Token | too |
Token ID | 1165 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ruck | +0.014 |
Tim | +0.013 |
John | +0.013 |
emergency | +0.013 |
Tom | +0.012 |
Neg logit contributions | |
violet | -0.011 |
pir | -0.011 |
Flor | -0.011 |
Sparkle | -0.010 |
Nad | -0.010 |
Token | high |
Token ID | 1029 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
violet | +0.011 |
delighted | +0.011 |
mesmer | +0.011 |
pir | +0.011 |
highest | +0.010 |
Neg logit contributions | |
ruck | -0.016 |
Tim | -0.015 |
emergency | -0.015 |
John | -0.014 |
leaning | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Tim | +0.090 |
John | +0.088 |
ruck | +0.085 |
Tom | +0.084 |
Billy | +0.083 |
Neg logit contributions | |
violet | -0.037 |
Sparkle | -0.036 |
Flor | -0.036 |
pro | -0.034 |
pir | -0.034 |
Token | too |
Token ID | 1165 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.012 |
John | +0.011 |
Tom | +0.011 |
emergency | +0.011 |
Neg logit contributions | |
violet | -0.014 |
Flor | -0.014 |
pir | -0.014 |
Nad | -0.013 |
superstar | -0.013 |
Token | w |
Token ID | 266 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.004 |
delighted | +0.004 |
mesmer | +0.004 |
pro | +0.004 |
Neg logit contributions | |
ruck | -0.006 |
Tim | -0.006 |
emergency | -0.006 |
John | -0.005 |
irens | -0.005 |
Token | obb |
Token ID | 21963 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
ruck | +0.052 |
Tim | +0.047 |
John | +0.046 |
cut | +0.043 |
Billy | +0.042 |
Neg logit contributions | |
violet | -0.052 |
hips | -0.050 |
Nad | -0.049 |
wrists | -0.048 |
highest | -0.047 |
Token | ly |
Token ID | 306 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
John | +0.170 |
Tim | +0.158 |
emergency | +0.146 |
Billy | +0.143 |
ruck | +0.139 |
Neg logit contributions | |
pro | -0.208 |
violet | -0.202 |
ind | -0.199 |
tail | -0.198 |
Flor | -0.197 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ruck | +0.103 |
Tim | +0.099 |
John | +0.094 |
emergency | +0.090 |
irens | +0.088 |
Neg logit contributions | |
violet | -0.104 |
pir | -0.100 |
Flor | -0.099 |
delighted | -0.095 |
mesmer | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
John | +0.001 |
emergency | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
violet | -0.001 |
pir | -0.000 |
Flor | -0.000 |
Sparkle | -0.000 |
delighted | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ruck | +0.014 |
Tim | +0.013 |
John | +0.012 |
emergency | +0.012 |
Tom | +0.012 |
Neg logit contributions | |
violet | -0.015 |
pir | -0.015 |
Flor | -0.015 |
Sparkle | -0.014 |
delighted | -0.014 |
Token | fell |
Token ID | 3214 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ruck | +0.032 |
Tim | +0.030 |
John | +0.027 |
emergency | +0.027 |
Tom | +0.027 |
Neg logit contributions | |
violet | -0.042 |
Flor | -0.040 |
pir | -0.040 |
Sparkle | -0.038 |
Nad | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
ruck | +0.006 |
Tim | +0.005 |
John | +0.005 |
emergency | +0.005 |
Tom | +0.005 |
Neg logit contributions | |
violet | -0.011 |
pir | -0.010 |
Flor | -0.010 |
superstar | -0.009 |
Nad | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
violet | +0.036 |
pir | +0.035 |
Flor | +0.034 |
superstar | +0.033 |
mesmer | +0.033 |
Neg logit contributions | |
ruck | -0.028 |
Tim | -0.025 |
John | -0.024 |
emergency | -0.023 |
Tom | -0.023 |
Token | park |
Token ID | 3952 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ruck | +0.005 |
Tim | +0.005 |
dd | +0.005 |
John | +0.005 |
irens | +0.004 |
Neg logit contributions | |
violet | -0.004 |
pir | -0.004 |
Flor | -0.004 |
tail | -0.004 |
Sparkle | -0.004 |
Token | many |
Token ID | 867 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.006 |
Flor | +0.005 |
superstar | +0.005 |
Nad | +0.005 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.003 |
John | -0.003 |
emergency | -0.003 |
Tom | -0.003 |
Token | years |
Token ID | 812 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.017 |
John | +0.015 |
emergency | +0.015 |
Tom | +0.015 |
Neg logit contributions | |
violet | -0.023 |
pir | -0.022 |
Flor | -0.022 |
Sparkle | -0.021 |
Nad | -0.021 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
ruck | +0.056 |
Tim | +0.053 |
John | +0.049 |
emergency | +0.048 |
Tom | +0.047 |
Neg logit contributions | |
violet | -0.059 |
Flor | -0.058 |
pir | -0.057 |
delighted | -0.055 |
Sparkle | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ruck | +0.184 |
Tim | +0.174 |
John | +0.162 |
emergency | +0.161 |
irens | +0.158 |
Neg logit contributions | |
violet | -0.194 |
pir | -0.187 |
Flor | -0.186 |
delighted | -0.180 |
mesmer | -0.178 |
Token | Toby |
Token ID | 37578 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ruck | +0.007 |
Tim | +0.006 |
John | +0.006 |
Tom | +0.006 |
irens | +0.006 |
Neg logit contributions | |
violet | -0.006 |
pir | -0.006 |
mesmer | -0.006 |
Flor | -0.006 |
delighted | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ruck | +0.009 |
Tim | +0.009 |
John | +0.008 |
Tom | +0.008 |
dd | +0.008 |
Neg logit contributions | |
violet | -0.012 |
pir | -0.011 |
Flor | -0.011 |
tail | -0.011 |
superstar | -0.010 |
Token | amazed |
Token ID | 24562 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
John | +0.009 |
ruck | +0.009 |
emergency | +0.008 |
his | +0.008 |
Tim | +0.008 |
Neg logit contributions | |
violet | -0.009 |
tail | -0.008 |
pir | -0.008 |
Want | -0.008 |
superstar | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
violet | +0.023 |
Flor | +0.022 |
pir | +0.022 |
delighted | +0.022 |
mesmer | +0.022 |
Neg logit contributions | |
ruck | -0.025 |
Tim | -0.024 |
emergency | -0.022 |
John | -0.022 |
irens | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ruck | +0.036 |
Tim | +0.033 |
John | +0.031 |
emergency | +0.031 |
Tom | +0.031 |
Neg logit contributions | |
violet | -0.035 |
Flor | -0.034 |
pir | -0.034 |
Sparkle | -0.033 |
Nad | -0.032 |
Token | birthday |
Token ID | 10955 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ruck | +0.016 |
Tim | +0.014 |
emergency | +0.013 |
John | +0.013 |
Tom | +0.013 |
Neg logit contributions | |
violet | -0.023 |
pir | -0.021 |
Flor | -0.021 |
Nad | -0.020 |
Sparkle | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
violet | +0.051 |
pir | +0.049 |
Flor | +0.048 |
mesmer | +0.047 |
delighted | +0.046 |
Neg logit contributions | |
ruck | -0.032 |
Tim | -0.029 |
John | -0.027 |
Tom | -0.026 |
emergency | -0.026 |
Token | few |
Token ID | 1178 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
violet | +0.002 |
Flor | +0.002 |
pir | +0.002 |
mesmer | +0.002 |
tail | +0.002 |
Neg logit contributions | |
ruck | -0.002 |
Tim | -0.001 |
John | -0.001 |
emergency | -0.001 |
Tom | -0.001 |
Token | days |
Token ID | 1528 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
violet | +0.040 |
Flor | +0.038 |
pir | +0.038 |
Sparkle | +0.036 |
Nad | +0.036 |
Neg logit contributions | |
ruck | -0.024 |
Tim | -0.021 |
John | -0.019 |
emergency | -0.019 |
Tom | -0.019 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
ruck | +0.057 |
Tim | +0.052 |
John | +0.049 |
emergency | +0.048 |
Tom | +0.047 |
Neg logit contributions | |
violet | -0.068 |
pir | -0.065 |
Flor | -0.065 |
Sparkle | -0.062 |
Nad | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
ruck | +0.184 |
Tim | +0.174 |
emergency | +0.163 |
John | +0.162 |
irens | +0.158 |
Neg logit contributions | |
violet | -0.191 |
pir | -0.183 |
Flor | -0.182 |
delighted | -0.175 |
Nad | -0.173 |
Token | She |
Token ID | 1375 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
Tim | +0.002 |
ruck | +0.002 |
John | +0.002 |
Tom | +0.002 |
irens | +0.002 |
Neg logit contributions | |
violet | -0.002 |
pir | -0.002 |
Flor | -0.002 |
superstar | -0.002 |
tail | -0.002 |
Token | liked |
Token ID | 8288 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
violet | +0.032 |
Flor | +0.031 |
pir | +0.030 |
tail | +0.030 |
Sparkle | +0.029 |
Neg logit contributions | |
ruck | -0.027 |
Tim | -0.026 |
John | -0.025 |
Tom | -0.024 |
dd | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
ruck | +0.025 |
Tim | +0.022 |
John | +0.021 |
emergency | +0.021 |
Tom | +0.020 |
Neg logit contributions | |
violet | -0.028 |
Flor | -0.027 |
pir | -0.026 |
tail | -0.026 |
superstar | -0.025 |
Token | practice |
Token ID | 3357 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
violet | +0.023 |
Flor | +0.022 |
pir | +0.022 |
mesmer | +0.021 |
Nad | +0.021 |
Neg logit contributions | |
ruck | -0.027 |
Tim | -0.025 |
John | -0.024 |
Tom | -0.023 |
emergency | -0.023 |
Token | ac |
Token ID | 936 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
violet | +0.014 |
pir | +0.013 |
Flor | +0.013 |
superstar | +0.013 |
Violet | +0.013 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.006 |
emergency | -0.005 |
waste | -0.005 |
Tom | -0.005 |
Token | orn |
Token ID | 1211 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ruck | +0.012 |
Tim | +0.010 |
John | +0.010 |
emergency | +0.010 |
Tom | +0.009 |
Neg logit contributions | |
violet | -0.024 |
pir | -0.023 |
Flor | -0.023 |
Sparkle | -0.023 |
Nad | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
ruck | +0.003 |
Tim | +0.003 |
emergency | +0.003 |
tools | +0.003 |
cream | +0.003 |
Neg logit contributions | |
violet | -0.005 |
pir | -0.005 |
Flor | -0.005 |
Nad | -0.005 |
superstar | -0.005 |
Token | few |
Token ID | 1178 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Violet | +0.018 |
violet | +0.018 |
Flor | +0.018 |
Julia | +0.018 |
Alicia | +0.018 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.013 |
waste | -0.012 |
emergency | -0.012 |
garbage | -0.011 |
Token | days |
Token ID | 1528 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
violet | +0.046 |
pir | +0.044 |
Flor | +0.043 |
superstar | +0.042 |
Sparkle | +0.042 |
Neg logit contributions | |
ruck | -0.040 |
Tim | -0.037 |
emergency | -0.034 |
John | -0.033 |
Tom | -0.033 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
ruck | +0.061 |
Tim | +0.055 |
John | +0.052 |
Tom | +0.051 |
emergency | +0.050 |
Neg logit contributions | |
violet | -0.064 |
pir | -0.062 |
Flor | -0.062 |
superstar | -0.059 |
Sparkle | -0.059 |
Token | so |
Token ID | 523 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ruck | +0.184 |
Tim | +0.168 |
John | +0.158 |
emergency | +0.155 |
Tom | +0.154 |
Neg logit contributions | |
violet | -0.198 |
pir | -0.191 |
Flor | -0.190 |
Sparkle | -0.181 |
superstar | -0.180 |
Token | I |
Token ID | 314 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.005 |
Flor | +0.005 |
superstar | +0.005 |
Sparkle | +0.005 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
John | -0.009 |
Tom | -0.009 |
emergency | -0.009 |
Token | could |
Token ID | 714 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.017 |
waste | +0.016 |
Tom | +0.016 |
dd | +0.015 |
Neg logit contributions | |
violet | -0.018 |
pir | -0.017 |
Flor | -0.016 |
Sparkle | -0.016 |
Nice | -0.016 |
Token | have |
Token ID | 423 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
ruck | +0.020 |
waste | +0.020 |
Tim | +0.020 |
repair | +0.019 |
emergency | +0.018 |
Neg logit contributions | |
pir | -0.027 |
violet | -0.027 |
Nice | -0.026 |
superstar | -0.026 |
Nad | -0.026 |
Token | some |
Token ID | 617 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
violet | +0.013 |
pir | +0.012 |
superstar | +0.012 |
Flor | +0.012 |
tail | +0.012 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
Tom | -0.008 |
John | -0.008 |
dd | -0.008 |
Token | flyer |
Token ID | 42464 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
violet | +0.021 |
pir | +0.020 |
Flor | +0.020 |
Sparkle | +0.019 |
Nad | +0.019 |
Neg logit contributions | |
ruck | -0.018 |
Tim | -0.017 |
John | -0.016 |
emergency | -0.015 |
Tom | -0.015 |
Token | posted |
Token ID | 4481 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
violet | +0.031 |
pir | +0.030 |
Flor | +0.030 |
Nad | +0.029 |
Sparkle | +0.028 |
Neg logit contributions | |
ruck | -0.027 |
Tim | -0.025 |
John | -0.023 |
emergency | -0.023 |
Tom | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.012 |
John | +0.011 |
emergency | +0.011 |
dd | +0.011 |
Neg logit contributions | |
violet | -0.011 |
Flor | -0.011 |
pir | -0.011 |
Sparkle | -0.010 |
delighted | -0.010 |
Token | few |
Token ID | 1178 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
violet | +0.027 |
Flor | +0.026 |
pir | +0.025 |
Nad | +0.024 |
Sparkle | +0.024 |
Neg logit contributions | |
ruck | -0.025 |
Tim | -0.022 |
emergency | -0.022 |
John | -0.021 |
Tom | -0.020 |
Token | days |
Token ID | 1528 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
violet | +0.050 |
pir | +0.049 |
Flor | +0.048 |
delighted | +0.047 |
mesmer | +0.046 |
Neg logit contributions | |
ruck | -0.043 |
Tim | -0.042 |
John | -0.038 |
Tom | -0.037 |
emergency | -0.036 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ruck | +0.055 |
Tim | +0.055 |
emergency | +0.051 |
John | +0.051 |
Tom | +0.050 |
Neg logit contributions | |
violet | -0.048 |
pir | -0.047 |
delighted | -0.046 |
mesmer | -0.046 |
Flor | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ruck | +0.188 |
Tim | +0.186 |
emergency | +0.173 |
John | +0.169 |
irens | +0.167 |
Neg logit contributions | |
violet | -0.162 |
pir | -0.158 |
delighted | -0.155 |
Flor | -0.154 |
mesmer | -0.152 |
Token | looking |
Token ID | 2045 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
Flor | +0.003 |
Nad | +0.003 |
Sparkle | +0.003 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
John | -0.004 |
emergency | -0.004 |
Tom | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ruck | +0.042 |
Tim | +0.039 |
John | +0.037 |
Tom | +0.036 |
emergency | +0.036 |
Neg logit contributions | |
violet | -0.032 |
pir | -0.031 |
Flor | -0.031 |
Sparkle | -0.029 |
delighted | -0.029 |
Token | help |
Token ID | 1037 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ruck | +0.034 |
Tim | +0.032 |
John | +0.030 |
Tom | +0.030 |
irens | +0.029 |
Neg logit contributions | |
Flor | -0.034 |
violet | -0.034 |
pir | -0.033 |
Sparkle | -0.032 |
Nad | -0.032 |
Token | around |
Token ID | 1088 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
pir | +0.001 |
Flor | +0.001 |
Sparkle | +0.001 |
violet | +0.001 |
tail | +0.001 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.001 |
dd | -0.001 |
John | -0.001 |
Tom | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
pir | +0.013 |
violet | +0.013 |
superstar | +0.012 |
delighted | +0.012 |
wrists | +0.012 |
Neg logit contributions | |
Tim | -0.019 |
ruck | -0.019 |
John | -0.018 |
Tom | -0.018 |
emergency | -0.017 |
Token | built |
Token ID | 3170 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
violet | +0.007 |
pir | +0.007 |
Flor | +0.007 |
wrists | +0.006 |
Nad | +0.006 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.007 |
Tom | -0.006 |
dd | -0.006 |
emergency | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ruck | +0.023 |
Tim | +0.021 |
John | +0.020 |
emergency | +0.020 |
Tom | +0.020 |
Neg logit contributions | |
violet | -0.024 |
Flor | -0.024 |
pir | -0.024 |
Sparkle | -0.022 |
Nad | -0.022 |
Token | many |
Token ID | 867 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
violet | +0.012 |
Nad | +0.011 |
pir | +0.011 |
Flor | +0.011 |
superstar | +0.011 |
Neg logit contributions | |
ruck | -0.011 |
Tim | -0.010 |
emergency | -0.009 |
John | -0.009 |
tools | -0.009 |
Token | years |
Token ID | 812 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ruck | +0.011 |
Tim | +0.010 |
emergency | +0.010 |
John | +0.010 |
Tom | +0.009 |
Neg logit contributions | |
violet | -0.015 |
Flor | -0.014 |
pir | -0.014 |
superstar | -0.013 |
Sparkle | -0.013 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ruck | +0.042 |
Tim | +0.038 |
John | +0.035 |
emergency | +0.035 |
Tom | +0.034 |
Neg logit contributions | |
violet | -0.054 |
pir | -0.052 |
Flor | -0.051 |
Sparkle | -0.049 |
Nad | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
ruck | +0.173 |
Tim | +0.154 |
John | +0.146 |
emergency | +0.142 |
Tom | +0.141 |
Neg logit contributions | |
violet | -0.200 |
pir | -0.193 |
Flor | -0.192 |
superstar | -0.184 |
Sparkle | -0.183 |
Token | I |
Token ID | 314 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
ruck | +0.025 |
Tim | +0.023 |
John | +0.022 |
emergency | +0.021 |
Tom | +0.021 |
Neg logit contributions | |
violet | -0.021 |
pir | -0.020 |
Flor | -0.020 |
superstar | -0.019 |
Nad | -0.019 |
Token | am |
Token ID | 716 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
ruck | +0.003 |
Tim | +0.003 |
John | +0.003 |
Tom | +0.003 |
emergency | +0.003 |
Neg logit contributions | |
violet | -0.003 |
pir | -0.003 |
Flor | -0.003 |
Sparkle | -0.003 |
Nad | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
pir | +0.020 |
violet | +0.019 |
tail | +0.019 |
Nice | +0.019 |
wrists | +0.019 |
Neg logit contributions | |
ruck | -0.019 |
emergency | -0.017 |
John | -0.016 |
waste | -0.016 |
fires | -0.015 |
Token | proud |
Token ID | 6613 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
tail | +0.003 |
Flor | +0.003 |
Sparkle | +0.003 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.003 |
John | -0.003 |
emergency | -0.003 |
dd | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
violet | +0.019 |
Flor | +0.019 |
pir | +0.018 |
Sparkle | +0.018 |
Nad | +0.018 |
Neg logit contributions | |
ruck | -0.021 |
dd | -0.019 |
Tim | -0.019 |
emergency | -0.019 |
irens | -0.018 |
Token | wardrobe |
Token ID | 35593 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
violet | +0.004 |
pir | +0.004 |
Flor | +0.004 |
Sparkle | +0.003 |
Nad | +0.003 |
Neg logit contributions | |
ruck | -0.005 |
Tim | -0.005 |
John | -0.005 |
irens | -0.005 |
dd | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
violet | +0.012 |
pir | +0.011 |
Flor | +0.011 |
Sparkle | +0.011 |
Nad | +0.011 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
John | -0.008 |
emergency | -0.008 |
Tom | -0.008 |
Token | few |
Token ID | 1178 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
violet | +0.010 |
Flor | +0.010 |
pir | +0.010 |
Nad | +0.009 |
Sparkle | +0.009 |
Neg logit contributions | |
ruck | -0.009 |
Tim | -0.009 |
emergency | -0.008 |
John | -0.008 |
Tom | -0.008 |
Token | days |
Token ID | 1528 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
violet | +0.042 |
pir | +0.042 |
Flor | +0.041 |
delighted | +0.039 |
Nad | +0.039 |
Neg logit contributions | |
ruck | -0.037 |
Tim | -0.034 |
John | -0.032 |
Tom | -0.031 |
emergency | -0.030 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
ruck | +0.056 |
Tim | +0.054 |
John | +0.051 |
emergency | +0.051 |
Tom | +0.049 |
Neg logit contributions | |
violet | -0.045 |
pir | -0.043 |
Flor | -0.042 |
delighted | -0.042 |
mesmer | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
ruck | +0.189 |
Tim | +0.183 |
emergency | +0.172 |
John | +0.171 |
irens | +0.167 |
Neg logit contributions | |
violet | -0.165 |
pir | -0.159 |
Flor | -0.156 |
delighted | -0.155 |
mesmer | -0.151 |
Token | so |
Token ID | 523 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
ruck | +0.011 |
Tim | +0.010 |
John | +0.009 |
emergency | +0.009 |
Tom | +0.009 |
Neg logit contributions | |
violet | -0.009 |
Flor | -0.009 |
pir | -0.009 |
superstar | -0.008 |
Nad | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
violet | +0.018 |
pir | +0.017 |
Flor | +0.017 |
