161 |
camel | -0.159 |
joy | -0.147 |
vehicle | -0.141 |
elephants | -0.140 |
Token | as |
Token ID | 355 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
bus | +0.023 |
camel | +0.023 |
joy | +0.022 |
elephants | +0.021 |
vehicle | +0.021 |
Neg logit contributions | |
uts | -0.013 |
cartridge | -0.012 |
ate | -0.012 |
rap | -0.011 |
ra | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
uts | +0.206 |
cartridge | +0.199 |
ate | +0.194 |
ra | +0.187 |
rap | +0.185 |
Neg logit contributions | |
bus | -0.137 |
camel | -0.136 |
joy | -0.125 |
elephants | -0.117 |
vehicle | -0.116 |
Token | could |
Token ID | 714 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
bus | +0.030 |
camel | +0.029 |
joy | +0.028 |
elephants | +0.027 |
vehicle | +0.027 |
Neg logit contributions | |
uts | -0.021 |
cartridge | -0.020 |
ate | -0.019 |
ra | -0.018 |
rap | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
uts | +0.152 |
cartridge | +0.139 |
ate | +0.135 |
ung | +0.134 |
ra | +0.129 |
Neg logit contributions | |
camel | -0.117 |
bus | -0.116 |
elephants | -0.108 |
joy | -0.105 |
vehicle | -0.103 |
Token | it |
Token ID | 340 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
uts | +0.003 |
cartridge | +0.002 |
cutter | +0.002 |
ra | +0.002 |
connected | +0.002 |
Neg logit contributions | |
camel | -0.003 |
bus | -0.003 |
year | -0.003 |
joy | -0.003 |
taxi | -0.003 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
uts | +0.013 |
cartridge | +0.013 |
ate | +0.013 |
rap | +0.012 |
ra | +0.012 |
Neg logit contributions | |
bus | -0.011 |
camel | -0.011 |
joy | -0.010 |
vehicle | -0.010 |
elephants | -0.010 |
Token | noticed |
Token ID | 6810 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
bus | +0.047 |
camel | +0.045 |
joy | +0.043 |
vehicle | +0.043 |
year | +0.042 |
Neg logit contributions | |
cartridge | -0.049 |
uts | -0.049 |
connected | -0.046 |
ra | -0.045 |
ressing | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
camel | +0.061 |
bus | +0.061 |
merry | +0.055 |
taxi | +0.053 |
sandbox | +0.053 |
Neg logit contributions | |
ate | -0.038 |
uts | -0.038 |
cartridge | -0.035 |
rap | -0.035 |
ra | -0.034 |
Token | bird |
Token ID | 6512 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
bus | +0.019 |
camel | +0.019 |
hi | +0.018 |
joy | +0.018 |
year | +0.018 |
Neg logit contributions | |
cartridge | -0.029 |
ate | -0.027 |
connected | -0.027 |
ra | -0.027 |
cutter | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
camel | +0.103 |
bus | +0.102 |
joy | +0.097 |
elephants | +0.092 |
vehicle | +0.089 |
Neg logit contributions | |
uts | -0.087 |
connected | -0.082 |
ra | -0.080 |
cartridge | -0.078 |
ung | -0.076 |
Token | still |
Token ID | 991 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
uts | +0.007 |
cartridge | +0.007 |
ate | +0.007 |
ung | +0.006 |
ra | +0.006 |
Neg logit contributions | |
bus | -0.008 |
camel | -0.008 |
joy | -0.007 |
elephants | -0.007 |
vehicle | -0.007 |
Token | stuck |
Token ID | 7819 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
uts | +0.182 |
cartridge | +0.179 |
ate | +0.172 |
ra | +0.165 |
ung | +0.163 |
Neg logit contributions | |
bus | -0.166 |
camel | -0.164 |
joy | -0.147 |
elephants | -0.147 |
vehicle | -0.144 |
Token | on |
Token ID | 319 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
cartridge | +0.156 |
uts | +0.156 |
ate | +0.146 |
ra | +0.144 |
ung | +0.141 |
Neg logit contributions | |
camel | -0.203 |
bus | -0.202 |
elephants | -0.184 |
vehicle | -0.178 |
merry | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
camel | +0.036 |
bus | +0.036 |
joy | +0.033 |
vehicle | +0.032 |
mo | +0.031 |
Neg logit contributions | |
uts | -0.031 |
cartridge | -0.030 |
ate | -0.029 |
ra | -0.029 |
rap | -0.028 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
joy | +0.026 |
year | +0.024 |
camel | +0.024 |
hi | +0.023 |
bus | +0.023 |
Neg logit contributions | |
cartridge | -0.026 |
cutter | -0.024 |
uts | -0.023 |
ra | -0.023 |
connected | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -7.45e-03 |
Pos logit contributions | |
camel | +0.015 |
bus | +0.015 |
joy | +0.014 |
elephants | +0.013 |
merry | +0.013 |
Neg logit contributions | |
uts | -0.017 |
cartridge | -0.016 |
ate | -0.015 |
ra | -0.014 |
ung | -0.014 |
Token | The |
Token ID | 383 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
uts | +0.012 |
cartridge | +0.011 |
ate | +0.011 |
ung | +0.010 |
ra | +0.010 |
Neg logit contributions | |
camel | -0.011 |
bus | -0.011 |
merry | -0.010 |
elephants | -0.010 |
vehicle | -0.010 |
Token | M |
Token ID | 337 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
bus | +0.019 |
camel | +0.019 |
joy | +0.018 |
elephants | +0.017 |
vehicle | +0.017 |
Neg logit contributions | |
uts | -0.020 |
cartridge | -0.020 |
ate | -0.019 |
ra | -0.018 |
rap | -0.018 |
Token | ummy |
Token ID | 13513 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
bus | +0.011 |
camel | +0.011 |
merry | +0.010 |
joy | +0.010 |
parking | +0.010 |
Neg logit contributions | |
uts | -0.008 |
ate | -0.007 |
ra | -0.007 |
rap | -0.007 |
ung | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
uts | +0.082 |
cartridge | +0.080 |
ate | +0.077 |
rap | +0.073 |
ra | +0.073 |
Neg logit contributions | |
bus | -0.079 |
camel | -0.078 |
joy | -0.070 |
vehicle | -0.069 |
elephants | -0.069 |
Token | it |
Token ID | 340 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
uts | +0.049 |
ra | +0.044 |
cartridge | +0.044 |
ung | +0.042 |
ate | +0.042 |
Neg logit contributions | |
bus | -0.047 |
camel | -0.045 |
joy | -0.043 |
elephants | -0.043 |
desert | -0.042 |
Token | would |
Token ID | 561 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
uts | +0.014 |
cartridge | +0.014 |
ate | +0.014 |
rap | +0.013 |
ra | +0.013 |
Neg logit contributions | |
bus | -0.010 |
camel | -0.009 |
joy | -0.008 |
vehicle | -0.008 |
elephants | -0.008 |
Token | work |
Token ID | 670 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
bus | +0.061 |
camel | +0.058 |
vehicle | +0.051 |
joy | +0.051 |
elephants | +0.051 |
Neg logit contributions | |
uts | -0.078 |
cartridge | -0.076 |
ate | -0.073 |
ung | -0.070 |
rap | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
uts | +0.201 |
cartridge | +0.198 |
ate | +0.190 |
ra | +0.181 |
rap | +0.180 |
Neg logit contributions | |
bus | -0.170 |
camel | -0.166 |
joy | -0.154 |
vehicle | -0.147 |
elephants | -0.147 |
Token | something |
Token ID | 1223 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
uts | +0.006 |
cartridge | +0.006 |
ate | +0.005 |
ung | +0.005 |
rap | +0.005 |
Neg logit contributions | |
bus | -0.005 |
camel | -0.005 |
joy | -0.005 |
elephants | -0.005 |
vehicle | -0.005 |
Token | special |
Token ID | 2041 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