Sparkle | +0.016 |
Nad | +0.016 |
Neg logit contributions | |
ruck | -0.030 |
Tim | -0.028 |
John | -0.026 |
emergency | -0.026 |
Tom | -0.026 |
Token | opened |
Token ID | 4721 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.014 |
Flor | +0.014 |
Nad | +0.013 |
Sparkle | +0.013 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.013 |
John | -0.012 |
emergency | -0.012 |
Tom | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
violet | +0.008 |
pir | +0.008 |
Flor | +0.008 |
superstar | +0.008 |
delighted | +0.008 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.007 |
John | -0.006 |
Tom | -0.006 |
emergency | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
ruck | +0.010 |
Tim | +0.010 |
Tom | +0.009 |
John | +0.009 |
emergency | +0.009 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.009 |
Flor | -0.009 |
Sparkle | -0.008 |
Nad | -0.008 |
Token | breakfast |
Token ID | 12607 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ruck | +0.000 |
Tim | +0.000 |
John | +0.000 |
emergency | +0.000 |
Tom | +0.000 |
Neg logit contributions | |
violet | -0.001 |
pir | -0.001 |
Flor | -0.001 |
Sparkle | -0.001 |
superstar | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
violet | +0.023 |
Flor | +0.022 |
pir | +0.022 |
Sparkle | +0.021 |
superstar | +0.021 |
Neg logit contributions | |
ruck | -0.030 |
Tim | -0.028 |
John | -0.027 |
Tom | -0.027 |
emergency | -0.027 |
Token | little |
Token ID | 1310 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ruck | +0.020 |
Tim | +0.020 |
emergency | +0.020 |
waste | +0.018 |
Tom | +0.018 |
Neg logit contributions | |
violet | -0.025 |
Flor | -0.025 |
mesmer | -0.024 |
pir | -0.024 |
Sparkle | -0.024 |
Token | while |
Token ID | 981 |
Feature activation | -6.92e-03 |
Pos logit contributions | |
ruck | +0.040 |
Tim | +0.038 |
emergency | +0.037 |
waste | +0.036 |
cream | +0.035 |
Neg logit contributions | |
violet | -0.036 |
pir | -0.034 |
Flor | -0.034 |
Sparkle | -0.033 |
Nad | -0.033 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
violet | +0.000 |
pir | +0.000 |
Flor | +0.000 |
superstar | +0.000 |
Sparkle | +0.000 |
Neg logit contributions | |
ruck | -0.000 |
Tim | -0.000 |
John | -0.000 |
emergency | -0.000 |
Tom | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ruck | +0.194 |
Tim | +0.180 |
John | +0.170 |
emergency | +0.168 |
Tom | +0.165 |
Neg logit contributions | |
violet | -0.171 |
pir | -0.164 |
Flor | -0.163 |
Sparkle | -0.154 |
Nad | -0.153 |
Token | so |
Token ID | 523 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
ruck | +0.011 |
Tim | +0.011 |
John | +0.011 |
Tom | +0.011 |
emergency | +0.010 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.008 |
Flor | -0.008 |
tail | -0.008 |
superstar | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
violet | +0.012 |
pir | +0.011 |
Flor | +0.011 |
superstar | +0.010 |
Sparkle | +0.010 |
Neg logit contributions | |
ruck | -0.018 |
Tim | -0.017 |
John | -0.017 |
Tom | -0.016 |
emergency | -0.016 |
Token | 'm |
Token ID | 1101 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
ruck | +0.006 |
Tim | +0.006 |
Tom | +0.006 |
John | +0.006 |
emergency | +0.005 |
Neg logit contributions | |
violet | -0.006 |
pir | -0.005 |
Flor | -0.005 |
Sparkle | -0.005 |
Nad | -0.005 |
Token | not |
Token ID | 407 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
violet | +0.030 |
pir | +0.030 |
tail | +0.029 |
Flor | +0.028 |
Nice | +0.028 |
Neg logit contributions | |
ruck | -0.027 |
emergency | -0.026 |
John | -0.024 |
Tim | -0.023 |
dd | -0.023 |
Token | it |
Token ID | 340 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.017 |
emergency | +0.016 |
tools | +0.015 |
Tom | +0.015 |
Neg logit contributions | |
violet | -0.017 |
pir | -0.016 |
superstar | -0.015 |
delighted | -0.015 |
mesmer | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.006 |
Nad | +0.006 |
Flor | +0.006 |
wrists | +0.006 |
Neg logit contributions | |
emergency | -0.006 |
Tim | -0.006 |
ruck | -0.006 |
waste | -0.006 |
garbage | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
pir | +0.020 |
violet | +0.020 |
superstar | +0.020 |
tail | +0.019 |
Nice | +0.019 |
Neg logit contributions | |
ruck | -0.018 |
emergency | -0.017 |
Tim | -0.016 |
fires | -0.016 |
garbage | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
ruck | +0.050 |
Tim | +0.046 |
John | +0.044 |
emergency | +0.043 |
Tom | +0.043 |
Neg logit contributions | |
violet | -0.039 |
pir | -0.037 |
Flor | -0.036 |
Sparkle | -0.034 |
Nad | -0.034 |
Token | minute |
Token ID | 5664 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
violet | +0.002 |
pir | +0.002 |
Flor | +0.002 |
Nad | +0.002 |
Sparkle | +0.002 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.001 |
emergency | -0.001 |
John | -0.001 |
Tom | -0.001 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
Flor | +0.003 |
Sparkle | +0.003 |
superstar | +0.003 |
Neg logit contributions | |
ruck | -0.002 |
Tim | -0.002 |
emergency | -0.002 |
John | -0.002 |
Tom | -0.002 |
Token | ." |
Token ID | 526 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ruck | +0.180 |
Tim | +0.166 |
John | +0.157 |
emergency | +0.154 |
Tom | +0.152 |
Neg logit contributions | |
violet | -0.185 |
pir | -0.177 |
Flor | -0.176 |
Sparkle | -0.167 |
Nad | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
violet | +0.013 |
Flor | +0.013 |
pir | +0.012 |
Sparkle | +0.012 |
Nad | +0.012 |
Neg logit contributions | |
ruck | -0.013 |
Tim | -0.012 |
John | -0.011 |
emergency | -0.011 |
dd | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
ruck | +0.044 |
emergency | +0.040 |
Tim | +0.038 |
dd | +0.038 |
John | +0.037 |
Neg logit contributions | |
violet | -0.025 |
Flor | -0.025 |
pir | -0.024 |
Sparkle | -0.023 |
delighted | -0.022 |
Token | They |
Token ID | 2990 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
ruck | +0.018 |
emergency | +0.016 |
dd | +0.014 |
ime | +0.013 |
irens | +0.013 |
Neg logit contributions | |
violet | -0.024 |
tail | -0.023 |
pir | -0.022 |
Flor | -0.022 |
Violet | -0.022 |
Token | heard |
Token ID | 2982 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
ruck | +0.023 |
Tim | +0.022 |
John | +0.020 |
Tom | +0.020 |
emergency | +0.020 |
Neg logit contributions | |
violet | -0.022 |
pir | -0.021 |
Flor | -0.020 |
Sparkle | -0.019 |
superstar | -0.019 |
Token | someone |
Token ID | 2130 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
violet | +0.001 |
Flor | +0.001 |
pir | +0.001 |
Sparkle | +0.001 |
Nad | +0.001 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.001 |
John | -0.001 |
emergency | -0.001 |
Tom | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ruck | +0.043 |
Tim | +0.040 |
emergency | +0.038 |
John | +0.038 |
Tom | +0.037 |
Neg logit contributions | |
violet | -0.036 |
pir | -0.034 |
Flor | -0.033 |
superstar | -0.032 |
Nad | -0.032 |
Token | very |
Token ID | 845 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
violet | +0.001 |
pir | +0.001 |
Flor | +0.001 |
Nad | +0.001 |
mesmer | +0.001 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.001 |
emergency | -0.001 |
John | -0.001 |
Tom | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
violet | +0.037 |
pir | +0.036 |
Flor | +0.035 |
delighted | +0.034 |
mesmer | +0.033 |
Neg logit contributions | |
ruck | -0.039 |
Tim | -0.036 |
John | -0.034 |
irens | -0.033 |
Tom | -0.033 |
Token | time |
Token ID | 640 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
ruck | +0.027 |
Tim | +0.025 |
John | +0.024 |
irens | +0.023 |
dd | +0.022 |
Neg logit contributions | |
violet | -0.036 |
pir | -0.035 |
Flor | -0.034 |
tail | -0.033 |
Sparkle | -0.033 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
ruck | +0.092 |
Tim | +0.083 |
John | +0.078 |
emergency | +0.077 |
Tom | +0.076 |
Neg logit contributions | |
violet | -0.101 |
pir | -0.097 |
Flor | -0.096 |
Sparkle | -0.092 |
superstar | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ruck | +0.179 |
Tim | +0.167 |
John | +0.156 |
emergency | +0.154 |
irens | +0.151 |
Neg logit contributions | |
violet | -0.181 |
pir | -0.174 |
Flor | -0.173 |
delighted | -0.165 |
Nad | -0.164 |
Token | The |
Token ID | 383 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
pir | +0.013 |
violet | +0.012 |
tail | +0.012 |
superstar | +0.012 |
mesmer | +0.011 |
Neg logit contributions | |
Tim | -0.011 |
ruck | -0.010 |
John | -0.010 |
Tom | -0.009 |
irens | -0.009 |
Token | little |
Token ID | 1310 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
violet | +0.002 |
Flor | +0.002 |
pir | +0.002 |
delighted | +0.002 |
Sparkle | +0.002 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.001 |
John | -0.001 |
irens | -0.001 |
dd | -0.001 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
violet | +0.021 |
pir | +0.020 |
Flor | +0.020 |
Sparkle | +0.019 |
mesmer | +0.019 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.013 |
John | -0.012 |
emergency | -0.012 |
Tom | -0.011 |
Token | thought |
Token ID | 1807 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
violet | +0.059 |
Flor | +0.056 |
Sparkle | +0.055 |
pir | +0.055 |
tail | +0.055 |
Neg logit contributions | |
Tim | -0.041 |
ruck | -0.041 |
John | -0.039 |
Tom | -0.038 |
dd | -0.035 |
Token | but |
Token ID | 475 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
violet | +0.000 |
pir | +0.000 |
Flor | +0.000 |
superstar | +0.000 |
Sparkle | +0.000 |
Neg logit contributions | |
ruck | -0.000 |
Tim | -0.000 |
Tom | -0.000 |
John | -0.000 |
emergency | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Tim | +0.025 |
ruck | +0.025 |
Tom | +0.023 |
John | +0.022 |
emergency | +0.022 |
Neg logit contributions | |
violet | -0.034 |
pir | -0.032 |
superstar | -0.031 |
tail | -0.031 |
Flor | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
ruck | +0.016 |
Tim | +0.016 |
Tom | +0.014 |
John | +0.014 |
emergency | +0.014 |
Neg logit contributions | |
violet | -0.020 |
Flor | -0.019 |
pir | -0.019 |
Sparkle | -0.018 |
superstar | -0.018 |
Token | too |
Token ID | 1165 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
ruck | +0.004 |
Tim | +0.004 |
emergency | +0.004 |
John | +0.004 |
Tom | +0.004 |
Neg logit contributions | |
violet | -0.002 |
pir | -0.002 |
Flor | -0.002 |
superstar | -0.002 |
tail | -0.002 |
Token | w |
Token ID | 266 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
violet | +0.010 |
highest | +0.009 |
pir | +0.008 |
mesmer | +0.008 |
delighted | +0.008 |
Neg logit contributions | |
ruck | -0.015 |
emergency | -0.013 |
John | -0.013 |
irens | -0.013 |
Tim | -0.013 |
Token | obb |
Token ID | 21963 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
ruck | +0.025 |
John | +0.023 |
Tim | +0.022 |
cut | +0.020 |
Billy | +0.019 |
Neg logit contributions | |
violet | -0.033 |
highest | -0.031 |
pir | -0.030 |
tail | -0.030 |
Flor | -0.030 |
Token | ly |
Token ID | 306 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
John | +0.151 |
Tim | +0.139 |
Billy | +0.123 |
Tom | +0.120 |
emergency | +0.120 |
Neg logit contributions | |
violet | -0.194 |
tail | -0.191 |
highest | -0.190 |
pro | -0.190 |
ind | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ruck | +0.088 |
Tim | +0.083 |
John | +0.079 |
emergency | +0.076 |
Tom | +0.075 |
Neg logit contributions | |
violet | -0.097 |
Flor | -0.093 |
pir | -0.093 |
Sparkle | -0.089 |
mesmer | -0.088 |
Token | They |
Token ID | 1119 |
Feature activation | +2.33e-03 |
Pos logit contributions | |
ruck | +0.005 |
Tim | +0.004 |
John | +0.004 |
emergency | +0.004 |
Tom | +0.004 |
Neg logit contributions | |
violet | -0.004 |
pir | -0.004 |
Flor | -0.004 |
Sparkle | -0.004 |
Nad | -0.004 |
Token | tried |
Token ID | 3088 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
ruck | +0.000 |
Tim | +0.000 |
John | +0.000 |
emergency | +0.000 |
irens | +0.000 |
Neg logit contributions | |
violet | -0.000 |
pir | -0.000 |
Flor | -0.000 |
Nad | -0.000 |
delighted | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
violet | +0.001 |
pir | +0.001 |
Flor | +0.001 |
Sparkle | +0.001 |
Nad | +0.001 |
Neg logit contributions | |
ruck | -0.002 |
Tim | -0.001 |
John | -0.001 |
emergency | -0.001 |
Tom | -0.001 |
Token | welcome |
Token ID | 7062 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
ruck | +0.036 |
Tim | +0.035 |
irens | +0.034 |
John | +0.033 |
Tom | +0.033 |
Neg logit contributions | |
violet | -0.030 |
Flor | -0.028 |
delighted | -0.028 |
mesmer | -0.028 |
pir | -0.028 |
Token | here |
Token ID | 994 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
violet | +0.008 |
Flor | +0.008 |
pir | +0.008 |
Sparkle | +0.008 |
Nad | +0.007 |
Neg logit contributions | |
ruck | -0.011 |
Tim | -0.010 |
John | -0.010 |
Tom | -0.009 |
irens | -0.009 |
Token | ." |
Token ID | 526 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ruck | +0.010 |
Tim | +0.009 |
John | +0.008 |
emergency | +0.008 |
Tom | +0.008 |
Neg logit contributions | |
violet | -0.012 |
pir | -0.011 |
Flor | -0.011 |
mesmer | -0.010 |
Nad | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
violet | +0.006 |
Flor | +0.006 |
pir | +0.005 |
Sparkle | +0.005 |
Nad | +0.005 |
Neg logit contributions | |
ruck | -0.008 |
Tim | -0.007 |
emergency | -0.007 |
John | -0.007 |
dd | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
ruck | +0.036 |
emergency | +0.033 |
fires | +0.031 |
dd | +0.031 |
garbage | +0.031 |
Neg logit contributions | |
Flor | -0.012 |
delighted | -0.011 |
violet | -0.011 |
Sparkle | -0.011 |
Violet | -0.010 |
Token | Un |
Token ID | 3118 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
ruck | +0.007 |
emergency | +0.007 |
fires | +0.006 |
consequences | +0.006 |
ime | +0.006 |
Neg logit contributions | |
delighted | -0.009 |
violet | -0.009 |
Rosa | -0.009 |
anytime | -0.008 |
Violet | -0.008 |
Token | cle |
Token ID | 2375 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
emergency | +0.148 |
waste | +0.146 |
garbage | +0.146 |
ruck | +0.142 |
junk | +0.138 |
Neg logit contributions | |
violet | -0.183 |
sometime | -0.176 |
tail | -0.174 |
seven | -0.171 |
anytime | -0.165 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ruck | +0.068 |
emergency | +0.062 |
dd | +0.060 |
irens | +0.059 |
agons | +0.057 |
Neg logit contributions | |
violet | -0.060 |
Flor | -0.059 |
delighted | -0.057 |
pir | -0.056 |
Nad | -0.056 |
Token | gr |
Token ID | 1036 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
ruck | +0.057 |
Tim | +0.052 |
emergency | +0.050 |
John | +0.050 |
irens | +0.049 |
Neg logit contributions | |
violet | -0.039 |
pir | -0.037 |
Flor | -0.037 |
delighted | -0.035 |
Nad | -0.035 |
Token | umbled |
Token ID | 11137 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
garbage | +0.031 |
Tim | +0.030 |
lumber | +0.030 |
junk | +0.029 |
fuel | +0.029 |
Neg logit contributions | |
delighted | -0.018 |
ectar | -0.018 |
mesmer | -0.018 |
agrees | -0.017 |
hesitant | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
ruck | +0.044 |
Tim | +0.042 |
dd | +0.041 |
John | +0.041 |
Tom | +0.039 |
Neg logit contributions | |
Flor | -0.025 |
delighted | -0.025 |
pir | -0.025 |
Sparkle | -0.025 |
lap | -0.024 |
Token | had |
Token ID | 550 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
violet | +0.002 |
pir | +0.002 |
Flor | +0.002 |
superstar | +0.002 |
Nad | +0.002 |
Neg logit contributions | |
ruck | -0.002 |
Tim | -0.002 |
John | -0.001 |
Tom | -0.001 |
emergency | -0.001 |
Token | been |
Token ID | 587 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
ruck | +0.004 |
Tim | +0.004 |
John | +0.004 |
emergency | +0.004 |
Tom | +0.003 |
Neg logit contributions | |
violet | -0.004 |
pir | -0.004 |
Flor | -0.004 |
Sparkle | -0.004 |
Nad | -0.004 |
Token | made |
Token ID | 925 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ruck | +0.025 |
Tim | +0.023 |
John | +0.022 |
Tom | +0.022 |
emergency | +0.022 |
Neg logit contributions | |
violet | -0.022 |
pir | -0.021 |
Flor | -0.021 |
delighted | -0.020 |
Sparkle | -0.020 |
Token | many |
Token ID | 867 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
ruck | +0.011 |
Tim | +0.010 |
John | +0.010 |
Tom | +0.009 |
emergency | +0.009 |
Neg logit contributions | |
violet | -0.012 |
pir | -0.012 |
Flor | -0.011 |
Sparkle | -0.011 |
delighted | -0.011 |
Token | years |
Token ID | 812 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ruck | +0.019 |
Tim | +0.018 |
dd | +0.018 |
John | +0.018 |
Tom | +0.017 |
Neg logit contributions | |
pir | -0.023 |
delighted | -0.021 |
violet | -0.021 |
mesmer | -0.021 |
highest | -0.021 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
ruck | +0.049 |
Tim | +0.048 |
John | +0.047 |
Stop | +0.044 |
Tom | +0.043 |
Neg logit contributions | |
violet | -0.050 |
pir | -0.050 |
Flor | -0.048 |
delighted | -0.047 |
mesmer | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ruck | +0.171 |
Tim | +0.163 |
John | +0.152 |
emergency | +0.152 |
Tom | +0.147 |
Neg logit contributions | |
violet | -0.181 |
pir | -0.174 |
Flor | -0.171 |
delighted | -0.167 |
mesmer | -0.165 |
Token | but |
Token ID | 475 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ruck | +0.007 |
Tim | +0.006 |
John | +0.006 |
Tom | +0.006 |
emergency | +0.006 |
Neg logit contributions | |
violet | -0.006 |
Flor | -0.006 |
pir | -0.006 |
superstar | -0.006 |
Nad | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Tim | +0.017 |
ruck | +0.017 |
emergency | +0.015 |
John | +0.015 |
Tom | +0.015 |
Neg logit contributions | |
violet | -0.023 |
pir | -0.023 |
superstar | -0.022 |
Flor | -0.022 |
tail | -0.021 |
Token | still |
Token ID | 991 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
ruck | +0.005 |
Tim | +0.004 |
John | +0.004 |
Tom | +0.004 |
emergency | +0.004 |
Neg logit contributions | |
violet | -0.005 |
Flor | -0.005 |
pir | -0.005 |
superstar | -0.005 |
Sparkle | -0.005 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
violet | +0.030 |
pir | +0.029 |
Flor | +0.029 |
Sparkle | +0.027 |
delighted | +0.027 |
Neg logit contributions | |
ruck | -0.035 |
Tim | -0.032 |
John | -0.031 |
emergency | -0.030 |
Tom | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ruck | +0.019 |
emergency | +0.018 |
Tim | +0.017 |
irens | +0.017 |
John | +0.016 |
Neg logit contributions | |
violet | -0.011 |
Flor | -0.011 |
pir | -0.011 |
Nad | -0.010 |
Sparkle | -0.010 |
Token | They |
Token ID | 2990 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ruck | +0.004 |
emergency | +0.004 |
tools | +0.003 |
ime | +0.003 |
earthquake | +0.003 |
Neg logit contributions | |
violet | -0.003 |
pir | -0.003 |
Flor | -0.003 |
mesmer | -0.003 |
Nad | -0.003 |
Token | get |
Token ID | 651 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
ruck | +0.008 |
Tim | +0.008 |
John | +0.007 |
emergency | +0.007 |
Tom | +0.007 |
Neg logit contributions | |
violet | -0.006 |
pir | -0.006 |
Flor | -0.006 |
Nad | -0.006 |
Sparkle | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
ruck | +0.028 |
Tim | +0.026 |
John | +0.025 |
Tom | +0.024 |
emergency | +0.024 |
Neg logit contributions | |
violet | -0.020 |
Flor | -0.019 |
pir | -0.019 |
delighted | -0.018 |
mesmer | -0.018 |
Token | m |
Token ID | 285 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
violet | +0.002 |
pir | +0.001 |
Flor | +0.001 |
Sparkle | +0.001 |
delighted | +0.001 |
Neg logit contributions | |
ruck | -0.002 |
Tim | -0.002 |
John | -0.002 |
emergency | -0.002 |
Tom | -0.002 |
Token | itt |
Token ID | 715 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.012 |
John | +0.012 |
emergency | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
violet | -0.013 |
pir | -0.012 |
Flor | -0.012 |
delighted | -0.012 |
tail | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ruck | +0.179 |
Tim | +0.169 |
John | +0.159 |
emergency | +0.156 |
Tom | +0.153 |
Neg logit contributions | |
violet | -0.179 |
pir | -0.171 |
Flor | -0.170 |
Sparkle | -0.161 |
Nad | -0.160 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-04 |
Pos logit contributions | |
ruck | +0.014 |
Tim | +0.013 |
waste | +0.012 |
tools | +0.012 |
Tom | +0.012 |
Neg logit contributions | |
violet | -0.020 |
superstar | -0.019 |
pir | -0.019 |
Nice | -0.018 |
Sparkle | -0.018 |
Token | spat |
Token ID | 15246 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ruck | +0.000 |
Tim | +0.000 |
emergency | +0.000 |
John | +0.000 |
Tom | +0.000 |
Neg logit contributions | |
violet | -0.000 |
Flor | -0.000 |
pir | -0.000 |
Sparkle | -0.000 |
mesmer | -0.000 |
Token | ula |
Token ID | 4712 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ruck | +0.032 |
Tim | +0.029 |
John | +0.028 |
emergency | +0.027 |
Tom | +0.027 |
Neg logit contributions | |
violet | -0.028 |
pir | -0.027 |
Flor | -0.027 |
Sparkle | -0.025 |
Nad | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
violet | +0.020 |
Flor | +0.019 |
pir | +0.019 |
Nad | +0.018 |
Sparkle | +0.018 |
Neg logit contributions | |
ruck | -0.019 |
Tim | -0.018 |
John | -0.017 |
emergency | -0.016 |
Tom | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
ruck | +0.025 |
Tim | +0.023 |
John | +0.022 |
emergency | +0.021 |
Tom | +0.021 |
Neg logit contributions | |
violet | -0.024 |
pir | -0.023 |
Flor | -0.023 |
Sparkle | -0.022 |
superstar | -0.022 |
Token | there |
Token ID | 612 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Flor | +0.027 |
violet | +0.027 |
pir | +0.026 |
delighted | +0.025 |
Sparkle | +0.025 |
Neg logit contributions | |
ruck | -0.033 |
irens | -0.029 |
emergency | -0.028 |
Tim | -0.027 |
iren | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
violet | +0.026 |
pir | +0.025 |
Flor | +0.025 |
Nad | +0.023 |
Sparkle | +0.023 |
Neg logit contributions | |
ruck | -0.027 |
Tim | -0.025 |
John | -0.024 |
emergency | -0.023 |
irens | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Flor | +0.002 |
violet | +0.002 |
pir | +0.002 |
delighted | +0.002 |
Sparkle | +0.002 |
Neg logit contributions | |
ruck | -0.002 |
irens | -0.002 |
emergency | -0.002 |
iren | -0.002 |
Tim | -0.002 |
Token | l |
Token ID | 300 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.011 |
irens | +0.011 |
John | +0.011 |
emergency | +0.010 |
Neg logit contributions | |
violet | -0.020 |
pir | -0.019 |
Flor | -0.019 |
superstar | -0.019 |
delighted | -0.018 |
Token | itt |
Token ID | 715 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
violet | +0.071 |
pir | +0.069 |
Flor | +0.069 |
Sparkle | +0.066 |
Nad | +0.066 |
Neg logit contributions | |
ruck | -0.034 |
Tim | -0.029 |
John | -0.027 |
emergency | -0.026 |
Tom | -0.025 |
Token | tle |
Token ID | 7100 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
Tim | +0.170 |
ruck | +0.169 |
John | +0.160 |
emergency | +0.157 |
Tom | +0.155 |
Neg logit contributions | |
violet | -0.181 |
pir | -0.171 |
Flor | -0.169 |
delighted | -0.164 |
Sparkle | -0.164 |
Token | girl |
Token ID | 2576 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ruck | +0.028 |
John | +0.026 |
Tim | +0.025 |
irens | +0.025 |
emergency | +0.024 |
Neg logit contributions | |
violet | -0.026 |
Flor | -0.026 |
Sparkle | -0.025 |
pir | -0.024 |
superstar | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.014 |
Flor | +0.014 |
superstar | +0.013 |
Sparkle | +0.013 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.013 |
John | -0.012 |
emergency | -0.012 |
Tom | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
Tom | +0.001 |
John | +0.001 |
emergency | +0.001 |
Neg logit contributions | |
violet | -0.001 |
pir | -0.001 |
Flor | -0.001 |
superstar | -0.001 |
mesmer | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
violet | +0.014 |
Flor | +0.014 |
pir | +0.014 |
Sparkle | +0.013 |
delighted | +0.013 |
Neg logit contributions | |
ruck | -0.018 |
irens | -0.016 |
emergency | -0.015 |
Tim | -0.015 |
John | -0.015 |
Token | by |
Token ID | 416 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
violet | +0.023 |
pir | +0.022 |
Flor | +0.022 |
Sparkle | +0.021 |
Nad | +0.021 |
Neg logit contributions | |
ruck | -0.022 |
Tim | -0.020 |
John | -0.019 |
emergency | -0.018 |
Tom | -0.018 |
Token | here |
Token ID | 994 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ruck | +0.011 |
Tim | +0.011 |
John | +0.010 |
emergency | +0.010 |
Tom | +0.010 |
Neg logit contributions | |
violet | -0.010 |
Flor | -0.010 |
pir | -0.010 |
Sparkle | -0.009 |
Nad | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ruck | +0.005 |
Tim | +0.004 |
John | +0.004 |
emergency | +0.003 |
Tom | +0.003 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.008 |
superstar | -0.008 |
Flor | -0.008 |
tail | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
violet | +0.009 |
Flor | +0.009 |
pir | +0.009 |
tail | +0.009 |
Nad | +0.009 |
Neg logit contributions | |
ruck | -0.008 |
Tim | -0.008 |
emergency | -0.007 |
John | -0.007 |
Tom | -0.007 |
Token | while |
Token ID | 981 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ruck | +0.009 |
Tim | +0.008 |
emergency | +0.008 |
John | +0.008 |
Tom | +0.007 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.009 |
Flor | -0.009 |
Nad | -0.008 |
mesmer | -0.008 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.005 |
Flor | +0.005 |
superstar | +0.005 |
Nad | +0.005 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
John | -0.004 |
emergency | -0.004 |
Tom | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ruck | +0.175 |
Tim | +0.161 |
John | +0.151 |
emergency | +0.148 |
Tom | +0.147 |
Neg logit contributions | |
violet | -0.184 |
pir | -0.176 |
Flor | -0.176 |
Sparkle | -0.166 |
Nad | -0.166 |
Token | He |
Token ID | 679 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
violet | +0.009 |
pir | +0.009 |
superstar | +0.008 |
mesmer | +0.008 |
delighted | +0.008 |
Neg logit contributions | |
Tim | -0.013 |
ruck | -0.012 |
John | -0.012 |
Tom | -0.011 |
Billy | -0.011 |
Token | went |
Token ID | 1816 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ruck | +0.042 |
Tim | +0.038 |
dd | +0.035 |
Tom | +0.035 |
tools | +0.035 |
Neg logit contributions | |
violet | -0.046 |
pir | -0.044 |
Flor | -0.042 |
Nad | -0.041 |
tail | -0.041 |
Token | that |
Token ID | 326 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.016 |
irens | +0.015 |
John | +0.014 |
emergency | +0.014 |
Neg logit contributions | |
violet | -0.020 |
pir | -0.019 |
superstar | -0.019 |
Flor | -0.019 |
mesmer | -0.019 |
Token | way |
Token ID | 835 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.014 |
Flor | +0.013 |
tail | +0.013 |
superstar | +0.013 |
Neg logit contributions | |
ruck | -0.012 |
Tim | -0.011 |
John | -0.010 |
emergency | -0.010 |
Tom | -0.010 |
Token | do |
Token ID | 466 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
violet | +0.017 |
pir | +0.017 |
Flor | +0.016 |
Sparkle | +0.016 |
Nad | +0.015 |
Neg logit contributions | |
ruck | -0.017 |
Tim | -0.015 |
John | -0.014 |
emergency | -0.014 |
Tom | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ruck | +0.014 |
Tim | +0.013 |
John | +0.012 |
emergency | +0.012 |
irens | +0.012 |
Neg logit contributions | |
violet | -0.013 |
pir | -0.013 |
Flor | -0.012 |
delighted | -0.012 |
Sparkle | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.005 |
Flor | +0.005 |
Nad | +0.005 |
superstar | +0.005 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.006 |
John | -0.006 |
emergency | -0.006 |
Tom | -0.006 |
Token | few |
Token ID | 1178 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
violet | +0.003 |
Flor | +0.003 |
pir | +0.003 |
Nad | +0.003 |
Sparkle | +0.003 |
Neg logit contributions | |
ruck | -0.003 |
Tim | -0.003 |
emergency | -0.003 |
John | -0.002 |
Tom | -0.002 |
Token | days |
Token ID | 1528 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
violet | +0.031 |
pir | +0.030 |
delighted | +0.030 |
Flor | +0.029 |
mesmer | +0.029 |
Neg logit contributions | |
ruck | -0.033 |
Tim | -0.031 |
John | -0.029 |
Tom | -0.028 |
dd | -0.028 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
ruck | +0.079 |
Tim | +0.078 |
emergency | +0.074 |
John | +0.072 |
Stop | +0.071 |
Neg logit contributions | |
delighted | -0.057 |
violet | -0.056 |
mesmer | -0.055 |
pir | -0.055 |
tail | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ruck | +0.194 |
Tim | +0.190 |
emergency | +0.181 |
irens | +0.175 |
John | +0.175 |
Neg logit contributions | |
violet | -0.146 |
pir | -0.141 |
delighted | -0.139 |
Flor | -0.136 |
mesmer | -0.135 |
Token | He |
Token ID | 679 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
violet | +0.007 |
pir | +0.007 |
Flor | +0.007 |
Sparkle | +0.007 |
superstar | +0.007 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.007 |
John | -0.006 |
emergency | -0.006 |
Tom | -0.006 |
Token | started |
Token ID | 2067 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ruck | +0.038 |
Tim | +0.036 |
John | +0.034 |
Tom | +0.033 |
emergency | +0.032 |
Neg logit contributions | |
violet | -0.039 |
pir | -0.037 |
Flor | -0.037 |
Sparkle | -0.035 |
Nad | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.012 |
John | +0.011 |
Tom | +0.011 |
emergency | +0.011 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.009 |
Flor | -0.009 |
mesmer | -0.008 |
Sparkle | -0.008 |
Token | applaud |
Token ID | 22517 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ruck | +0.024 |
Tim | +0.022 |
John | +0.021 |
irens | +0.021 |
dd | +0.021 |
Neg logit contributions | |
violet | -0.018 |
pir | -0.017 |
Flor | -0.017 |
Sparkle | -0.016 |
mesmer | -0.016 |
Token | started |
Token ID | 2067 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
violet | +0.008 |
pir | +0.007 |
Flor | +0.007 |
Sparkle | +0.007 |
Nad | +0.007 |
Neg logit contributions | |
ruck | -0.009 |
Tim | -0.008 |
Tom | -0.007 |
John | -0.007 |
emergency | -0.007 |
Token | smoking |
Token ID | 9216 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
ruck | +0.020 |
Tim | +0.019 |
John | +0.018 |
Tom | +0.018 |
emergency | +0.017 |
Neg logit contributions | |
violet | -0.015 |
pir | -0.014 |
Flor | -0.014 |
mesmer | -0.013 |
Sparkle | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ruck | +0.028 |
Tim | +0.026 |
John | +0.025 |
emergency | +0.024 |
Tom | +0.024 |
Neg logit contributions | |
violet | -0.025 |
Flor | -0.024 |
pir | -0.024 |
Sparkle | -0.022 |
Nad | -0.022 |
Token | long |
Token ID | 890 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
violet | +0.012 |
pir | +0.012 |
Flor | +0.012 |
superstar | +0.011 |
Sparkle | +0.011 |
Neg logit contributions | |
ruck | -0.009 |
Tim | -0.008 |
John | -0.007 |
Tom | -0.007 |
irens | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ruck | +0.014 |
John | +0.013 |
Tim | +0.013 |
irens | +0.013 |
dd | +0.012 |
Neg logit contributions | |
violet | -0.012 |
pir | -0.011 |
tail | -0.011 |
ind | -0.011 |
mouth | -0.011 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
ruck | +0.089 |
Tim | +0.084 |
John | +0.079 |
emergency | +0.076 |
Tom | +0.076 |
Neg logit contributions | |
violet | -0.086 |
pir | -0.082 |
Flor | -0.081 |
mesmer | -0.077 |
delighted | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ruck | +0.166 |
Tim | +0.152 |
John | +0.143 |
emergency | +0.140 |
Tom | +0.138 |
Neg logit contributions | |
violet | -0.191 |
pir | -0.183 |
Flor | -0.183 |
Sparkle | -0.173 |
Nad | -0.173 |
Token | now |
Token ID | 783 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ruck | +0.014 |
Tim | +0.013 |
John | +0.012 |
emergency | +0.012 |
Tom | +0.012 |
Neg logit contributions | |
violet | -0.013 |
Flor | -0.012 |
pir | -0.012 |
Sparkle | -0.011 |
delighted | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
violet | +0.008 |
pir | +0.007 |
Flor | +0.007 |
Nad | +0.007 |
mesmer | +0.007 |
Neg logit contributions | |
ruck | -0.008 |
Tim | -0.008 |
emergency | -0.007 |
John | -0.007 |
Tom | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ruck | +0.022 |
Tim | +0.021 |
emergency | +0.020 |
John | +0.019 |
Tom | +0.019 |
Neg logit contributions | |
violet | -0.019 |
pir | -0.018 |
Flor | -0.018 |
Nad | -0.017 |
mesmer | -0.017 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
violet | +0.042 |
pir | +0.040 |
Flor | +0.040 |
Sparkle | +0.038 |
Nad | +0.038 |
Neg logit contributions | |
ruck | -0.039 |
Tim | -0.036 |
John | -0.034 |
emergency | -0.033 |
Tom | -0.033 |
Token | time |
Token ID | 640 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
John | +0.001 |
emergency | +0.001 |
irens | +0.001 |
Neg logit contributions | |
violet | -0.002 |
pir | -0.002 |
Flor | -0.002 |
Sparkle | -0.002 |
Nad | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
ruck | +0.030 |
Tim | +0.027 |
John | +0.026 |
emergency | +0.025 |
Tom | +0.025 |
Neg logit contributions | |
violet | -0.027 |
pir | -0.026 |
Flor | -0.026 |
Sparkle | -0.024 |
Nad | -0.024 |
Token | not |
Token ID | 407 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Flor | +0.025 |
violet | +0.025 |
pir | +0.024 |
delighted | +0.024 |
Sparkle | +0.024 |
Neg logit contributions | |
ruck | -0.028 |
irens | -0.024 |
emergency | -0.024 |
Tim | -0.023 |
John | -0.023 |
Token | so |
Token ID | 523 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ruck | +0.046 |
Tim | +0.046 |
irens | +0.045 |
emergency | +0.045 |
John | +0.044 |
Neg logit contributions | |
Flor | -0.039 |
violet | -0.039 |
pir | -0.038 |
Sparkle | -0.037 |
mesmer | -0.036 |
Token | long |
Token ID | 890 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
violet | +0.039 |
pir | +0.037 |
Flor | +0.037 |
delighted | +0.036 |
Sparkle | +0.035 |
Neg logit contributions | |
ruck | -0.052 |
Tim | -0.046 |
irens | -0.046 |
John | -0.045 |
emergency | -0.044 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
ruck | +0.113 |
Tim | +0.106 |
John | +0.103 |
emergency | +0.097 |
Tom | +0.097 |
Neg logit contributions | |
violet | -0.079 |
Flor | -0.076 |
pir | -0.075 |
Sparkle | -0.073 |
Nad | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ruck | +0.176 |
Tim | +0.163 |
John | +0.153 |
emergency | +0.152 |
irens | +0.149 |
Neg logit contributions | |
violet | -0.177 |
pir | -0.171 |
Flor | -0.170 |
delighted | -0.162 |
Sparkle | -0.161 |
Token | there |
Token ID | 612 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
Flor | +0.011 |
violet | +0.011 |
pir | +0.011 |
Sparkle | +0.010 |
Nad | +0.010 |
Neg logit contributions | |
ruck | -0.012 |
irens | -0.010 |
emergency | -0.010 |
Tim | -0.010 |
John | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
violet | +0.025 |
pir | +0.024 |
Flor | +0.024 |
superstar | +0.023 |
Sparkle | +0.022 |
Neg logit contributions | |
ruck | -0.021 |
Tim | -0.019 |
John | -0.018 |
Tom | -0.018 |
emergency | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
violet | +0.008 |
Flor | +0.008 |
pir | +0.008 |
Sparkle | +0.007 |
delighted | +0.007 |
Neg logit contributions | |
ruck | -0.009 |
Tim | -0.008 |
irens | -0.008 |
emergency | -0.008 |
John | -0.008 |
Token | big |
Token ID | 1263 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ruck | +0.009 |
Tim | +0.008 |
John | +0.007 |
irens | +0.007 |
emergency | +0.007 |
Neg logit contributions | |
violet | -0.014 |
pir | -0.014 |
Flor | -0.014 |
superstar | -0.013 |
Sparkle | -0.013 |
Token | uncle |
Token ID | 7711 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ruck | +0.026 |
Tim | +0.024 |
John | +0.023 |
emergency | +0.022 |
Tom | +0.022 |
Neg logit contributions | |
violet | -0.031 |
pir | -0.030 |
Flor | -0.030 |
Sparkle | -0.028 |
Nad | -0.028 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ruck | +0.049 |
Tim | +0.046 |
John | +0.044 |
Tom | +0.043 |
emergency | +0.042 |
Neg logit contributions | |
violet | -0.040 |
pir | -0.038 |
Flor | -0.036 |
mesmer | -0.036 |
Nad | -0.035 |
Token | ." |
Token ID | 526 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
violet | +0.004 |
pir | +0.003 |
Flor | +0.003 |
mesmer | +0.003 |
Nad | +0.003 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
Tom | -0.003 |
John | -0.003 |
emergency | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
Flor | +0.003 |
mesmer | +0.003 |
superstar | +0.003 |
Neg logit contributions | |
ruck | -0.003 |
Tim | -0.003 |
Tom | -0.003 |
John | -0.003 |
irens | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ruck | +0.048 |
emergency | +0.043 |
Tim | +0.041 |
John | +0.040 |
irens | +0.040 |
Neg logit contributions | |
violet | -0.029 |
Flor | -0.029 |
Sparkle | -0.028 |
pir | -0.027 |
Nad | -0.026 |
Token | Un |
Token ID | 3118 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
ruck | +0.018 |
emergency | +0.015 |
garbage | +0.013 |
waste | +0.013 |
ime | +0.013 |
Neg logit contributions | |
violet | -0.029 |
Sparkle | -0.027 |
tail | -0.027 |
Flor | -0.027 |
Violet | -0.027 |
Token | cle |
Token ID | 2375 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ruck | +0.132 |
emergency | +0.128 |
waste | +0.119 |
garbage | +0.117 |
Tim | +0.115 |
Neg logit contributions | |
violet | -0.213 |
tail | -0.208 |
sometime | -0.193 |
superstar | -0.189 |
seven | -0.189 |
Token | Ben |
Token ID | 3932 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
ruck | +0.049 |
Tim | +0.043 |
emergency | +0.041 |
John | +0.040 |
irens | +0.039 |
Neg logit contributions | |
violet | -0.066 |
Flor | -0.064 |
pir | -0.063 |
Sparkle | -0.061 |
Nad | -0.061 |
Token | hugged |
Token ID | 41130 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
ruck | +0.023 |
Tim | +0.022 |
Tom | +0.021 |
John | +0.021 |
irens | +0.019 |
Neg logit contributions | |
violet | -0.023 |
pir | -0.022 |
Flor | -0.022 |
tail | -0.021 |
mesmer | -0.021 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Flor | +0.023 |
Sparkle | +0.022 |
Violet | +0.022 |
Pearl | +0.021 |
Alicia | +0.021 |
Neg logit contributions | |
ruck | -0.035 |
dd | -0.031 |
John | -0.031 |
emergency | -0.031 |
Tim | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
violet | +0.060 |
pir | +0.057 |
Flor | +0.055 |
mesmer | +0.054 |
superstar | +0.054 |
Neg logit contributions | |
ruck | -0.041 |
Tim | -0.038 |
Tom | -0.035 |
John | -0.034 |
emergency | -0.033 |
Token | together |
Token ID | 1978 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
violet | +0.038 |
pir | +0.037 |
Flor | +0.036 |
Sparkle | +0.034 |
Nad | +0.034 |
Neg logit contributions | |
ruck | -0.035 |
Tim | -0.032 |
John | -0.031 |
emergency | -0.030 |
Tom | -0.029 |
Token | forever |
Token ID | 8097 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
violet | +0.059 |
pir | +0.058 |
Flor | +0.056 |
Nad | +0.054 |
tail | +0.054 |
Neg logit contributions | |
ruck | -0.042 |
Tim | -0.036 |
John | -0.035 |
emergency | -0.034 |
Tom | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
violet | +0.031 |
pir | +0.030 |
Flor | +0.029 |
Nad | +0.028 |
superstar | +0.028 |
Neg logit contributions | |
ruck | -0.021 |
Tim | -0.018 |
John | -0.017 |
emergency | -0.017 |
Tom | -0.017 |
Token | On |