bus | +0.035 |
camel | +0.035 |
joy | +0.032 |
vehicle | +0.031 |
elephants | +0.031 |
Neg logit contributions | |
uts | -0.034 |
cartridge | -0.033 |
ate | -0.032 |
ra | -0.031 |
rap | -0.030 |
Token | would |
Token ID | 561 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
uts | +0.086 |
cartridge | +0.085 |
ate | +0.081 |
rap | +0.081 |
ung | +0.079 |
Neg logit contributions | |
bus | -0.055 |
camel | -0.051 |
year | -0.047 |
vehicle | -0.046 |
elephants | -0.045 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
bus | +0.068 |
camel | +0.066 |
joy | +0.060 |
elephants | +0.059 |
vehicle | +0.059 |
Neg logit contributions | |
uts | -0.069 |
cartridge | -0.068 |
ate | -0.065 |
ung | -0.062 |
ra | -0.061 |
Token | But |
Token ID | 1537 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
uts | +0.031 |
cartridge | +0.030 |
ate | +0.029 |
ra | +0.027 |
rap | +0.027 |
Neg logit contributions | |
bus | -0.037 |
camel | -0.037 |
joy | -0.035 |
elephants | -0.033 |
vehicle | -0.033 |
Token | then |
Token ID | 788 |
Feature activation | -9.78e-03 |
Pos logit contributions | |
uts | +0.003 |
cartridge | +0.003 |
ate | +0.003 |
ra | +0.003 |
rap | +0.003 |
Neg logit contributions | |
bus | -0.003 |
camel | -0.003 |
joy | -0.003 |
elephants | -0.003 |
vehicle | -0.003 |
Token | their |
Token ID | 511 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
uts | +0.015 |
cartridge | +0.014 |
ate | +0.014 |
ra | +0.014 |
ung | +0.014 |
Neg logit contributions | |
bus | -0.014 |
camel | -0.014 |
joy | -0.013 |
merry | -0.013 |
vehicle | -0.013 |
Token | car |
Token ID | 1097 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
uts | +0.049 |
cartridge | +0.048 |
ate | +0.046 |
ra | +0.045 |
rap | +0.043 |
Neg logit contributions | |
bus | -0.051 |
camel | -0.051 |
joy | -0.048 |
elephants | -0.046 |
vehicle | -0.045 |
Token | got |
Token ID | 1392 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
camel | +0.069 |
bus | +0.066 |
joy | +0.065 |
elephants | +0.061 |
merry | +0.061 |
Neg logit contributions | |
uts | -0.071 |
cartridge | -0.068 |
ra | -0.065 |
ung | -0.065 |
ate | -0.064 |
Token | stuck |
Token ID | 7819 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
uts | +0.044 |
cartridge | +0.042 |
ate | +0.041 |
rap | +0.039 |
ra | +0.039 |
Neg logit contributions | |
bus | -0.043 |
camel | -0.042 |
joy | -0.039 |
vehicle | -0.038 |
elephants | -0.037 |
Token | in |
Token ID | 287 |
Feature activation | -3.60e-04 |
Pos logit contributions | |
uts | +0.167 |
cartridge | +0.164 |
ate | +0.157 |
ra | +0.150 |
ung | +0.148 |
Neg logit contributions | |
camel | -0.174 |
bus | -0.172 |
joy | -0.158 |
elephants | -0.154 |
vehicle | -0.151 |
Token | the |
Token ID | 262 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
uts | +0.001 |
cartridge | +0.001 |
ate | +0.000 |
ra | +0.000 |
rap | +0.000 |
Neg logit contributions | |
camel | -0.001 |
bus | -0.001 |
joy | -0.001 |
elephants | -0.000 |
mo | -0.000 |
Token | mud |
Token ID | 17492 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
joy | +0.030 |
inspection | +0.028 |
camel | +0.027 |
hi | +0.027 |
hello | +0.026 |
Neg logit contributions | |
cartridge | -0.030 |
connected | -0.027 |
ra | -0.027 |
ate | -0.027 |
cutter | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-04 |
Pos logit contributions | |
uts | +0.089 |