Token ID | 1550 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.005 |
Flor | +0.004 |
superstar | +0.004 |
mesmer | +0.004 |
Neg logit contributions | |
ruck | -0.005 |
Tim | -0.005 |
John | -0.005 |
Tom | -0.005 |
emergency | -0.005 |
Token | their |
Token ID | 511 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
violet | +0.044 |
pir | +0.042 |
Flor | +0.042 |
Sparkle | +0.040 |
Nad | +0.040 |
Neg logit contributions | |
ruck | -0.037 |
Tim | -0.034 |
John | -0.032 |
emergency | -0.031 |
Tom | -0.031 |
Token | wedding |
Token ID | 10614 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
emergency | +0.002 |
ruck | +0.002 |
Tim | +0.002 |
John | +0.002 |
waste | +0.002 |
Neg logit contributions | |
violet | -0.002 |
Flor | -0.001 |
Nice | -0.001 |
pir | -0.001 |
superstar | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
violet | +0.170 |
pir | +0.159 |
mesmer | +0.158 |
Flor | +0.157 |
superstar | +0.154 |
Neg logit contributions | |
ruck | -0.122 |
Tim | -0.114 |
emergency | -0.111 |
John | -0.107 |
Tom | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
pir | +0.028 |
Flor | +0.027 |
Sparkle | +0.027 |
violet | +0.026 |
Nad | +0.026 |
Neg logit contributions | |
ruck | -0.056 |
Tim | -0.053 |
John | -0.049 |
Tom | -0.048 |
plug | -0.048 |
Token | they |
Token ID | 484 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Flor | +0.032 |
violet | +0.031 |
pir | +0.030 |
Sparkle | +0.030 |
Nad | +0.029 |
Neg logit contributions | |
ruck | -0.040 |
Tim | -0.035 |
irens | -0.034 |
emergency | -0.034 |
John | -0.033 |
Token | kissed |
Token ID | 27946 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
violet | +0.038 |
pir | +0.037 |
Flor | +0.035 |
tail | +0.034 |
Nice | +0.034 |
Neg logit contributions | |
ruck | -0.032 |
Tim | -0.029 |
John | -0.027 |
Tom | -0.027 |
dd | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
violet | +0.057 |
Flor | +0.056 |
pir | +0.055 |
Sparkle | +0.054 |
Nad | +0.053 |
Neg logit contributions | |
ruck | -0.060 |
Tim | -0.055 |
emergency | -0.052 |
irens | -0.052 |
John | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
violet | +0.084 |
pir | +0.081 |
Flor | +0.080 |
Sparkle | +0.076 |
Nad | +0.076 |
Neg logit contributions | |
ruck | -0.070 |
Tim | -0.063 |
John | -0.059 |
emergency | -0.058 |
Tom | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.015 |
tail | +0.014 |
Flor | +0.014 |
mesmer | +0.014 |
Neg logit contributions | |
Tim | -0.011 |
ruck | -0.011 |
Tom | -0.010 |
John | -0.010 |
irens | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
violet | +0.004 |
pir | +0.004 |
Flor | +0.004 |
Sparkle | +0.004 |
Nad | +0.004 |
Neg logit contributions | |
ruck | -0.006 |
Tim | -0.005 |
emergency | -0.005 |
John | -0.005 |
irens | -0.005 |
Token | At |
Token ID | 2953 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
violet | +0.021 |
pir | +0.020 |
delighted | +0.019 |
superstar | +0.019 |
mesmer | +0.018 |
Neg logit contributions | |
ruck | -0.022 |
emergency | -0.019 |
irens | -0.018 |
tools | -0.017 |
ime | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
violet | +0.045 |
pir | +0.044 |
Flor | +0.043 |
delighted | +0.042 |
mesmer | +0.042 |
Neg logit contributions | |
ruck | -0.033 |
Tim | -0.029 |
John | -0.028 |
emergency | -0.027 |
Tom | -0.026 |
Token | wedding |
Token ID | 10614 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
violet | +0.029 |
mesmer | +0.028 |
pir | +0.028 |
Flor | +0.028 |
delighted | +0.027 |
Neg logit contributions | |
ruck | -0.025 |
emergency | -0.023 |
Tim | -0.023 |
Tom | -0.021 |
John | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
violet | +0.182 |
mesmer | +0.174 |
pir | +0.171 |
wrists | +0.168 |
Flor | +0.166 |
Neg logit contributions | |
ruck | -0.102 |
emergency | -0.096 |
Tim | -0.094 |
Tom | -0.089 |
John | -0.086 |
Token | there |
Token ID | 612 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
violet | +0.039 |
Flor | +0.038 |
pir | +0.037 |
Sparkle | +0.036 |
superstar | +0.035 |
Neg logit contributions | |
ruck | -0.039 |
Tim | -0.035 |
emergency | -0.034 |
John | -0.033 |
irens | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
violet | +0.037 |
Flor | +0.036 |
pir | +0.036 |
Sparkle | +0.034 |
Nad | +0.034 |
Neg logit contributions | |
ruck | -0.037 |
Tim | -0.033 |
John | -0.032 |
emergency | -0.031 |
irens | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
violet | +0.042 |
pir | +0.041 |
Flor | +0.040 |
tail | +0.038 |
superstar | +0.038 |
Neg logit contributions | |
ruck | -0.032 |
Tim | -0.030 |
John | -0.028 |
emergency | -0.027 |
Tom | -0.027 |
Token | big |
Token ID | 1263 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
violet | +0.010 |
Flor | +0.009 |
pir | +0.009 |
tail | +0.009 |
Nad | +0.009 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.006 |
emergency | -0.006 |
John | -0.006 |
Tom | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
superstar | +0.022 |
violet | +0.022 |
pir | +0.022 |
Flor | +0.022 |
Nad | +0.021 |
Neg logit contributions | |
ruck | -0.009 |
Tim | -0.008 |
tools | -0.006 |
junk | -0.006 |
John | -0.006 |
Token | find |
Token ID | 1064 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
violet | +0.018 |
pir | +0.018 |
superstar | +0.017 |
Flor | +0.017 |
mesmer | +0.017 |
Neg logit contributions | |
ruck | -0.019 |
Tim | -0.019 |
Tom | -0.017 |
John | -0.017 |
emergency | -0.017 |
Token | out |
Token ID | 503 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
ruck | +0.023 |
Tim | +0.021 |
John | +0.019 |
emergency | +0.019 |
Tom | +0.018 |
Neg logit contributions | |
violet | -0.029 |
pir | -0.028 |
Flor | -0.027 |
superstar | -0.027 |
mesmer | -0.026 |
Token | where |
Token ID | 810 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
Flor | +0.003 |
Sparkle | +0.003 |
Nad | +0.003 |
Neg logit contributions | |
ruck | -0.003 |
Tim | -0.002 |
John | -0.002 |
emergency | -0.002 |
Tom | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
violet | +0.032 |
Flor | +0.031 |
pir | +0.031 |
Sparkle | +0.030 |
Nad | +0.029 |
Neg logit contributions | |
ruck | -0.037 |
Tim | -0.033 |
John | -0.032 |
emergency | -0.031 |
irens | -0.031 |
Token | song |
Token ID | 3496 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
violet | +0.024 |
Flor | +0.024 |
pir | +0.024 |
Nad | +0.022 |
Sparkle | +0.022 |
Neg logit contributions | |
ruck | -0.023 |
Tim | -0.022 |
emergency | -0.020 |
John | -0.020 |
Tom | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
violet | +0.167 |
Flor | +0.165 |
pir | +0.160 |
Nad | +0.156 |
mesmer | +0.152 |
Neg logit contributions | |
ruck | -0.110 |
Tim | -0.101 |
Tom | -0.092 |
emergency | -0.091 |
John | -0.088 |
Token | coming |
Token ID | 2406 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
violet | +0.032 |
Flor | +0.031 |
pir | +0.030 |
superstar | +0.030 |
Nad | +0.029 |
Neg logit contributions | |
ruck | -0.026 |
Tim | -0.022 |
emergency | -0.022 |
John | -0.020 |
Tom | -0.020 |
Token | from |
Token ID | 422 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
ruck | +0.038 |
Tim | +0.034 |
John | +0.033 |
emergency | +0.033 |
Tom | +0.032 |
Neg logit contributions | |
violet | -0.037 |
Flor | -0.036 |
pir | -0.035 |
Sparkle | -0.034 |
Nad | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
violet | +0.015 |
Flor | +0.015 |
pir | +0.014 |
Sparkle | +0.014 |
tail | +0.014 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.013 |
John | -0.012 |
Tom | -0.012 |
irens | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
Tim | +0.008 |
ruck | +0.008 |
John | +0.007 |
Tom | +0.007 |
irens | +0.007 |
Neg logit contributions | |
violet | -0.008 |
pir | -0.007 |
Flor | -0.007 |
superstar | -0.007 |
tail | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
violet | +0.007 |
pir | +0.006 |
Flor | +0.006 |
Sparkle | +0.006 |
Nad | +0.006 |
Neg logit contributions | |
ruck | -0.008 |
Tim | -0.007 |
John | -0.007 |
emergency | -0.007 |
Tom | -0.007 |
Token | would |
Token ID | 561 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
violet | +0.036 |
pir | +0.035 |
Flor | +0.034 |
Sparkle | +0.032 |
superstar | +0.032 |
Neg logit contributions | |
ruck | -0.046 |
Tim | -0.043 |
John | -0.041 |
emergency | -0.040 |
irens | -0.040 |
Token | write |
Token ID | 3551 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
violet | +0.014 |
Flor | +0.013 |
pir | +0.013 |
Sparkle | +0.012 |
Nad | +0.012 |
Neg logit contributions | |
ruck | -0.016 |
Tim | -0.014 |
John | -0.014 |
emergency | -0.014 |
Tom | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
violet | +0.015 |
Flor | +0.014 |
pir | +0.014 |
Nad | +0.014 |
superstar | +0.014 |
Neg logit contributions | |
ruck | -0.011 |
Tim | -0.009 |
John | -0.009 |
emergency | -0.009 |
Tom | -0.009 |
Token | new |
Token ID | 649 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Flor | +0.054 |
violet | +0.053 |
Rosa | +0.052 |
tail | +0.051 |
Violet | +0.050 |
Neg logit contributions | |
ruck | -0.040 |
emergency | -0.033 |
Tim | -0.031 |
tools | -0.031 |
Tom | -0.030 |
Token | tale |
Token ID | 12838 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
Flor | +0.050 |
violet | +0.048 |
mesmer | +0.046 |
Nad | +0.046 |
pir | +0.046 |
Neg logit contributions | |
ruck | -0.044 |
emergency | -0.036 |
tools | -0.036 |
Tim | -0.035 |
cream | -0.033 |
Token | about |
Token ID | 546 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
Flor | +0.165 |
violet | +0.165 |
pir | +0.162 |
mesmer | +0.156 |
Nad | +0.156 |
Neg logit contributions | |
ruck | -0.112 |
emergency | -0.098 |
Tim | -0.097 |
Tom | -0.093 |
John | -0.092 |
Token | ships |
Token ID | 7937 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
emergency | +0.000 |
John | +0.000 |
tools | +0.000 |
Neg logit contributions | |
violet | -0.001 |
pir | -0.001 |
Flor | -0.001 |
superstar | -0.001 |
tail | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
ruck | +0.050 |
Tim | +0.044 |
emergency | +0.041 |
John | +0.041 |
Tom | +0.040 |
Neg logit contributions | |
violet | -0.062 |
pir | -0.060 |
Flor | -0.060 |
Nad | -0.057 |
mesmer | -0.057 |
Token | sailors |
Token ID | 29996 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
violet | +0.002 |
pir | +0.002 |
Flor | +0.002 |
superstar | +0.002 |
Nad | +0.002 |
Neg logit contributions | |
ruck | -0.003 |
Tim | -0.002 |
emergency | -0.002 |
tools | -0.002 |
John | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ruck | +0.032 |
Tim | +0.027 |
John | +0.025 |
Tom | +0.024 |
emergency | +0.024 |
Neg logit contributions | |
violet | -0.047 |
pir | -0.046 |
Flor | -0.044 |
Nad | -0.043 |
mesmer | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
violet | +0.141 |
pir | +0.135 |
mesmer | +0.130 |
Flor | +0.130 |
ind | +0.129 |
Neg logit contributions | |
ruck | -0.084 |
Tim | -0.075 |
emergency | -0.070 |
John | -0.070 |
Tom | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
Tim | +0.017 |
ruck | +0.015 |
John | +0.014 |
Tom | +0.014 |
Billy | +0.013 |
Neg logit contributions | |
violet | -0.021 |
pir | -0.021 |
tail | -0.020 |
Flor | -0.020 |
superstar | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ruck | +0.012 |
Tim | +0.012 |
John | +0.011 |
Tom | +0.011 |
emergency | +0.011 |
Neg logit contributions | |
violet | -0.011 |
pir | -0.011 |
Flor | -0.011 |
superstar | -0.010 |
Sparkle | -0.010 |
Token | At |
Token ID | 2953 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.005 |
Sparkle | +0.005 |
delighted | +0.004 |
superstar | +0.004 |
Neg logit contributions | |
ruck | -0.004 |
emergency | -0.003 |
irens | -0.003 |
John | -0.003 |
tools | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
violet | +0.033 |
pir | +0.032 |
Flor | +0.032 |
superstar | +0.030 |
delighted | +0.030 |
Neg logit contributions | |
ruck | -0.026 |
Tim | -0.024 |
John | -0.023 |
emergency | -0.022 |
Tom | -0.022 |
Token | wedding |
Token ID | 10614 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
violet | +0.018 |
pir | +0.017 |
mesmer | +0.017 |
Flor | +0.017 |
tail | +0.016 |
Neg logit contributions | |
ruck | -0.022 |
emergency | -0.022 |
Tim | -0.022 |
Tom | -0.020 |
John | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
violet | +0.171 |
mesmer | +0.164 |
pir | +0.161 |
wrists | +0.158 |
superstar | +0.157 |
Neg logit contributions | |
ruck | -0.103 |
Tim | -0.098 |
emergency | -0.097 |
Tom | -0.090 |
John | -0.089 |
Token | Benny |
Token ID | 44275 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
violet | +0.034 |
pir | +0.033 |
Flor | +0.033 |
Sparkle | +0.031 |
Nad | +0.031 |
Neg logit contributions | |
ruck | -0.028 |
Tim | -0.026 |
John | -0.024 |
emergency | -0.024 |
Tom | -0.023 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ruck | +0.000 |
Tim | +0.000 |
Tom | +0.000 |
John | +0.000 |
dd | +0.000 |
Neg logit contributions | |
violet | -0.001 |
pir | -0.001 |
Flor | -0.001 |
Nice | -0.001 |
superstar | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
ruck | +0.051 |
Tim | +0.046 |
John | +0.044 |
emergency | +0.044 |
irens | +0.043 |
Neg logit contributions | |
Flor | -0.052 |
violet | -0.052 |
Sparkle | -0.050 |
pir | -0.049 |
delighted | -0.048 |
Token | big |
Token ID | 1263 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
violet | +0.030 |
Flor | +0.030 |
pir | +0.029 |
tail | +0.028 |
Nad | +0.028 |
Neg logit contributions | |
ruck | -0.023 |
Tim | -0.021 |
John | -0.019 |
emergency | -0.019 |
Tom | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
superstar | +0.044 |
pir | +0.043 |
violet | +0.043 |
mesmer | +0.042 |
delighted | +0.041 |
Neg logit contributions | |
Tim | -0.014 |
ruck | -0.012 |
waste | -0.012 |
him | -0.011 |
cream | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
Tim | +0.009 |
Tom | +0.008 |
ruck | +0.008 |
John | +0.008 |
emergency | +0.007 |
Neg logit contributions | |
violet | -0.008 |
pir | -0.008 |
superstar | -0.008 |
Flor | -0.008 |
mesmer | -0.008 |
Token | carefully |
Token ID | 7773 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
violet | +0.020 |
pir | +0.019 |
Flor | +0.019 |
Nad | +0.018 |
delighted | +0.018 |
Neg logit contributions | |
ruck | -0.018 |
Tim | -0.016 |
emergency | -0.016 |
John | -0.016 |
irens | -0.015 |
Token | picked |
Token ID | 6497 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ruck | +0.022 |
Tim | +0.019 |
John | +0.019 |
emergency | +0.019 |
irens | +0.018 |
Neg logit contributions | |
violet | -0.022 |
pir | -0.021 |
Flor | -0.021 |
delighted | -0.020 |
Nad | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
pir | +0.015 |
violet | +0.015 |
superstar | +0.015 |
tail | +0.014 |
mesmer | +0.014 |
Neg logit contributions | |
ruck | -0.011 |
Tim | -0.010 |
Tom | -0.009 |
dd | -0.009 |
John | -0.008 |
Token | flower |
Token ID | 15061 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
Nice | +0.062 |
pir | +0.060 |
sometime | +0.059 |
superstar | +0.059 |
Want | +0.057 |
Neg logit contributions | |
waste | -0.051 |
cream | -0.048 |
ruck | -0.046 |
trash | -0.045 |
things | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
superstar | +0.204 |
pir | +0.196 |
la | +0.193 |
violet | +0.191 |
pleasure | +0.191 |
Neg logit contributions | |
waste | -0.059 |
Tim | -0.057 |
ruck | -0.050 |
cream | -0.050 |
junk | -0.048 |
Token | smelled |
Token ID | 37609 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
violet | +0.016 |
pir | +0.016 |
Flor | +0.016 |
superstar | +0.015 |
Nice | +0.015 |
Neg logit contributions | |
ruck | -0.012 |
Tim | -0.012 |
Tom | -0.011 |
John | -0.011 |
dd | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
violet | +0.068 |
pir | +0.066 |
Flor | +0.063 |
superstar | +0.063 |
tail | +0.062 |
Neg logit contributions | |
ruck | -0.058 |
Tim | -0.052 |
emergency | -0.049 |
John | -0.048 |
Tom | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
emergency | +0.001 |
John | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
violet | -0.002 |
pir | -0.002 |
Flor | -0.002 |
superstar | -0.002 |
Sparkle | -0.002 |
Token | It |
Token ID | 632 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Tim | +0.014 |
ruck | +0.014 |
Tom | +0.013 |
John | +0.013 |
irens | +0.012 |
Neg logit contributions | |
violet | -0.013 |
pir | -0.013 |
superstar | -0.012 |
Flor | -0.012 |
mesmer | -0.012 |
Token | family |
Token ID | 1641 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
emergency | +0.009 |
ruck | +0.009 |
tools | +0.009 |
Tim | +0.008 |
cream | +0.008 |
Neg logit contributions | |
violet | -0.013 |
Want | -0.012 |
ind | -0.012 |
mesmer | -0.012 |
Nice | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
violet | +0.046 |
pir | +0.044 |
Flor | +0.044 |
mesmer | +0.043 |
superstar | +0.042 |
Neg logit contributions | |
ruck | -0.026 |
Tim | -0.023 |
Tom | -0.020 |
emergency | -0.020 |
John | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
Tim | +0.005 |
ruck | +0.005 |
Tom | +0.004 |
John | +0.004 |
irens | +0.004 |
Neg logit contributions | |
violet | -0.005 |
pir | -0.005 |
superstar | -0.005 |
mesmer | -0.005 |
Flor | -0.005 |
Token | sang |
Token ID | 25889 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
violet | +0.031 |
Nice | +0.030 |
Flor | +0.030 |
tail | +0.029 |
highest | +0.028 |
Neg logit contributions | |
ruck | -0.023 |
Tim | -0.021 |
dd | -0.020 |
Tom | -0.020 |
John | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
violet | +0.131 |
Flor | +0.123 |
pir | +0.122 |
tail | +0.119 |
Nad | +0.118 |
Neg logit contributions | |
ruck | -0.090 |
Tim | -0.081 |
John | -0.078 |
Tom | -0.075 |
dd | -0.069 |
Token | song |
Token ID | 3496 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
Flor | +0.031 |
sometime | +0.031 |
tail | +0.031 |
violet | +0.031 |
Wouldn | +0.029 |
Neg logit contributions | |
ruck | -0.023 |
Tim | -0.021 |
Tom | -0.019 |
John | -0.019 |
cream | -0.018 |
Token | about |
Token ID | 546 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Flor | +0.179 |
wrists | +0.179 |
violet | +0.178 |
Wouldn | +0.177 |
pir | +0.176 |
Neg logit contributions | |
ruck | -0.092 |
ly | -0.071 |
Tim | -0.068 |
Tom | -0.064 |
John | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
ruck | +0.006 |
Tim | +0.005 |
John | +0.005 |
emergency | +0.005 |
Tom | +0.005 |
Neg logit contributions | |
violet | -0.008 |
pir | -0.008 |
tail | -0.008 |
Flor | -0.008 |
superstar | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
hips | +0.022 |
tail | +0.021 |
Flor | +0.021 |
violet | +0.021 |
Nad | +0.021 |
Neg logit contributions | |
Tim | -0.014 |
ruck | -0.013 |
emergency | -0.013 |
Tom | -0.013 |
waste | -0.012 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
violet | +0.004 |
hips | +0.004 |
Nad | +0.004 |
mesmer | +0.004 |
Flor | +0.004 |
Neg logit contributions | |
ruck | -0.002 |
emergency | -0.002 |
Tim | -0.002 |
waste | -0.002 |
traffic | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
pleasure | +0.057 |
pir | +0.057 |
violet | +0.055 |
Flor | +0.055 |
Nad | +0.054 |
Neg logit contributions | |
ruck | -0.028 |
Tim | -0.026 |
Tom | -0.022 |
emergency | -0.020 |
dd | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
ruck | +0.002 |
Tim | +0.002 |
John | +0.001 |
emergency | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
violet | -0.002 |
Flor | -0.002 |
pir | -0.002 |
Sparkle | -0.002 |
Nad | -0.002 |
Token | trying |
Token ID | 2111 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ruck | +0.033 |
Tim | +0.031 |
John | +0.029 |
Tom | +0.028 |
emergency | +0.028 |
Neg logit contributions | |
violet | -0.027 |
Flor | -0.026 |
pir | -0.026 |
Sparkle | -0.025 |
delighted | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
ruck | +0.020 |
Tim | +0.018 |
John | +0.017 |
emergency | +0.017 |
Tom | +0.017 |
Neg logit contributions | |
violet | -0.018 |
pir | -0.017 |
Flor | -0.017 |
Nad | -0.016 |
superstar | -0.016 |
Token | steal |
Token ID | 8711 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
violet | +0.019 |
pir | +0.018 |
Flor | +0.018 |
Nad | +0.017 |
Sparkle | +0.017 |
Neg logit contributions | |
ruck | -0.025 |
Tim | -0.024 |
John | -0.023 |
emergency | -0.022 |
Tom | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
Flor | +0.007 |
violet | +0.007 |
pir | +0.007 |
Sparkle | +0.007 |
Nad | +0.007 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.006 |
John | -0.006 |
irens | -0.006 |
dd | -0.006 |
Token | song |
Token ID | 3496 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
ruck | +0.018 |
emergency | +0.018 |
tools | +0.016 |
waste | +0.016 |
Tim | +0.016 |
Neg logit contributions | |
violet | -0.019 |
Flor | -0.019 |
Nad | -0.019 |
pir | -0.018 |
superstar | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
violet | +0.169 |
pir | +0.161 |
Flor | +0.158 |
Nad | +0.151 |
mesmer | +0.151 |
Neg logit contributions | |
ruck | -0.112 |
Tim | -0.103 |
John | -0.094 |
emergency | -0.093 |
Tom | -0.091 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
ruck | +0.028 |
Tim | +0.027 |
John | +0.026 |
Tom | +0.025 |
emergency | +0.025 |
Neg logit contributions | |
violet | -0.024 |
pir | -0.023 |
Flor | -0.022 |
tail | -0.021 |
superstar | -0.021 |
Token | The |
Token ID | 464 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.016 |
emergency | +0.016 |
John | +0.015 |
irens | +0.015 |
Neg logit contributions | |
violet | -0.015 |
Flor | -0.014 |
pir | -0.014 |
Sparkle | -0.014 |
Nad | -0.014 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ruck | +0.032 |
Tim | +0.028 |
irens | +0.027 |
John | +0.027 |
dd | +0.026 |
Neg logit contributions | |
violet | -0.032 |
pir | -0.031 |
Flor | -0.031 |
Sparkle | -0.031 |
delighted | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.005 |
Flor | +0.005 |
Nad | +0.005 |
Sparkle | +0.005 |
Neg logit contributions | |
ruck | -0.005 |
Tim | -0.005 |
John | -0.005 |
emergency | -0.004 |
Tom | -0.004 |
Token | But |
Token ID | 887 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Tim | +0.004 |
ruck | +0.003 |
Tom | +0.003 |
John | +0.003 |
Billy | +0.003 |
Neg logit contributions | |
violet | -0.004 |
mesmer | -0.004 |
pir | -0.004 |
superstar | -0.004 |
delighted | -0.004 |
Token | when |
Token ID | 618 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
violet | +0.013 |
pir | +0.012 |
mesmer | +0.012 |
delighted | +0.011 |
Flor | +0.011 |
Neg logit contributions | |
ruck | -0.009 |
Tim | -0.009 |
emergency | -0.008 |
Tom | -0.008 |
John | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
violet | +0.040 |
mesmer | +0.038 |
pir | +0.037 |
delighted | +0.036 |
Flor | +0.035 |
Neg logit contributions | |
Tim | -0.034 |
ruck | -0.033 |
Tom | -0.031 |
emergency | -0.031 |
John | -0.030 |
Token | poured |
Token ID | 19036 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
violet | +0.067 |
pir | +0.065 |
Flor | +0.064 |
Sparkle | +0.061 |
Nad | +0.061 |
Neg logit contributions | |
ruck | -0.059 |
Tim | -0.055 |
John | -0.051 |
emergency | -0.050 |
Tom | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
violet | +0.060 |
Flor | +0.059 |
pir | +0.058 |
Sparkle | +0.055 |
Nad | +0.054 |
Neg logit contributions | |
ruck | -0.064 |
Tim | -0.058 |
John | -0.056 |
emergency | -0.055 |
Tom | -0.054 |
Token | tea |
Token ID | 8887 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
violet | +0.033 |
pir | +0.031 |
Flor | +0.030 |
mesmer | +0.030 |
superstar | +0.029 |
Neg logit contributions | |
ruck | -0.046 |
Tim | -0.044 |
emergency | -0.041 |
Tom | -0.040 |
John | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
violet | +0.143 |
pir | +0.135 |
Flor | +0.134 |
mesmer | +0.133 |
superstar | +0.129 |
Neg logit contributions | |
ruck | -0.129 |
Tim | -0.123 |
emergency | -0.113 |
Tom | -0.112 |
John | -0.110 |
Token | she |
Token ID | 673 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
violet | +0.040 |
Flor | +0.039 |
pir | +0.038 |
Sparkle | +0.036 |
Nad | +0.036 |
Neg logit contributions | |
ruck | -0.055 |
Tim | -0.050 |
John | -0.048 |
emergency | -0.047 |
irens | -0.047 |
Token | accidentally |
Token ID | 14716 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
violet | +0.063 |
pir | +0.059 |
Flor | +0.059 |
Nice | +0.056 |
mesmer | +0.056 |
Neg logit contributions | |
ruck | -0.049 |
Tim | -0.046 |
Tom | -0.043 |
John | -0.041 |
emergency | -0.041 |
Token | spilled |
Token ID | 31896 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ruck | +0.046 |
Tim | +0.042 |
John | +0.039 |
emergency | +0.038 |
Tom | +0.037 |
Neg logit contributions | |
violet | -0.066 |
pir | -0.064 |
Flor | -0.064 |
Sparkle | -0.061 |
Nad | -0.060 |
Token | it |
Token ID | 340 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
ruck | +0.012 |
John | +0.012 |
Tim | +0.011 |
emergency | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
violet | -0.009 |
Flor | -0.009 |
pir | -0.008 |
Sparkle | -0.008 |
Nad | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Tim | +0.007 |
ruck | +0.007 |
John | +0.006 |
Tom | +0.006 |
emergency | +0.006 |
Neg logit contributions | |
violet | -0.012 |
pir | -0.012 |
Flor | -0.011 |
superstar | -0.011 |
mesmer | -0.011 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Tim | +0.031 |
Tom | +0.031 |
ruck | +0.028 |
ts | +0.025 |
John | +0.025 |
Neg logit contributions | |
Nice | -0.056 |
violet | -0.054 |
pleasure | -0.054 |
tail | -0.053 |
Want | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ruck | +0.039 |
Tim | +0.037 |
John | +0.035 |
emergency | +0.034 |
Tom | +0.034 |
Neg logit contributions | |
violet | -0.031 |
pir | -0.029 |
Flor | -0.029 |
Sparkle | -0.028 |
Nad | -0.027 |
Token | share |
Token ID | 2648 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
violet | +0.019 |
delighted | +0.018 |
Flor | +0.018 |
pir | +0.018 |
superstar | +0.018 |
Neg logit contributions | |
ruck | -0.018 |
Tim | -0.018 |
Tom | -0.017 |
waste | -0.016 |
John | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
violet | +0.078 |
pir | +0.075 |
Flor | +0.074 |
superstar | +0.072 |
mesmer | +0.072 |
Neg logit contributions | |
ruck | -0.038 |
Tim | -0.034 |
John | -0.031 |
Tom | -0.030 |
emergency | -0.029 |
Token | song |
Token ID | 3496 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
ruck | +0.035 |
Tim | +0.031 |
emergency | +0.029 |
John | +0.029 |
Tom | +0.028 |
Neg logit contributions | |
violet | -0.051 |
Flor | -0.050 |
pir | -0.050 |
Nad | -0.048 |
Sparkle | -0.047 |
Token | with |
Token ID | 351 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
violet | +0.195 |
pir | +0.180 |
Nad | +0.174 |
Flor | +0.173 |
mesmer | +0.173 |
Neg logit contributions | |
ruck | -0.076 |
Tim | -0.073 |
Tom | -0.065 |
his | -0.063 |
John | -0.063 |
Token | other |
Token ID | 584 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Flor | +0.007 |
violet | +0.007 |
pir | +0.006 |
Sparkle | +0.006 |
Nad | +0.006 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.003 |
John | -0.003 |
dd | -0.003 |
emergency | -0.003 |
Token | people |
Token ID | 661 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
violet | +0.008 |
pir | +0.008 |
Flor | +0.008 |
Sparkle | +0.008 |
superstar | +0.008 |
Neg logit contributions | |
ruck | -0.005 |
Tim | -0.004 |
John | -0.004 |
emergency | -0.004 |
dd | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
ruck | +0.056 |
Tim | +0.050 |
John | +0.047 |
emergency | +0.046 |
Tom | +0.046 |
Neg logit contributions | |
violet | -0.072 |
pir | -0.069 |
Flor | -0.069 |
Nad | -0.065 |
Sparkle | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.012 |
John | +0.011 |
emergency | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
violet | -0.015 |
pir | -0.014 |
Flor | -0.014 |
Sparkle | -0.014 |
Nad | -0.013 |
Token | tried |
Token ID | 3088 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ruck | +0.040 |
Tim | +0.037 |
dd | +0.035 |
Tom | +0.034 |
John | +0.034 |
Neg logit contributions | |
violet | -0.053 |
pir | -0.049 |
Flor | -0.048 |
Nice | -0.047 |
Violet | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
violet | +0.004 |
superstar | +0.004 |
Flor | +0.004 |
ind | +0.004 |
tail | +0.004 |
Neg logit contributions | |
ruck | -0.003 |
emergency | -0.002 |
Tim | -0.002 |
his | -0.002 |
John | -0.002 |
Token | sing |
Token ID | 1702 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
violet | +0.011 |
pir | +0.010 |
Nice | +0.010 |
Flor | +0.010 |
superstar | +0.010 |
Neg logit contributions | |
ruck | -0.013 |
Tim | -0.012 |
emergency | -0.011 |
waste | -0.011 |
Tom | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
violet | +0.137 |
Flor | +0.126 |
pir | +0.125 |
Nad | +0.122 |
superstar | +0.120 |
Neg logit contributions | |
ruck | -0.096 |
Tim | -0.086 |
John | -0.081 |
emergency | -0.079 |
Tom | -0.078 |
Token | green |
Token ID | 4077 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
emergency | +0.025 |
tools | +0.025 |
ruck | +0.024 |
cream | +0.024 |
things | +0.023 |
Neg logit contributions | |
violet | -0.035 |
Want | -0.031 |
Shall | -0.030 |
ind | -0.030 |
seven | -0.030 |
Token | song |
Token ID | 3496 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
violet | +0.039 |
Flor | +0.038 |
mesmer | +0.037 |
delighted | +0.037 |
pir | +0.036 |
Neg logit contributions | |
ruck | -0.042 |
emergency | -0.038 |
Tim | -0.036 |
tools | -0.035 |
cream | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
violet | +0.174 |
Flor | +0.161 |
pir | +0.160 |
Nad | +0.153 |
mesmer | +0.152 |
Neg logit contributions | |
ruck | -0.104 |
Tim | -0.089 |
John | -0.081 |
emergency | -0.081 |
Tom | -0.079 |
Token | but |
Token ID | 475 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
emergency | +0.001 |
John | +0.001 |
tools | +0.001 |
Neg logit contributions | |
violet | -0.001 |
Flor | -0.001 |
tail | -0.001 |
Nad | -0.001 |
pir | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
ruck | +0.009 |
Tim | +0.008 |
John | +0.008 |
emergency | +0.008 |
Tom | +0.007 |
Neg logit contributions | |
violet | -0.016 |
pir | -0.015 |
Flor | -0.015 |
superstar | -0.014 |
tail | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
John | +0.001 |
emergency | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
violet | -0.002 |
pir | -0.002 |
Flor | -0.002 |
Sparkle | -0.002 |
Nad | -0.002 |
Token | could |
Token ID | 714 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ruck | +0.040 |
Tim | +0.039 |
dd | +0.038 |
Tom | +0.036 |
John | +0.036 |
Neg logit contributions | |
violet | -0.045 |
pir | -0.041 |
Nice | -0.039 |
Flor | -0.039 |
Want | -0.039 |
Token | help |
Token ID | 1037 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ruck | +0.030 |
Tim | +0.028 |
John | +0.026 |
emergency | +0.025 |
Tom | +0.025 |
Neg logit contributions | |
violet | -0.030 |
pir | -0.029 |
Flor | -0.029 |
Sparkle | -0.027 |
Nad | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.012 |
John | +0.011 |
emergency | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
violet | -0.013 |
pir | -0.012 |
Flor | -0.012 |
Sparkle | -0.012 |
Nad | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.006 |
Flor | +0.006 |
tail | +0.006 |
superstar | +0.006 |
Neg logit contributions | |
ruck | -0.006 |
Tim | -0.006 |
John | -0.005 |
Tom | -0.005 |
emergency | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
ruck | +0.019 |
Tim | +0.018 |
John | +0.018 |
Tom | +0.017 |
emergency | +0.017 |
Neg logit contributions | |
violet | -0.022 |
pir | -0.021 |
superstar | -0.020 |
Nice | -0.020 |
Flor | -0.020 |
Token | gave |
Token ID | 2921 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
violet | +0.017 |
pir | +0.016 |
Flor | +0.016 |
tail | +0.016 |
Sparkle | +0.016 |
Neg logit contributions | |
ruck | -0.016 |
Tim | -0.015 |
John | -0.015 |
Tom | -0.014 |
emergency | -0.013 |
Token | Ana |
Token ID | 17639 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
violet | +0.028 |
pir | +0.027 |
superstar | +0.027 |
mesmer | +0.027 |
Nice | +0.026 |
Neg logit contributions | |
ruck | -0.015 |
Tim | -0.013 |
John | -0.013 |
Tom | -0.012 |
him | -0.011 |
Token | some |
Token ID | 617 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
violet | +0.147 |
pir | +0.142 |
Flor | +0.137 |
superstar | +0.137 |
mesmer | +0.134 |
Neg logit contributions | |
ruck | -0.121 |
Tim | -0.111 |
John | -0.106 |
Tom | -0.102 |
emergency | -0.100 |
Token | hints |
Token ID | 20269 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
violet | +0.017 |
pir | +0.016 |
Flor | +0.016 |
Sparkle | +0.015 |
delighted | +0.015 |
Neg logit contributions | |
ruck | -0.015 |
Tim | -0.014 |
John | -0.013 |
emergency | -0.013 |
Tom | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
ruck | +0.028 |
Tim | +0.025 |
John | +0.024 |
Tom | +0.023 |
emergency | +0.023 |
Neg logit contributions | |
violet | -0.041 |
pir | -0.040 |
Flor | -0.039 |
superstar | -0.037 |
Nad | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Tim | +0.016 |
Tom | +0.016 |
John | +0.016 |
Dad | +0.014 |
li | +0.014 |
Neg logit contributions | |
superstar | -0.030 |
happiest | -0.030 |
tallest | -0.030 |
highest | -0.029 |
tail | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Tim | +0.024 |
John | +0.023 |
ruck | +0.022 |
Tom | +0.022 |
Dad | +0.019 |
Neg logit contributions | |
violet | -0.034 |
superstar | -0.034 |
pir | -0.033 |
tail | -0.033 |
ind | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.005 |
Flor | +0.005 |
Nad | +0.005 |
superstar | +0.005 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
emergency | -0.004 |
John | -0.003 |
Tom | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
violet | +0.016 |
pir | +0.015 |
Flor | +0.015 |
superstar | +0.014 |
mesmer | +0.014 |
Neg logit contributions | |
ruck | -0.015 |
Tim | -0.015 |
John | -0.014 |
Tom | -0.014 |
emergency | -0.013 |
Token | gives |
Token ID | 3607 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
violet | +0.030 |
pir | +0.029 |
Flor | +0.028 |
superstar | +0.027 |
Sparkle | +0.027 |
Neg logit contributions | |
ruck | -0.028 |
Tim | -0.026 |
Tom | -0.025 |
John | -0.025 |
emergency | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Flor | +0.044 |
violet | +0.043 |
Sparkle | +0.042 |
pir | +0.041 |
Nad | +0.041 |
Neg logit contributions | |
ruck | -0.038 |
Tim | -0.034 |
John | -0.032 |
emergency | -0.032 |
irens | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
violet | +0.066 |
pir | +0.064 |
mesmer | +0.061 |
Flor | +0.061 |
superstar | +0.060 |
Neg logit contributions | |
ruck | -0.052 |
Tim | -0.047 |
emergency | -0.043 |
John | -0.043 |
Tom | -0.042 |
Token | kiss |
Token ID | 9245 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
violet | +0.034 |
pir | +0.033 |
Flor | +0.033 |
mesmer | +0.031 |
Nad | +0.031 |
Neg logit contributions | |
ruck | -0.047 |
Tim | -0.043 |
John | -0.041 |
emergency | -0.041 |
Tom | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
violet | +0.165 |
pir | +0.165 |
mesmer | +0.159 |
Flor | +0.157 |
Nad | +0.153 |
Neg logit contributions | |
ruck | -0.109 |
Tim | -0.094 |
Tom | -0.089 |
John | -0.086 |
emergency | -0.081 |
Token | She |
Token ID | 1375 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
Tim | +0.009 |
ruck | +0.009 |
Tom | +0.009 |
John | +0.008 |
irens | +0.008 |
Neg logit contributions | |
pir | -0.010 |
violet | -0.010 |
superstar | -0.009 |
delighted | -0.009 |
mesmer | -0.009 |
Token | says |
Token ID | 1139 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
violet | +0.022 |
pir | +0.022 |
Nice | +0.021 |
mesmer | +0.021 |
Want | +0.021 |
Neg logit contributions | |
ruck | -0.024 |
Tom | -0.023 |
Tim | -0.022 |
tools | -0.022 |
cream | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
violet | +0.011 |
pir | +0.011 |
Flor | +0.010 |
mesmer | +0.010 |
superstar | +0.010 |
Neg logit contributions | |
ruck | -0.013 |
Tim | -0.013 |
John | -0.012 |
Tom | -0.012 |
emergency | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
pir | +0.031 |
tail | +0.030 |
highest | +0.030 |
violet | +0.030 |
Nad | +0.029 |
Neg logit contributions | |
ruck | -0.033 |
Tim | -0.032 |
Tom | -0.031 |
John | -0.030 |
emergency | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.006 |
Flor | +0.005 |
Nad | +0.005 |
tail | +0.005 |
Neg logit contributions | |
ruck | -0.006 |
emergency | -0.005 |
Tim | -0.005 |
John | -0.005 |
Tom | -0.005 |
Token | When |
Token ID | 1649 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
pir | +0.002 |
violet | +0.002 |
superstar | +0.002 |
delighted | +0.002 |
wrists | +0.002 |
Neg logit contributions | |
Tim | -0.002 |
ruck | -0.002 |
John | -0.002 |
Tom | -0.002 |
Billy | -0.002 |
Token | I |
Token ID | 314 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
violet | +0.019 |
pir | +0.018 |
Flor | +0.018 |
mesmer | +0.017 |
delighted | +0.017 |
Neg logit contributions | |
ruck | -0.018 |
Tim | -0.017 |
John | -0.016 |
emergency | -0.016 |
Tom | -0.016 |
Token | give |
Token ID | 1577 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
violet | +0.022 |
pir | +0.021 |
wrists | +0.021 |
Flor | +0.021 |
Nice | +0.021 |
Neg logit contributions | |
ruck | -0.019 |
Tim | -0.017 |
waste | -0.017 |
Stop | -0.017 |
Tom | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
violet | +0.014 |
pir | +0.013 |
Flor | +0.013 |
Sparkle | +0.012 |
Nad | +0.012 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.013 |
John | -0.012 |
emergency | -0.012 |
Tom | -0.012 |
Token | song |
Token ID | 3496 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
violet | +0.031 |
Flor | +0.031 |
pir | +0.031 |
Nad | +0.030 |
Sparkle | +0.029 |
Neg logit contributions | |
ruck | -0.027 |
Tim | -0.024 |
emergency | -0.024 |
John | -0.022 |
Tom | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
violet | +0.153 |
pir | +0.148 |
Flor | +0.144 |
superstar | +0.144 |
mesmer | +0.143 |
Neg logit contributions | |
ruck | -0.106 |
Tim | -0.096 |
emergency | -0.091 |
cream | -0.090 |
tools | -0.089 |
Token | people |
Token ID | 661 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
violet | +0.049 |
Flor | +0.047 |
pir | +0.047 |
Sparkle | +0.044 |
Nad | +0.044 |
Neg logit contributions | |
ruck | -0.047 |
Tim | -0.044 |
John | -0.041 |
emergency | -0.040 |
Tom | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ruck | +0.034 |
Tim | +0.029 |
John | +0.028 |
emergency | +0.027 |
Tom | +0.027 |
Neg logit contributions | |
violet | -0.038 |
pir | -0.037 |
Flor | -0.036 |
Nad | -0.034 |
mesmer | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.005 |
Flor | +0.004 |
superstar | +0.004 |
Nad | +0.004 |
Neg logit contributions | |
ruck | -0.006 |
Tim | -0.005 |
John | -0.005 |
emergency | -0.005 |
Tom | -0.005 |
Token | makes |
Token ID | 1838 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
ruck | +0.002 |
emergency | +0.002 |
waste | +0.001 |
Stop | +0.001 |
Tim | +0.001 |
Neg logit contributions | |
violet | -0.002 |
pir | -0.001 |
Nad | -0.001 |
Flor | -0.001 |
Sof | -0.001 |
Token | says |
Token ID | 1139 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