cartridge | +0.084 |
ate | +0.078 |
cutter | +0.077 |
ung | +0.077 |
Neg logit contributions | |
camel | -0.083 |
joy | -0.081 |
bus | -0.080 |
hi | -0.074 |
merry | -0.073 |
Token | Cindy |
Token ID | 39062 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
camel | +0.000 |
bus | +0.000 |
joy | +0.000 |
elephants | +0.000 |
merry | +0.000 |
Neg logit contributions | |
uts | -0.000 |
cartridge | -0.000 |
ate | -0.000 |
ra | -0.000 |
ung | -0.000 |
Token | walked |
Token ID | 6807 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
bus | +0.015 |
camel | +0.014 |
joy | +0.014 |
elephants | +0.013 |
vehicle | +0.013 |
Neg logit contributions | |
uts | -0.016 |
cartridge | -0.016 |
ate | -0.016 |
ra | -0.016 |
connected | -0.015 |
Token | through |
Token ID | 832 |
Feature activation | +5.37e-03 |
Pos logit contributions | |
camel | +0.143 |
bus | +0.141 |
joy | +0.133 |
elephants | +0.131 |
vehicle | +0.130 |
Neg logit contributions | |
cartridge | -0.094 |
ate | -0.093 |
uts | -0.092 |
rap | -0.084 |
ra | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
camel | +0.010 |
bus | +0.010 |
vehicle | +0.009 |
mo | +0.009 |
joy | +0.009 |
Neg logit contributions | |
ate | -0.006 |
ra | -0.005 |
connected | -0.005 |
uts | -0.005 |
cartridge | -0.005 |
Token | tall |
Token ID | 7331 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
joy | +0.027 |
camel | +0.025 |
bus | +0.025 |
hi | +0.025 |
mo | +0.023 |
Neg logit contributions | |
ate | -0.031 |
cartridge | -0.030 |
connected | -0.028 |
ra | -0.028 |
cutter | -0.027 |
Token | st |
Token ID | 336 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
joy | +0.054 |
hi | +0.051 |
camel | +0.050 |
bus | +0.049 |
mo | +0.048 |
Neg logit contributions | |
ate | -0.061 |
cutter | -0.058 |
ra | -0.058 |
cartridge | -0.056 |
uts | -0.055 |
Token | alks |
Token ID | 23833 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
bus | +0.007 |
camel | +0.007 |
joy | +0.007 |
elephants | +0.007 |
vehicle | +0.007 |
Neg logit contributions | |
cartridge | -0.004 |
uts | -0.004 |
ate | -0.003 |
ra | -0.003 |
rap | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
uts | +0.242 |
cartridge | +0.230 |
ate | +0.217 |
ung | +0.208 |
cutter | +0.207 |
Neg logit contributions | |
camel | -0.211 |
bus | -0.210 |
joy | -0.195 |
vehicle | -0.190 |
elephants | -0.187 |
Token | corn |
Token ID | 11676 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
bus | +0.034 |
camel | +0.034 |
mo | +0.033 |
joy | +0.032 |
vehicle | +0.031 |
Neg logit contributions | |
ate | -0.025 |
cartridge | -0.023 |
connected | -0.023 |
cutter | -0.022 |
ra | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
uts | +0.046 |
cartridge | +0.045 |
ate | +0.044 |
ra | +0.042 |
cutter | +0.041 |
Neg logit contributions | |
bus | -0.035 |
camel | -0.034 |
joy | -0.032 |
vehicle | -0.030 |
taxi | -0.030 |
Token | discovered |
Token ID | 5071 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
cartridge | +0.002 |
uts | +0.002 |
ate | +0.002 |
ra | +0.002 |
cutter | +0.002 |
Neg logit contributions | |
bus | -0.002 |
camel | -0.002 |
joy | -0.001 |
vehicle | -0.001 |
taxi | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
ate | +0.013 |
uts | +0.013 |
connected | +0.011 |
ourselves | +0.011 |
cartridge | +0.011 |
Neg logit contributions | |
bus | -0.022 |
joy | -0.021 |
camel | -0.020 |
vehicle | -0.019 |
mo | -0.019 |