superstar | +0.032 |
violet | +0.032 |
tallest | +0.031 |
pleasure | +0.031 |
pir | +0.030 |
Neg logit contributions | |
Tom | -0.022 |
Tim | -0.020 |
ruck | -0.019 |
Stop | -0.019 |
him | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ruck | +0.020 |
Tim | +0.018 |
John | +0.017 |
Tom | +0.016 |
emergency | +0.016 |
Neg logit contributions | |
violet | -0.030 |
pir | -0.029 |
Flor | -0.029 |
superstar | -0.028 |
Sparkle | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Tim | +0.018 |
Tom | +0.017 |
ruck | +0.016 |
John | +0.016 |
irens | +0.016 |
Neg logit contributions | |
pir | -0.019 |
superstar | -0.018 |
violet | -0.018 |
mesmer | -0.017 |
tail | -0.017 |
Token | picks |
Token ID | 11103 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
tail | +0.014 |
ectar | +0.014 |
comb | +0.014 |
superstar | +0.014 |
Nice | +0.014 |
Neg logit contributions | |
ruck | -0.010 |
Tom | -0.010 |
Stop | -0.010 |
tools | -0.010 |
Tim | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.011 |
Tom | +0.011 |
John | +0.010 |
emergency | +0.010 |
Neg logit contributions | |
pir | -0.017 |
violet | -0.017 |
superstar | -0.016 |
tail | -0.016 |
mesmer | -0.016 |
Token | flower |
Token ID | 15061 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
pir | +0.061 |
sometime | +0.059 |
mesmer | +0.059 |
superstar | +0.058 |
Nad | +0.057 |
Neg logit contributions | |
waste | -0.062 |
ruck | -0.061 |
cream | -0.059 |
trash | -0.058 |
Tim | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
pleasure | +0.200 |
pir | +0.194 |
superstar | +0.191 |
mesmer | +0.189 |
Doesn | +0.187 |
Neg logit contributions | |
waste | -0.048 |
Tim | -0.048 |
cream | -0.046 |
fire | -0.044 |
ash | -0.044 |
Token | gives |
Token ID | 3607 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
waste | +0.001 |
trash | +0.001 |
tools | +0.001 |
garbage | +0.001 |
ruck | +0.001 |
Neg logit contributions | |
ectar | -0.001 |
Nice | -0.001 |
superstar | -0.001 |
delighted | -0.001 |
comb | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
violet | +0.028 |
pir | +0.028 |
mesmer | +0.027 |
superstar | +0.027 |
delighted | +0.026 |
Neg logit contributions | |
ruck | -0.020 |
Tim | -0.019 |
Tom | -0.018 |
John | -0.017 |
dd | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
superstar | +0.019 |
violet | +0.019 |
pir | +0.018 |
mesmer | +0.018 |
delighted | +0.018 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.014 |
Tom | -0.012 |
tools | -0.012 |
cream | -0.012 |
Token | Ben |
Token ID | 3932 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
violet | +0.001 |
pir | +0.001 |
mesmer | +0.001 |
delighted | +0.001 |
superstar | +0.001 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.001 |
Tom | -0.001 |
John | -0.001 |
emergency | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
violet | +0.004 |
pir | +0.004 |
Flor | +0.004 |
Nad | +0.004 |
mesmer | +0.004 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
John | -0.003 |
emergency | -0.003 |
Tom | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
violet | +0.018 |
pir | +0.017 |
Flor | +0.017 |
Sparkle | +0.016 |
Nad | +0.016 |
Neg logit contributions | |
ruck | -0.027 |
Tim | -0.025 |
John | -0.024 |
emergency | -0.023 |
Tom | -0.023 |
Token | opened |
Token ID | 4721 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
violet | +0.036 |
Nice | +0.034 |
Flor | +0.034 |
tail | +0.033 |
pleasure | +0.032 |
Neg logit contributions | |
ruck | -0.023 |
Tim | -0.022 |
Tom | -0.020 |
John | -0.019 |
tools | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
violet | +0.016 |
pir | +0.016 |
superstar | +0.016 |
Nice | +0.015 |
Flor | +0.015 |
Neg logit contributions | |
ruck | -0.008 |
Tim | -0.007 |
John | -0.007 |
Tom | -0.006 |
tools | -0.006 |
Token | fl |
Token ID | 781 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
violet | +0.035 |
pir | +0.033 |
Flor | +0.033 |
Nad | +0.032 |
Sparkle | +0.032 |
Neg logit contributions | |
ruck | -0.029 |
Tim | -0.027 |
John | -0.025 |
emergency | -0.025 |
Tom | -0.024 |
Token | aps |
Token ID | 1686 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
violet | +0.034 |
Flor | +0.032 |
pir | +0.032 |
superstar | +0.031 |
Sparkle | +0.030 |
Neg logit contributions | |
ruck | -0.050 |
Tim | -0.049 |
John | -0.047 |
emergency | -0.046 |
Tom | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
violet | +0.161 |
Flor | +0.157 |
pir | +0.156 |
mesmer | +0.147 |
Nad | +0.147 |
Neg logit contributions | |
ruck | -0.109 |
Tim | -0.097 |
Tom | -0.089 |
John | -0.089 |
emergency | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
ruck | +0.023 |
Tim | +0.021 |
John | +0.020 |
emergency | +0.019 |
Tom | +0.019 |
Neg logit contributions | |
violet | -0.031 |
pir | -0.030 |
Flor | -0.030 |
superstar | -0.029 |
mesmer | -0.029 |
Token | box |
Token ID | 3091 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
ruck | +0.015 |
John | +0.014 |
dd | +0.014 |
Tim | +0.014 |
Tom | +0.013 |
Neg logit contributions | |
violet | -0.012 |
pir | -0.011 |
Flor | -0.011 |
Sparkle | -0.011 |
highest | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.011 |
Tom | +0.009 |
John | +0.009 |
tools | +0.009 |
Neg logit contributions | |
violet | -0.027 |
Flor | -0.027 |
pir | -0.026 |
Nad | -0.025 |
Sparkle | -0.025 |
Token | climbed |
Token ID | 19952 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
violet | +0.007 |
pir | +0.006 |
Flor | +0.006 |
superstar | +0.006 |
tail | +0.006 |
Neg logit contributions | |
ruck | -0.006 |
Tim | -0.006 |
John | -0.005 |
Tom | -0.005 |
dd | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ruck | +0.029 |
Tim | +0.025 |
irens | +0.025 |
John | +0.025 |
emergency | +0.025 |
Neg logit contributions | |
pir | -0.020 |
Flor | -0.020 |
violet | -0.020 |
delighted | -0.019 |
mesmer | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
ruck | +0.048 |
Tim | +0.046 |
dd | +0.045 |
John | +0.044 |
Tom | +0.043 |
Neg logit contributions | |
violet | -0.025 |
pir | -0.024 |
Flor | -0.024 |
Sparkle | -0.023 |
Nad | -0.022 |
Token | write |
Token ID | 3551 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
violet | +0.022 |
pir | +0.021 |
Flor | +0.021 |
Nad | +0.019 |
Sparkle | +0.019 |
Neg logit contributions | |
ruck | -0.028 |
Tim | -0.025 |
John | -0.024 |
irens | -0.024 |
dd | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
violet | +0.017 |
pir | +0.017 |
Flor | +0.017 |
Nad | +0.016 |
mesmer | +0.016 |
Neg logit contributions | |
ruck | -0.012 |
Tim | -0.010 |
John | -0.010 |
emergency | -0.010 |
Tom | -0.009 |
Token | own |
Token ID | 898 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
violet | +0.001 |
Flor | +0.001 |
pir | +0.001 |
mesmer | +0.001 |
Rosa | +0.001 |
Neg logit contributions | |
ruck | -0.001 |
emergency | -0.001 |
tools | -0.001 |
cream | -0.001 |
waste | -0.001 |
Token | song |
Token ID | 3496 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
violet | +0.034 |
Flor | +0.033 |
pir | +0.032 |
Nad | +0.031 |
Sparkle | +0.031 |
Neg logit contributions | |
ruck | -0.029 |
emergency | -0.025 |
Tim | -0.024 |
tools | -0.023 |
John | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
violet | +0.183 |
pir | +0.175 |
Flor | +0.172 |
mesmer | +0.169 |
Nad | +0.164 |
Neg logit contributions | |
ruck | -0.090 |
Tim | -0.077 |
emergency | -0.072 |
John | -0.070 |
Tom | -0.067 |
Token | He |
Token ID | 679 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ruck | +0.009 |
Tim | +0.007 |
emergency | +0.007 |
dd | +0.007 |
John | +0.007 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.009 |
Flor | -0.009 |
Nad | -0.009 |
Sparkle | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
ruck | +0.045 |
Tim | +0.041 |
irens | +0.040 |
emergency | +0.040 |
John | +0.039 |
Neg logit contributions | |
violet | -0.035 |
pir | -0.035 |
Flor | -0.034 |
delighted | -0.032 |
superstar | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ruck | +0.000 |
Tim | +0.000 |
John | +0.000 |
Tom | +0.000 |
emergency | +0.000 |
Neg logit contributions | |
violet | -0.000 |
Flor | -0.000 |
pir | -0.000 |
Sparkle | -0.000 |
Nad | -0.000 |
Token | lot |
Token ID | 1256 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
ruck | +0.003 |
emergency | +0.003 |
Tim | +0.003 |
John | +0.002 |
Tom | +0.002 |
Neg logit contributions | |
violet | -0.004 |
Flor | -0.004 |
pir | -0.004 |
Nad | -0.004 |
mesmer | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
violet | +0.047 |
pir | +0.046 |
Flor | +0.044 |
mesmer | +0.043 |
Nad | +0.042 |
Neg logit contributions | |
ruck | -0.035 |
Tim | -0.031 |
emergency | -0.031 |
Tom | -0.029 |
John | -0.029 |
Token | You |
Token ID | 921 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ruck | +0.016 |
Tim | +0.015 |
John | +0.014 |
Tom | +0.014 |
emergency | +0.014 |
Neg logit contributions | |
violet | -0.010 |
pir | -0.010 |
Flor | -0.009 |
delighted | -0.009 |
mesmer | -0.009 |
Token | 're |
Token ID | 821 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
ruck | +0.004 |
Tim | +0.003 |
emergency | +0.003 |
waste | +0.003 |
Tom | +0.003 |
Neg logit contributions | |
violet | -0.004 |
pir | -0.004 |
Flor | -0.004 |
Nad | -0.004 |
Nice | -0.003 |
Token | ruining |
Token ID | 39842 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
violet | +0.014 |
pir | +0.014 |
tail | +0.014 |
lap | +0.013 |
wrists | +0.013 |
Neg logit contributions | |
ruck | -0.014 |
emergency | -0.013 |
Tim | -0.013 |
waste | -0.012 |
John | -0.012 |
Token | our |
Token ID | 674 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
violet | +0.004 |
pir | +0.004 |
Flor | +0.004 |
Sparkle | +0.004 |
Nad | +0.004 |
Neg logit contributions | |
ruck | -0.005 |
Tim | -0.005 |
John | -0.004 |
emergency | -0.004 |
Tom | -0.004 |
Token | song |
Token ID | 3496 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
violet | +0.011 |
Flor | +0.010 |
Nad | +0.010 |
Nice | +0.010 |
pir | +0.010 |
Neg logit contributions | |
emergency | -0.009 |
ruck | -0.009 |
Tim | -0.008 |
waste | -0.008 |
tools | -0.008 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
violet | +0.156 |
pir | +0.146 |
Flor | +0.142 |
Nad | +0.135 |
mesmer | +0.135 |
Neg logit contributions | |
ruck | -0.116 |
Tim | -0.107 |
emergency | -0.098 |
Tom | -0.097 |
cream | -0.096 |
Token | The |
Token ID | 383 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
violet | +0.003 |
Flor | +0.003 |
pir | +0.003 |
Sparkle | +0.003 |
Nad | +0.003 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
John | -0.004 |
emergency | -0.003 |
Tom | -0.003 |
Token | shy |
Token ID | 15800 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
ruck | +0.032 |
Tim | +0.028 |
John | +0.027 |
irens | +0.027 |
dd | +0.026 |
Neg logit contributions | |
violet | -0.036 |
pir | -0.034 |
Flor | -0.034 |
delighted | -0.033 |
Sparkle | -0.032 |
Token | little |
Token ID | 1310 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
violet | +0.017 |
Flor | +0.016 |
pir | +0.016 |
superstar | +0.015 |
delighted | +0.015 |
Neg logit contributions | |
ruck | -0.026 |
John | -0.025 |
Tim | -0.024 |
irens | -0.024 |
dd | -0.023 |
Token | bird |
Token ID | 6512 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
ruck | +0.011 |
Tim | +0.011 |
emergency | +0.010 |
Tom | +0.010 |
John | +0.010 |
Neg logit contributions | |
violet | -0.014 |
pir | -0.014 |
Flor | -0.013 |
Nad | -0.013 |
Sparkle | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ruck | +0.010 |
John | +0.008 |
Tim | +0.008 |
Tom | +0.007 |
emergency | +0.007 |
Neg logit contributions | |
violet | -0.017 |
pir | -0.016 |
Flor | -0.016 |
ind | -0.015 |
Nad | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Tim | +0.010 |
ruck | +0.010 |
Tom | +0.009 |
John | +0.009 |
Billy | +0.008 |
Neg logit contributions | |
pir | -0.012 |
violet | -0.012 |
mesmer | -0.012 |
delighted | -0.011 |
superstar | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ruck | +0.012 |
emergency | +0.011 |
Tim | +0.011 |
irens | +0.010 |
John | +0.010 |
Neg logit contributions | |
violet | -0.014 |
Flor | -0.014 |
pir | -0.014 |
Sparkle | -0.013 |
delighted | -0.013 |
Token | At |
Token ID | 2953 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
Flor | +0.003 |
Sparkle | +0.003 |
mesmer | +0.003 |
Neg logit contributions | |
ruck | -0.004 |
emergency | -0.003 |
irens | -0.003 |
tools | -0.003 |
Tim | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
violet | +0.034 |
pir | +0.033 |
Flor | +0.033 |
Sparkle | +0.031 |
Nad | +0.031 |
Neg logit contributions | |
ruck | -0.028 |
Tim | -0.025 |
John | -0.024 |
emergency | -0.023 |
Tom | -0.023 |
Token | wedding |
Token ID | 10614 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
violet | +0.027 |
pir | +0.026 |
Flor | +0.026 |
mesmer | +0.025 |
Sparkle | +0.025 |
Neg logit contributions | |
ruck | -0.022 |
Tim | -0.021 |
emergency | -0.019 |
John | -0.019 |
Tom | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
violet | +0.167 |
mesmer | +0.156 |
pir | +0.155 |
Flor | +0.152 |
tail | +0.151 |
Neg logit contributions | |
ruck | -0.096 |
emergency | -0.089 |
Tim | -0.087 |
John | -0.083 |
Tom | -0.083 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
violet | +0.046 |
Flor | +0.045 |
pir | +0.045 |
Sparkle | +0.042 |
Nad | +0.042 |
Neg logit contributions | |
ruck | -0.043 |
Tim | -0.039 |
John | -0.037 |
emergency | -0.036 |
irens | -0.035 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
violet | +0.040 |
Flor | +0.037 |
Nice | +0.037 |
pir | +0.036 |
Violet | +0.035 |
Neg logit contributions | |
ruck | -0.034 |
Tim | -0.029 |
Tom | -0.028 |
John | -0.028 |
dd | -0.027 |
Token | her |
Token ID | 607 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
violet | +0.004 |
Flor | +0.004 |
pir | +0.004 |
Sparkle | +0.004 |
Nad | +0.004 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
John | -0.004 |
emergency | -0.003 |
Tom | -0.003 |
Token | impressive |
Token ID | 8036 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
violet | +0.026 |
pir | +0.024 |
Want | +0.023 |
superstar | +0.022 |
ind | +0.022 |
Neg logit contributions | |
ruck | -0.021 |
tools | -0.020 |
emergency | -0.020 |
cream | -0.019 |
waste | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
violet | +0.017 |
pir | +0.017 |
Flor | +0.016 |
superstar | +0.016 |
tail | +0.016 |
Neg logit contributions | |
ruck | -0.008 |
Tim | -0.007 |
John | -0.007 |
Tom | -0.007 |
emergency | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
Tim | +0.002 |
Tom | +0.002 |
ruck | +0.002 |
John | +0.002 |
waste | +0.002 |
Neg logit contributions | |
violet | -0.002 |
superstar | -0.002 |
pir | -0.002 |
mesmer | -0.002 |
Flor | -0.002 |
Token | closed |
Token ID | 4838 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
violet | +0.026 |
Flor | +0.025 |
pir | +0.025 |
Sparkle | +0.024 |
superstar | +0.024 |
Neg logit contributions | |
ruck | -0.023 |
Tim | -0.022 |
John | -0.020 |
Tom | -0.020 |
emergency | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
violet | +0.049 |
pir | +0.048 |
Flor | +0.047 |
Sparkle | +0.045 |
superstar | +0.045 |
Neg logit contributions | |
ruck | -0.040 |
Tim | -0.036 |
John | -0.034 |
emergency | -0.033 |
Tom | -0.033 |
Token | fl |
Token ID | 781 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
violet | +0.016 |
pir | +0.015 |
Flor | +0.014 |
Sparkle | +0.014 |
highest | +0.014 |
Neg logit contributions | |
ruck | -0.021 |
dd | -0.021 |
John | -0.021 |
Tim | -0.020 |
irens | -0.019 |
Token | aps |
Token ID | 1686 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
violet | +0.028 |
Flor | +0.026 |
pir | +0.025 |
superstar | +0.024 |
Sparkle | +0.024 |
Neg logit contributions | |
Tim | -0.038 |
ruck | -0.038 |
John | -0.037 |
emergency | -0.037 |
Tom | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
violet | +0.142 |
pir | +0.137 |
Flor | +0.136 |
Sparkle | +0.129 |
Nad | +0.129 |
Neg logit contributions | |
ruck | -0.125 |
Tim | -0.115 |
John | -0.108 |
emergency | -0.106 |
Tom | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ruck | +0.016 |
dd | +0.015 |
Tim | +0.015 |
John | +0.015 |
emergency | +0.014 |
Neg logit contributions | |
violet | -0.015 |
Flor | -0.015 |
pir | -0.014 |
Sparkle | -0.014 |
Nad | -0.013 |
Token | box |
Token ID | 3091 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
dd | +0.014 |
John | +0.014 |
ruck | +0.013 |
irens | +0.013 |
Jon | +0.013 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.008 |
highest | -0.008 |
Flor | -0.007 |
Sparkle | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ruck | +0.005 |
Tim | +0.004 |
John | +0.004 |
tools | +0.004 |
emergency | +0.004 |
Neg logit contributions | |
violet | -0.007 |
Flor | -0.007 |
pir | -0.007 |
superstar | -0.007 |
Nad | -0.007 |
Token | pretended |
Token ID | 36766 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
John | +0.001 |
Tom | +0.001 |
emergency | +0.001 |
Neg logit contributions | |
violet | -0.001 |
pir | -0.001 |
Flor | -0.001 |
superstar | -0.001 |
Sparkle | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
violet | +0.003 |
Flor | +0.003 |
pir | +0.003 |
Sparkle | +0.003 |
delighted | +0.003 |
Neg logit contributions | |
ruck | -0.003 |
emergency | -0.003 |
irens | -0.003 |
Tim | -0.003 |
iren | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ruck | +0.014 |
Tim | +0.012 |
irens | +0.012 |
John | +0.012 |
emergency | +0.011 |
Neg logit contributions | |
violet | -0.022 |
pir | -0.021 |
Flor | -0.021 |
superstar | -0.020 |
delighted | -0.020 |
Token | brave |
Token ID | 14802 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
violet | +0.017 |
pir | +0.016 |
Flor | +0.016 |
delighted | +0.015 |
superstar | +0.015 |
Neg logit contributions | |
ruck | -0.020 |
Tim | -0.018 |
John | -0.018 |
irens | -0.017 |
Tom | -0.017 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ruck | +0.009 |
John | +0.008 |
Tim | +0.008 |
irens | +0.008 |
dd | +0.008 |
Neg logit contributions | |
violet | -0.009 |
Flor | -0.008 |
pir | -0.008 |
superstar | -0.008 |
Sparkle | -0.008 |
Token | year |
Token ID | 614 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ruck | +0.034 |
Enough | +0.030 |
Stop | +0.030 |
arl | +0.029 |
anked | +0.029 |
Neg logit contributions | |
delighted | -0.040 |
violet | -0.039 |
pir | -0.039 |
Ana | -0.038 |
Flor | -0.037 |
Token | old |
Token ID | 1468 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
ruck | +0.043 |
Tim | +0.040 |
Stop | +0.040 |
John | +0.039 |
Tom | +0.038 |
Neg logit contributions | |
violet | -0.042 |
Flor | -0.041 |
pir | -0.040 |
delighted | -0.038 |
Sparkle | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ruck | +0.114 |
irens | +0.112 |
John | +0.108 |
Tim | +0.108 |
dd | +0.107 |
Neg logit contributions | |
violet | -0.110 |
Flor | -0.105 |
superstar | -0.102 |
tail | -0.101 |
Sparkle | -0.100 |
Token | He |
Token ID | 679 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
violet | +0.007 |
pir | +0.007 |
Flor | +0.007 |
Nad | +0.007 |
Nice | +0.007 |
Neg logit contributions | |
ruck | -0.009 |
dd | -0.008 |
Tim | -0.008 |
emergency | -0.008 |
irens | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
ruck | +0.053 |
irens | +0.047 |
emergency | +0.046 |
Tim | +0.046 |
John | +0.045 |
Neg logit contributions | |
violet | -0.038 |
pir | -0.037 |
Flor | -0.036 |
Sparkle | -0.035 |
delighted | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ruck | +0.022 |
Tim | +0.021 |
emergency | +0.020 |
John | +0.020 |
Tom | +0.019 |
Neg logit contributions | |
violet | -0.015 |
pir | -0.015 |
Flor | -0.014 |
superstar | -0.014 |
Nad | -0.013 |
Token | bit |
Token ID | 1643 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ruck | +0.016 |
Tim | +0.015 |
John | +0.014 |
emergency | +0.014 |
Tom | +0.014 |
Neg logit contributions | |
violet | -0.017 |
pir | -0.017 |
Flor | -0.017 |
Sparkle | -0.016 |
Nad | -0.016 |
Token | Joe |
Token ID | 19585 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.016 |
emergency | +0.016 |
John | +0.015 |
irens | +0.015 |
Neg logit contributions | |
violet | -0.012 |
Flor | -0.012 |
pir | -0.012 |
Sparkle | -0.011 |
Nad | -0.011 |
Token | y |
Token ID | 88 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
ruck | +0.055 |
Tim | +0.052 |
emergency | +0.051 |
irens | +0.050 |
John | +0.049 |
Neg logit contributions | |
violet | -0.043 |
Flor | -0.041 |
pir | -0.040 |
delighted | -0.039 |
mesmer | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
ruck | +0.003 |
Tim | +0.003 |
John | +0.003 |
emergency | +0.002 |
Tom | +0.002 |
Neg logit contributions | |
violet | -0.003 |
pir | -0.003 |
Flor | -0.003 |
Sparkle | -0.003 |
Nad | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
ruck | +0.025 |
Tim | +0.024 |
John | +0.023 |
emergency | +0.022 |
Tom | +0.022 |
Neg logit contributions | |
violet | -0.021 |
pir | -0.020 |
Flor | -0.020 |
Nad | -0.019 |
Sparkle | -0.019 |
Token | 3 |
Token ID | 513 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
ruck | +0.022 |
Tim | +0.021 |
John | +0.019 |
emergency | +0.019 |
Tom | +0.019 |
Neg logit contributions | |
violet | -0.029 |
pir | -0.028 |
Flor | -0.028 |
Sparkle | -0.027 |
Nad | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
ruck | +0.027 |
Tim | +0.023 |
arl | +0.022 |
irens | +0.022 |
Stop | +0.022 |
Neg logit contributions | |
delighted | -0.032 |
pir | -0.030 |
mesmer | -0.029 |
violet | -0.029 |
Ana | -0.029 |
Token | year |
Token ID | 1941 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
ruck | +0.129 |
emergency | +0.117 |
garbage | +0.111 |
Tim | +0.110 |
irens | +0.108 |
Neg logit contributions | |
violet | -0.135 |
delighted | -0.135 |
Flor | -0.134 |
pir | -0.127 |
bug | -0.127 |
Token | - |
Token ID | 12 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
Tim | +0.097 |
ruck | +0.093 |
Stop | +0.090 |
John | +0.088 |
Tom | +0.084 |
Neg logit contributions | |
delighted | -0.145 |
violet | -0.142 |
pir | -0.141 |
Flor | -0.139 |
mesmer | -0.135 |
Token | old |
Token ID | 727 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
ruck | +0.106 |
emergency | +0.099 |
garbage | +0.096 |
Stop | +0.094 |
Tim | +0.090 |
Neg logit contributions | |
delighted | -0.154 |
Flor | -0.154 |
violet | -0.151 |
tail | -0.150 |
pir | -0.146 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ruck | +0.087 |
Tim | +0.080 |
John | +0.074 |
emergency | +0.074 |
irens | +0.074 |
Neg logit contributions | |
violet | -0.102 |
Flor | -0.101 |
pir | -0.099 |
delighted | -0.096 |
Sparkle | -0.096 |
Token | who |
Token ID | 508 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
ruck | +0.032 |
Tim | +0.030 |
John | +0.028 |
emergency | +0.027 |
Tom | +0.027 |
Neg logit contributions | |
violet | -0.036 |
Flor | -0.035 |
pir | -0.035 |
Sparkle | -0.033 |
Nad | -0.033 |
Token | - |
Token ID | 532 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ruck | +0.050 |
John | +0.045 |
irens | +0.044 |
emergency | +0.044 |
Tim | +0.044 |
Neg logit contributions | |
violet | -0.028 |
Flor | -0.026 |
tail | -0.025 |
pir | -0.024 |
Sparkle | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
ruck | +0.029 |
Tim | +0.026 |
John | +0.024 |
emergency | +0.024 |
irens | +0.023 |
Neg logit contributions | |
violet | -0.043 |
pir | -0.042 |
Flor | -0.042 |
Sparkle | -0.040 |
Nad | -0.040 |
Token | three |
Token ID | 1115 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
violet | +0.012 |
pir | +0.012 |
Flor | +0.011 |
superstar | +0.011 |
Sparkle | +0.011 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
John | -0.008 |
emergency | -0.008 |
irens | -0.008 |
Token | - |
Token ID | 12 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.011 |
John | +0.010 |
irens | +0.010 |
Billy | +0.010 |
Neg logit contributions | |
violet | -0.021 |
pir | -0.020 |
delighted | -0.020 |
Flor | -0.019 |
superstar | -0.019 |
Token | year |
Token ID | 1941 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ruck | +0.105 |
emergency | +0.103 |
irens | +0.098 |
anked | +0.098 |
Stop | +0.097 |
Neg logit contributions | |
violet | -0.108 |
Flor | -0.105 |
delighted | -0.102 |
pir | -0.098 |
tail | -0.096 |
Token | - |
Token ID | 12 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
Tim | +0.085 |
ruck | +0.083 |
John | +0.080 |
Stop | +0.076 |
Tom | +0.073 |
Neg logit contributions | |
violet | -0.141 |
pir | -0.140 |
delighted | -0.138 |
Flor | -0.135 |
mesmer | -0.131 |
Token | old |
Token ID | 727 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ruck | +0.086 |
Stop | +0.085 |
emergency | +0.084 |
anked | +0.079 |
Enough | +0.077 |
Neg logit contributions | |
Flor | -0.137 |
violet | -0.137 |
delighted | -0.135 |
pir | -0.132 |
royal | -0.131 |
Token | named |
Token ID | 3706 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ruck | +0.066 |
Tim | +0.060 |
irens | +0.060 |
John | +0.059 |
dd | +0.057 |
Neg logit contributions | |
violet | -0.101 |
Flor | -0.100 |
superstar | -0.097 |
pir | -0.096 |
Sparkle | -0.094 |
Token | Peter |
Token ID | 5613 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Flor | +0.041 |
Nad | +0.039 |
violet | +0.039 |
Nice | +0.038 |
Sparkle | +0.038 |
Neg logit contributions | |
ruck | -0.038 |
emergency | -0.032 |
dd | -0.032 |
irens | -0.032 |
anked | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
irens | +0.039 |
ruck | +0.039 |
Tim | +0.038 |
John | +0.037 |
emergency | +0.037 |
Neg logit contributions | |
violet | -0.026 |
Flor | -0.025 |
Sparkle | -0.024 |
pir | -0.023 |
Nad | -0.023 |
Token | Peter |
Token ID | 5613 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
ruck | +0.007 |
Tim | +0.006 |
John | +0.006 |
emergency | +0.006 |
Tom | +0.006 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.009 |
Flor | -0.009 |
Nad | -0.008 |
Sparkle | -0.008 |
Token | Daddy |
Token ID | 26926 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ruck | +0.020 |
irens | +0.019 |
iren | +0.018 |
emergency | +0.018 |
agons | +0.018 |
Neg logit contributions | |
delighted | -0.013 |
violet | -0.013 |
Flor | -0.013 |
Rosa | -0.013 |
pir | -0.013 |
Token | took |
Token ID | 1718 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
irens | +0.052 |
Tim | +0.049 |
ruck | +0.048 |
emergency | +0.047 |
bomb | +0.046 |
Neg logit contributions | |
violet | -0.032 |
definitely | -0.030 |
delighted | -0.030 |
Flor | -0.029 |
Nad | -0.028 |
Token | Sara |
Token ID | 24799 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
cut | +0.039 |
ruck | +0.038 |
Tim | +0.034 |
coon | +0.033 |
arl | +0.033 |
Neg logit contributions | |
Flor | -0.024 |
Sparkle | -0.023 |
Ana | -0.023 |
Rosa | -0.023 |
Nad | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
Flor | +0.034 |
violet | +0.034 |
pir | +0.034 |
tail | +0.033 |
Sparkle | +0.033 |
Neg logit contributions | |
ruck | -0.071 |
Tim | -0.069 |
John | -0.066 |
emergency | -0.065 |
Tom | -0.065 |
Token | 3 |
Token ID | 513 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
violet | +0.002 |
pir | +0.002 |
highest | +0.002 |
nic | +0.002 |
Flor | +0.002 |
Neg logit contributions | |
ruck | -0.002 |
Tim | -0.002 |
dd | -0.002 |
John | -0.002 |
Tom | -0.002 |
Token | - |
Token ID | 12 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
ruck | +0.017 |
Tim | +0.016 |
Billy | +0.015 |
arl | +0.015 |
Stop | +0.015 |
Neg logit contributions | |
pir | -0.018 |
delighted | -0.017 |
Ana | -0.017 |
lap | -0.017 |
royal | -0.016 |
Token | year |
Token ID | 1941 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
emergency | +0.116 |
garbage | +0.108 |
waste | +0.108 |
ruck | +0.107 |
Tim | +0.106 |
Neg logit contributions | |
violet | -0.107 |
Flor | -0.106 |
seven | -0.103 |
tail | -0.103 |
pir | -0.102 |
Token | - |
Token ID | 12 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
Tim | +0.110 |
Stop | +0.104 |
Billy | +0.100 |
John | +0.099 |
ruck | +0.097 |
Neg logit contributions | |
pir | -0.135 |
delighted | -0.132 |
violet | -0.132 |
Flor | -0.129 |
royal | -0.128 |
Token | old |
Token ID | 727 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
emergency | +0.108 |
garbage | +0.103 |
waste | +0.098 |
Stop | +0.098 |
Tim | +0.096 |
Neg logit contributions | |
Flor | -0.127 |
violet | -0.125 |
pir | -0.125 |
tail | -0.124 |
seven | -0.123 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ruck | +0.096 |
Tim | +0.096 |
dd | +0.088 |
John | +0.088 |
irens | +0.088 |
Neg logit contributions | |
Flor | -0.073 |
pir | -0.070 |
delighted | -0.069 |
Nad | -0.067 |
violet | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
ruck | +0.040 |
Tim | +0.037 |
irens | +0.036 |
dd | +0.036 |
iren | +0.034 |
Neg logit contributions | |
pir | -0.028 |
violet | -0.027 |
tail | -0.026 |
Flor | -0.026 |
Nad | -0.026 |
Token | her |
Token ID | 607 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Flor | +0.034 |
Sparkle | +0.032 |
Violet | +0.031 |
violet | +0.031 |
Rose | +0.029 |
Neg logit contributions | |
ruck | -0.055 |
dd | -0.050 |
John | -0.049 |
irens | -0.048 |
emergency | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
violet | +0.012 |
pir | +0.011 |
Flor | +0.011 |
Nad | +0.011 |
mesmer | +0.011 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
emergency | -0.009 |
Tom | -0.008 |
John | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
violet | +0.007 |
pir | +0.007 |
Flor | +0.007 |
mesmer | +0.007 |
superstar | +0.007 |
Neg logit contributions | |
ruck | -0.011 |
Tim | -0.011 |
Tom | -0.010 |
John | -0.010 |
emergency | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ruck | +0.008 |
emergency | +0.008 |
dd | +0.007 |
Tim | +0.007 |
irens | +0.007 |
Neg logit contributions | |
violet | -0.005 |
Flor | -0.005 |
pir | -0.004 |
Sparkle | -0.004 |
Nad | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
violet | +0.007 |
Flor | +0.006 |
pir | +0.006 |
tail | +0.006 |
Violet | +0.006 |
Neg logit contributions | |
ruck | -0.012 |
emergency | -0.010 |
cubes | -0.009 |
dd | -0.009 |
fuel | -0.009 |
Token | Stop |
Token ID | 19485 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
violet | +0.030 |
Flor | +0.029 |
pir | +0.028 |
Violet | +0.027 |
Sparkle | +0.027 |
Neg logit contributions | |
ruck | -0.021 |
emergency | -0.017 |
irens | -0.016 |
ime | -0.015 |
agons | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ruck | +0.130 |
Tim | +0.120 |
John | +0.113 |
emergency | +0.111 |
Tom | +0.110 |
Neg logit contributions | |
violet | -0.122 |
pir | -0.116 |
Flor | -0.115 |
Nad | -0.109 |
Sparkle | -0.108 |
Token | ! |
Token ID | 0 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.006 |
Flor | +0.006 |
Sparkle | +0.006 |
Nad | +0.006 |
Neg logit contributions | |
ruck | -0.008 |
Tim | -0.007 |
John | -0.007 |
emergency | -0.007 |
Tom | -0.007 |
Token | Stop |
Token ID | 13707 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ruck | +0.024 |
Tim | +0.023 |
John | +0.022 |
emergency | +0.021 |
Tom | +0.021 |
Neg logit contributions | |
violet | -0.015 |
pir | -0.015 |
Flor | -0.015 |
Sparkle | -0.014 |
Nad | -0.013 |
Token | rocking |
Token ID | 38059 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ruck | +0.090 |
Tim | +0.084 |
John | +0.079 |
emergency | +0.078 |
Tom | +0.077 |
Neg logit contributions | |
violet | -0.071 |
pir | -0.067 |
Flor | -0.067 |
Sparkle | -0.063 |
Nad | -0.063 |
Token | ! |
Token ID | 0 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
ruck | +0.004 |
Tim | +0.004 |
John | +0.004 |
emergency | +0.003 |
Tom | +0.003 |
Neg logit contributions | |
violet | -0.004 |
pir | -0.004 |
Flor | -0.004 |
superstar | -0.004 |
Nad | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ruck | +0.007 |
Tim | +0.007 |
John | +0.006 |
Tom | +0.006 |
dd | +0.006 |
Neg logit contributions | |
violet | -0.010 |
pir | -0.009 |
tail | -0.009 |
mesmer | -0.009 |
Flor | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
tail | +0.007 |
pir | +0.006 |
highest | +0.006 |
Flor | +0.006 |
violet | +0.006 |
Neg logit contributions | |
Tim | -0.006 |
ruck | -0.006 |
John | -0.005 |
Tom | -0.005 |
Billy | -0.005 |
Token | I |
Token ID | 40 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
violet | +0.016 |
pir | +0.016 |
Flor | +0.016 |
Nad | +0.015 |
delighted | +0.015 |
Neg logit contributions | |
ruck | -0.011 |
Tim | -0.011 |
Tom | -0.010 |
John | -0.010 |
dd | -0.009 |
Token | 'm |
Token ID | 1101 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
ruck | +0.005 |
Tim | +0.004 |
Tom | +0.004 |
dd | +0.004 |
waste | +0.004 |
Neg logit contributions | |
violet | -0.006 |
wrists | -0.006 |
pir | -0.005 |
Flor | -0.005 |
Sparkle | -0.005 |
Token | glad |
Token ID | 9675 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
wrists | +0.030 |
tail | +0.030 |
pir | +0.028 |
superstar | +0.028 |
violet | +0.027 |
Neg logit contributions | |
ruck | -0.026 |
John | -0.024 |
dd | -0.024 |
emergency | -0.024 |
Tim | -0.023 |
Token | you |
Token ID | 345 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
violet | +0.032 |
pir | +0.030 |
superstar | +0.029 |
delighted | +0.029 |
mesmer | +0.029 |
Neg logit contributions | |
ruck | -0.025 |
Tim | -0.024 |
John | -0.022 |
Tom | -0.022 |
emergency | -0.021 |
Token | like |
Token ID | 588 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
ruck | +0.035 |
Tim | +0.030 |
waste | +0.029 |
dd | +0.028 |
Tom | +0.028 |
Neg logit contributions | |
violet | -0.033 |
pir | -0.032 |
Flor | -0.031 |
Violet | -0.029 |
Nad | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
ruck | +0.026 |
Tim | +0.023 |
emergency | +0.022 |
John | +0.021 |
dd | +0.020 |
Neg logit contributions | |
violet | -0.036 |
tail | -0.036 |
pir | -0.036 |
superstar | -0.035 |
Flor | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
ruck | +0.024 |
Tim | +0.021 |
emergency | +0.019 |
John | +0.019 |
Tom | +0.018 |
Neg logit contributions | |
violet | -0.041 |
pir | -0.040 |
Flor | -0.039 |
wrists | -0.039 |
mesmer | -0.038 |
Token | You |
Token ID | 921 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Tim | +0.002 |
Tom | +0.002 |
ruck | +0.002 |
John | +0.002 |
Billy | +0.002 |
Neg logit contributions | |
pir | -0.003 |
wrists | -0.003 |
delighted | -0.003 |
mesmer | -0.003 |
bou | -0.003 |
Token | can |
Token ID | 460 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ruck | +0.005 |
Tim | +0.004 |
waste | +0.004 |
Tom | +0.004 |
John | +0.004 |
Neg logit contributions | |
violet | -0.005 |
pir | -0.005 |
Flor | -0.005 |
Nice | -0.005 |
tail | -0.005 |
Token | from |
Token ID | 422 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
violet | +0.054 |
pir | +0.053 |
Flor | +0.050 |
superstar | +0.049 |
mesmer | +0.049 |
Neg logit contributions | |
ruck | -0.046 |
Tim | -0.042 |
John | -0.038 |
Tom | -0.037 |
emergency | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Flor | +0.020 |
violet | +0.019 |
pir | +0.019 |
Sparkle | +0.019 |
tail | +0.018 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.013 |
John | -0.012 |
Tom | -0.012 |
irens | -0.012 |
Token | hot |
Token ID | 3024 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
violet | +0.008 |
pir | +0.008 |
Flor | +0.008 |
Sparkle | +0.007 |
delighted | +0.007 |
Neg logit contributions | |
ruck | -0.009 |
Tim | -0.008 |
John | -0.008 |
irens | -0.008 |
dd | -0.008 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.015 |
Flor | +0.013 |
tail | +0.013 |
lap | +0.013 |
Neg logit contributions | |
ruck | -0.022 |
John | -0.021 |
Tim | -0.020 |
dd | -0.020 |
irens | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.005 |
Flor | +0.005 |
Nad | +0.005 |
delighted | +0.005 |
Neg logit contributions | |
ruck | -0.003 |
Tim | -0.003 |
emergency | -0.003 |
John | -0.003 |
Tom | -0.003 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ruck | +0.007 |
Tim | +0.006 |
emergency | +0.006 |
John | +0.006 |
dd | +0.005 |
Neg logit contributions | |
violet | -0.007 |
pir | -0.007 |
Flor | -0.007 |
Sparkle | -0.006 |
delighted | -0.006 |
Token | my |
Token ID | 1820 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
ruck | +0.043 |
Tim | +0.039 |
irens | +0.038 |
emergency | +0.038 |
John | +0.038 |
Neg logit contributions | |
violet | -0.047 |
pir | -0.045 |
Flor | -0.044 |
Nad | -0.043 |
Sparkle | -0.043 |
Token | thought |
Token ID | 1807 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
ruck | +0.024 |
Tim | +0.023 |
John | +0.021 |
Tom | +0.021 |
dd | +0.020 |
Neg logit contributions | |
violet | -0.033 |
Flor | -0.032 |
pir | -0.031 |
Sparkle | -0.030 |
superstar | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.017 |
John | +0.016 |
irens | +0.016 |
Tom | +0.015 |
Neg logit contributions | |
pir | -0.012 |
violet | -0.012 |
Flor | -0.011 |
delighted | -0.011 |
Sparkle | -0.011 |
Token | hat |
Token ID | 6877 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Flor | +0.030 |
violet | +0.029 |
Sparkle | +0.029 |
pir | +0.029 |
superstar | +0.028 |
Neg logit contributions | |
ruck | -0.024 |
Tim | -0.022 |
Tom | -0.021 |
emergency | -0.020 |
John | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
violet | +0.065 |
Flor | +0.062 |
pir | +0.061 |
Nad | +0.059 |
Rosa | +0.057 |
Neg logit contributions | |
ruck | -0.049 |
Tim | -0.046 |
emergency | -0.041 |
John | -0.041 |
Tom | -0.040 |
Token | found |
Token ID | 1043 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
violet | +0.024 |
Flor | +0.022 |
Nice | +0.021 |
pir | +0.021 |
Want | +0.021 |
Neg logit contributions | |
ruck | -0.019 |
Tim | -0.018 |
Tom | -0.017 |
John | -0.017 |
dd | -0.017 |
Token | herself |
Token ID | 5223 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
ruck | +0.059 |
Tim | +0.054 |
John | +0.051 |
emergency | +0.050 |
Tom | +0.049 |
Neg logit contributions | |
violet | -0.069 |
pir | -0.066 |
Flor | -0.066 |
superstar | -0.063 |
Nad | -0.062 |
Token | walking |
Token ID | 6155 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
violet | +0.022 |
Flor | +0.020 |
pir | +0.020 |
Nad | +0.020 |
superstar | +0.019 |
Neg logit contributions | |
ruck | -0.018 |
Tim | -0.016 |
John | -0.015 |
emergency | -0.015 |
Tom | -0.015 |
Token | towards |
Token ID | 3371 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
John | +0.001 |
emergency | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
violet | -0.001 |
pir | -0.001 |
Flor | -0.001 |
Sparkle | -0.001 |
Nad | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
violet | +0.006 |
pir | +0.006 |
Flor | +0.005 |
superstar | +0.005 |
delighted | +0.005 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
John | -0.004 |
emergency | -0.004 |
Tom | -0.004 |
Token | woods |
Token ID | 16479 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ruck | +0.004 |
Tim | +0.004 |
emergency | +0.004 |
John | +0.004 |
Tom | +0.004 |
Neg logit contributions | |
violet | -0.004 |
pir | -0.004 |
Flor | -0.004 |
Nad | -0.004 |
Sparkle | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ruck | +0.053 |
Tim | +0.048 |
John | +0.044 |
emergency | +0.043 |
Tom | +0.043 |
Neg logit contributions | |
violet | -0.073 |
pir | -0.070 |
Flor | -0.069 |
superstar | -0.066 |
Nad | -0.066 |
Token | |
Token ID | 220 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
Tim | +0.012 |
Tom | +0.012 |
John | +0.011 |
ruck | +0.011 |
Dad | +0.011 |
Neg logit contributions | |
superstar | -0.015 |
violet | -0.015 |
pir | -0.015 |
tail | -0.015 |
ind | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
violet | +0.029 |
Flor | +0.028 |
pir | +0.028 |
Sparkle | +0.026 |
Nad | +0.026 |
Neg logit contributions | |
ruck | -0.035 |
Tim | -0.032 |
John | -0.031 |
emergency | -0.030 |
Tom | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
Tim | +0.015 |
ruck | +0.015 |
John | +0.015 |
Tom | +0.015 |
dd | +0.013 |
Neg logit contributions | |
violet | -0.019 |
pir | -0.019 |
superstar | -0.019 |
tail | -0.018 |
Flor | -0.018 |
Token | Before |
Token ID | 8421 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
ruck | +0.002 |
Tim | +0.002 |
John | +0.002 |
Tom | +0.002 |
dd | +0.002 |
Neg logit contributions | |
violet | -0.003 |
Flor | -0.003 |
pir | -0.003 |
superstar | -0.003 |
Sparkle | -0.003 |
Token | best |
Token ID | 1266 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
violet | +0.026 |
pir | +0.026 |
Flor | +0.025 |
mesmer | +0.024 |
delighted | +0.024 |
Neg logit contributions | |
ruck | -0.035 |
Tim | -0.033 |
emergency | -0.032 |
John | -0.030 |
Tom | -0.030 |
Token | day |
Token ID | 1110 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
Flor | +0.003 |
Nad | +0.003 |
Sparkle | +0.003 |
Neg logit contributions | |
ruck | -0.003 |
Tim | -0.003 |
John | -0.003 |
emergency | -0.003 |
Tom | -0.003 |
Token | ever |
Token ID | 1683 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
ruck | +0.046 |
Tim | +0.043 |
John | +0.041 |
Tom | +0.040 |
dd | +0.039 |
Neg logit contributions | |
violet | -0.043 |
pir | -0.040 |
Flor | -0.039 |
mesmer | -0.038 |
superstar | -0.038 |
Token | ! |
Token ID | 0 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
violet | +0.022 |
pir | +0.021 |
Flor | +0.021 |
mesmer | +0.020 |
Nad | +0.020 |
Neg logit contributions | |
ruck | -0.022 |
Tim | -0.020 |
Tom | -0.018 |
John | -0.018 |
emergency | -0.018 |
Token | I |
Token ID | 314 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Tim | +0.039 |
Tom | +0.037 |
ruck | +0.036 |
John | +0.036 |
Stop | +0.032 |
Neg logit contributions | |
violet | -0.029 |
pir | -0.029 |
mesmer | -0.028 |
Flor | -0.028 |
delighted | -0.028 |
Token | love |
Token ID | 1842 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ruck | +0.006 |
Tim | +0.005 |
Tom | +0.005 |
dd | +0.005 |
John | +0.005 |
Neg logit contributions | |
violet | -0.006 |
pir | -0.006 |
Flor | -0.006 |
wrists | -0.006 |
Sparkle | -0.006 |
Token | you |
Token ID | 345 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ruck | +0.031 |
Tim | +0.028 |
John | +0.026 |
emergency | +0.026 |
Tom | +0.025 |
Neg logit contributions | |
violet | -0.042 |
pir | -0.041 |
Flor | -0.040 |
mesmer | -0.040 |
superstar | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
ruck | +0.052 |
Tim | +0.044 |
Tom | +0.042 |
John | +0.041 |
emergency | +0.039 |
Neg logit contributions | |
pir | -0.070 |
Flor | -0.069 |
violet | -0.069 |
mesmer | -0.066 |
Nad | -0.063 |
Token | Max |
Token ID | 5436 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
Tim | +0.009 |
ruck | +0.008 |
Tom | +0.008 |
emergency | +0.008 |
John | +0.007 |
Neg logit contributions | |
violet | -0.016 |
mesmer | -0.015 |
pir | -0.015 |
tail | -0.015 |
Flor | -0.015 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ruck | +0.029 |
Tim | +0.027 |
Tom | +0.026 |
John | +0.025 |
emergency | +0.024 |
Neg logit contributions | |
violet | -0.030 |
pir | -0.030 |
Flor | -0.028 |
mesmer | -0.028 |
Nad | -0.027 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ruck | +0.008 |
Tim | +0.007 |
Tom | +0.007 |
John | +0.007 |
irens | +0.006 |
Neg logit contributions | |
violet | -0.010 |
pir | -0.009 |
Flor | -0.009 |
mesmer | -0.009 |
superstar | -0.009 |
Token | proud |
Token ID | 6613 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
violet | +0.027 |
pir | +0.025 |
Flor | +0.025 |
Sparkle | +0.024 |
superstar | +0.023 |
Neg logit contributions | |
ruck | -0.041 |
Tim | -0.039 |
John | -0.037 |
emergency | -0.036 |
Tom | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
violet | +0.023 |
pir | +0.022 |
Flor | +0.022 |
Sparkle | +0.021 |
Nad | +0.021 |
Neg logit contributions | |
ruck | -0.017 |
Tim | -0.015 |
John | -0.014 |
emergency | -0.014 |
Tom | -0.013 |
Token | himself |
Token ID | 2241 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ruck | +0.023 |
Tim | +0.020 |
emergency | +0.018 |
irens | +0.018 |
John | +0.018 |
Neg logit contributions | |
violet | -0.030 |
Flor | -0.030 |
pir | -0.028 |
Sparkle | -0.028 |
Nad | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ruck | +0.058 |
Tim | +0.053 |
John | +0.050 |
emergency | +0.049 |
Tom | +0.048 |
Neg logit contributions | |
violet | -0.061 |
pir | -0.059 |
Flor | -0.058 |
superstar | -0.055 |
Nad | -0.055 |
Token | He |
Token ID | 679 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ruck | +0.010 |
Tim | +0.010 |
John | +0.009 |
Tom | +0.009 |
emergency | +0.009 |
Neg logit contributions | |
violet | -0.012 |
pir | -0.012 |
Flor | -0.012 |
superstar | -0.011 |
mesmer | -0.011 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ruck | +0.035 |
Tim | +0.034 |
John | +0.032 |
Tom | +0.032 |
dd | +0.030 |
Neg logit contributions | |
violet | -0.043 |
pir | -0.040 |
tail | -0.040 |
Flor | -0.040 |
superstar | -0.039 |
Token | dressing |
Token ID | 18544 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
ruck | +0.043 |
Tim | +0.040 |
John | +0.037 |
emergency | +0.037 |
Tom | +0.036 |
Neg logit contributions | |
violet | -0.041 |
pir | -0.039 |
Flor | -0.039 |
Sparkle | -0.037 |
delighted | -0.036 |
Token | up |
Token ID | 510 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
violet | +0.001 |
pir | +0.001 |
Flor | +0.001 |
Sparkle | +0.001 |
Nad | +0.001 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.001 |
John | -0.001 |
emergency | -0.001 |
Tom | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
violet | +0.040 |
Flor | +0.040 |
pir | +0.039 |
Sparkle | +0.037 |
Nad | +0.037 |
Neg logit contributions | |
ruck | -0.041 |
Tim | -0.038 |
John | -0.036 |
emergency | -0.036 |
irens | -0.035 |
Token | feeling |
Token ID | 4203 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
violet | +0.018 |
Flor | +0.017 |
pir | +0.017 |
superstar | +0.016 |
tail | +0.016 |
Neg logit contributions | |
ruck | -0.024 |
Tim | -0.021 |
John | -0.020 |
emergency | -0.020 |
Tom | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
violet | +0.017 |
pir | +0.016 |
Flor | +0.016 |
tail | +0.015 |
superstar | +0.015 |
Neg logit contributions | |
ruck | -0.021 |
Tim | -0.019 |
John | -0.019 |
emergency | -0.018 |
dd | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
Tim | +0.007 |
Tom | +0.007 |
ruck | +0.006 |
John | +0.006 |
Dad | +0.005 |
Neg logit contributions | |
pir | -0.011 |
tail | -0.011 |
violet | -0.011 |
Flor | -0.010 |
superstar | -0.010 |
Token | did |
Token ID | 750 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
violet | +0.002 |
pir | +0.002 |
Flor | +0.002 |
tail | +0.002 |
Nice | +0.002 |
Neg logit contributions | |
ruck | -0.002 |
Tim | -0.002 |
Tom | -0.002 |
John | -0.002 |
waste | -0.002 |
Token | not |
Token ID | 407 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
violet | +0.017 |
tail | +0.017 |
pir | +0.016 |
Sparkle | +0.016 |
Nad | +0.016 |
Neg logit contributions | |
ruck | -0.013 |
Tim | -0.012 |
Tom | -0.012 |
waste | -0.012 |
cream | -0.011 |
Token | like |
Token ID | 588 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ruck | +0.043 |
John | +0.041 |
Tim | +0.041 |
irens | +0.040 |
emergency | +0.040 |
Neg logit contributions | |
violet | -0.025 |
pir | -0.024 |
Flor | -0.024 |
superstar | -0.022 |
Sparkle | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ruck | +0.016 |
Tim | +0.014 |
John | +0.014 |
irens | +0.013 |
dd | +0.013 |
Neg logit contributions | |
violet | -0.016 |
Flor | -0.016 |
pir | -0.015 |
Sparkle | -0.015 |
Nad | -0.014 |
Token | comb |
Token ID | 1974 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ruck | +0.004 |
Tim | +0.003 |
John | +0.003 |
emergency | +0.003 |
irens | +0.003 |
Neg logit contributions | |
violet | -0.004 |
Flor | -0.004 |
pir | -0.004 |
Sparkle | -0.003 |
Nad | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
violet | +0.056 |
pir | +0.054 |
Flor | +0.053 |
mesmer | +0.051 |
Sparkle | +0.051 |
Neg logit contributions | |
ruck | -0.041 |
Tim | -0.037 |
emergency | -0.034 |
John | -0.033 |
Tom | -0.033 |
Token | They |
Token ID | 1119 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Tim | +0.001 |
Tom | +0.001 |
ruck | +0.001 |
John | +0.001 |
Dad | +0.001 |
Neg logit contributions | |
pir | -0.002 |
violet | -0.002 |
tail | -0.002 |
superstar | -0.002 |
Flor | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
violet | +0.007 |
pir | +0.007 |
Flor | +0.006 |
Sparkle | +0.006 |
Nad | +0.006 |
Neg logit contributions | |
ruck | -0.006 |
Tim | -0.006 |
Tom | -0.006 |
John | -0.006 |
emergency | -0.005 |
Token | angry |
Token ID | 7954 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.016 |
emergency | +0.015 |
Tom | +0.015 |
John | +0.015 |
Neg logit contributions | |
violet | -0.019 |
pir | -0.018 |
tail | -0.018 |
Flor | -0.018 |
superstar | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
ruck | +0.008 |
Tim | +0.007 |
John | +0.007 |
emergency | +0.006 |
Tom | +0.006 |
Neg logit contributions | |
violet | -0.008 |
pir | -0.008 |
Flor | -0.008 |
Sparkle | -0.007 |
Nad | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
ruck | +0.007 |
Tim | +0.006 |
emergency | +0.006 |
arl | +0.006 |
leaning | +0.006 |
Neg logit contributions | |
Flor | -0.004 |
Sparkle | -0.004 |
pir | -0.004 |
Nad | -0.004 |
Rosa | -0.004 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ruck | +0.029 |
Tim | +0.027 |
John | +0.025 |
emergency | +0.025 |
Tom | +0.024 |
Neg logit contributions | |
violet | -0.032 |
pir | -0.031 |
Flor | -0.031 |
Sparkle | -0.029 |
Nad | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ruck | +0.006 |
Tim | +0.006 |
emergency | +0.006 |
irens | +0.006 |
John | +0.005 |
Neg logit contributions | |
violet | -0.004 |
pir | -0.004 |
Flor | -0.004 |
Sparkle | -0.003 |
delighted | -0.003 |
Token | take |
Token ID | 1011 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
irens | +0.001 |
dd | +0.001 |
John | +0.001 |
Neg logit contributions | |
violet | -0.001 |
pir | -0.001 |
Flor | -0.001 |
Sparkle | -0.001 |
Nad | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ruck | +0.006 |
Tim | +0.005 |
Tom | +0.005 |
cut | +0.005 |
John | +0.005 |
Neg logit contributions | |
Sparkle | -0.004 |
pir | -0.004 |
Flor | -0.004 |
violet | -0.004 |
tail | -0.004 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ruck | +0.009 |
Tim | +0.008 |
John | +0.008 |
Tom | +0.008 |
irens | +0.008 |
Neg logit contributions | |
violet | -0.008 |
pir | -0.008 |
Flor | -0.008 |
Sparkle | -0.008 |
superstar | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
pir | +0.004 |
violet | +0.003 |
Flor | +0.003 |
tail | +0.003 |
Sparkle | +0.003 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
emergency | -0.004 |
John | -0.004 |
Tom | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
violet | +0.013 |
pir | +0.013 |
Flor | +0.013 |
Sparkle | +0.012 |
Nad | +0.012 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
John | -0.009 |
emergency | -0.009 |
Tom | -0.008 |
Token | woods |
Token ID | 16479 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.012 |
John | +0.011 |
dd | +0.011 |
irens | +0.011 |
Neg logit contributions | |
violet | -0.012 |
Flor | -0.012 |
pir | -0.012 |
Sparkle | -0.011 |
tail | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ruck | +0.063 |
Tim | +0.058 |
John | +0.054 |
emergency | +0.053 |
Tom | +0.053 |
Neg logit contributions | |
violet | -0.073 |
pir | -0.071 |
Flor | -0.070 |
Sparkle | -0.067 |
Nad | -0.067 |
Token | As |
Token ID | 1081 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
violet | +0.009 |
pir | +0.008 |
Flor | +0.008 |
Sparkle | +0.008 |
Nad | +0.008 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.006 |
John | -0.006 |
emergency | -0.006 |
Tom | -0.006 |
Token | lly |
Token ID | 12810 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
violet | +0.010 |
Flor | +0.009 |
pir | +0.009 |
Sparkle | +0.009 |
superstar | +0.009 |
Neg logit contributions | |
ruck | -0.009 |
Tim | -0.008 |
John | -0.008 |
Tom | -0.008 |
dd | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.014 |
Flor | +0.014 |
delighted | +0.013 |
mesmer | +0.013 |
Neg logit contributions | |
ruck | -0.017 |
Tim | -0.016 |
emergency | -0.015 |
John | -0.015 |
irens | -0.014 |
Token | confused |
Token ID | 10416 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ruck | +0.024 |
John | +0.023 |
emergency | +0.022 |
Tim | +0.021 |
ime | +0.021 |
Neg logit contributions | |
violet | -0.018 |
superstar | -0.018 |
tail | -0.018 |
Nice | -0.018 |
Want | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ruck | +0.009 |
Tim | +0.008 |
John | +0.008 |
Tom | +0.008 |
emergency | +0.008 |
Neg logit contributions | |
violet | -0.008 |
Flor | -0.008 |
pir | -0.008 |
mesmer | -0.007 |
delighted | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ruck | +0.011 |
Tim | +0.010 |
John | +0.010 |
Tom | +0.010 |
emergency | +0.009 |
Neg logit contributions | |
violet | -0.010 |
pir | -0.009 |
superstar | -0.009 |
tail | -0.009 |
Flor | -0.009 |
Token | walked |
Token ID | 6807 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
violet | +0.001 |
Flor | +0.001 |
pir | +0.001 |
superstar | +0.000 |
Sparkle | +0.000 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.000 |
John | -0.000 |
emergency | -0.000 |
Tom | -0.000 |
Token | closer |
Token ID | 5699 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
ruck | +0.012 |
Tim | +0.011 |
John | +0.011 |
Tom | +0.010 |
emergency | +0.010 |
Neg logit contributions | |
violet | -0.009 |
pir | -0.008 |
Flor | -0.008 |
superstar | -0.008 |
tail | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
violet | +0.023 |
pir | +0.022 |
Flor | +0.022 |
superstar | +0.022 |
tail | +0.021 |
Neg logit contributions | |
ruck | -0.020 |
Tim | -0.018 |
John | -0.017 |
Tom | -0.016 |
emergency | -0.016 |
Token | asked |
Token ID | 1965 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
Flor | +0.003 |
superstar | +0.003 |
tail | +0.003 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
John | -0.004 |
Tom | -0.004 |
emergency | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ruck | +0.023 |
Tim | +0.021 |
John | +0.020 |
emergency | +0.020 |
Tom | +0.019 |
Neg logit contributions | |
violet | -0.022 |
pir | -0.021 |
Flor | -0.021 |
Sparkle | -0.020 |
Nad | -0.020 |
Token | k |
Token ID | 479 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.005 |
Flor | +0.005 |
superstar | +0.005 |
delighted | +0.005 |
Neg logit contributions | |
ruck | -0.006 |
Tim | -0.005 |
emergency | -0.005 |
John | -0.005 |
Tom | -0.005 |
Token | put |
Token ID | 1234 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
violet | +0.008 |
Flor | +0.008 |
pir | +0.008 |
Sparkle | +0.007 |
Nad | +0.007 |
Neg logit contributions | |
ruck | -0.012 |
Tim | -0.011 |
John | -0.010 |
irens | -0.010 |
emergency | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
violet | +0.011 |
Flor | +0.011 |
pir | +0.011 |
Sparkle | +0.010 |
tail | +0.010 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
John | -0.009 |
Tom | -0.008 |
emergency | -0.008 |
Token | shirt |
Token ID | 10147 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.017 |
emergency | +0.016 |
John | +0.016 |
Tom | +0.015 |
Neg logit contributions | |
violet | -0.016 |
pir | -0.015 |
Flor | -0.015 |
Nad | -0.014 |
superstar | -0.014 |
Token | back |
Token ID | 736 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
violet | +0.041 |
pir | +0.040 |
Flor | +0.039 |
Sparkle | +0.037 |
delighted | +0.037 |
Neg logit contributions | |
ruck | -0.057 |
Tim | -0.054 |
John | -0.051 |
emergency | -0.051 |
irens | -0.050 |
Token | on |
Token ID | 319 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
violet | +0.054 |
pir | +0.052 |
Flor | +0.052 |
Sparkle | +0.050 |
Nad | +0.049 |
Neg logit contributions | |
ruck | -0.045 |
Tim | -0.042 |
John | -0.039 |
emergency | -0.038 |
Tom | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
violet | +0.046 |
Flor | +0.046 |
pir | +0.045 |
Sparkle | +0.044 |
Nad | +0.043 |
Neg logit contributions | |
ruck | -0.040 |
Tim | -0.036 |
John | -0.034 |
emergency | -0.033 |
irens | -0.033 |
Token | He |
Token ID | 679 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
violet | +0.003 |
pir | +0.003 |
superstar | +0.003 |
delighted | +0.003 |
mesmer | +0.003 |
Neg logit contributions | |
Tim | -0.002 |
ruck | -0.002 |
Tom | -0.002 |
John | -0.002 |
irens | -0.002 |
Token | felt |
Token ID | 2936 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
Tim | +0.026 |
ruck | +0.026 |
Tom | +0.024 |
John | +0.024 |
dd | +0.023 |
Neg logit contributions | |
violet | -0.033 |
Nice | -0.030 |
pir | -0.030 |
Flor | -0.030 |
tail | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
violet | +0.018 |
pir | +0.017 |
Flor | +0.016 |
superstar | +0.016 |
tail | +0.016 |
Neg logit contributions | |
ruck | -0.025 |
Tim | -0.023 |
John | -0.023 |
emergency | -0.022 |
Tom | -0.022 |
Token | lot |
Token ID | 1256 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
ruck | +0.027 |
Tim | +0.025 |
John | +0.023 |
emergency | +0.023 |
Tom | +0.022 |
Neg logit contributions | |
violet | -0.033 |
pir | -0.032 |
Flor | -0.032 |
Sparkle | -0.030 |
superstar | -0.030 |
Token | better |
Token ID | 1365 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.017 |
John | +0.017 |
emergency | +0.016 |
Tom | +0.016 |
Neg logit contributions | |
violet | -0.013 |
Flor | -0.012 |
pir | -0.012 |
delighted | -0.012 |
Sparkle | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ruck | +0.001 |
Tim | +0.001 |
Tom | +0.001 |
John | +0.001 |
emergency | +0.001 |
Neg logit contributions | |
violet | -0.001 |
Flor | -0.001 |
pir | -0.001 |
superstar | -0.001 |
mesmer | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Tim | +0.028 |
ruck | +0.026 |
Tom | +0.025 |
tools | +0.024 |
ts | +0.024 |
Neg logit contributions | |
Nice | -0.045 |
tail | -0.042 |
pir | -0.041 |
pleasure | -0.041 |
Want | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.015 |
Flor | +0.014 |
superstar | +0.014 |
mesmer | +0.014 |
Neg logit contributions | |
ruck | -0.014 |
Tim | -0.014 |
John | -0.013 |
emergency | -0.013 |
Tom | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
violet | +0.037 |
pir | +0.036 |
Flor | +0.036 |
Sparkle | +0.034 |
Nad | +0.034 |
Neg logit contributions | |
ruck | -0.031 |
Tim | -0.028 |
John | -0.026 |
emergency | -0.026 |
Tom | -0.025 |
Token | drum |
Token ID | 13026 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
violet | +0.035 |
pir | +0.034 |
Flor | +0.034 |
Nad | +0.032 |
Sparkle | +0.032 |
Neg logit contributions | |
ruck | -0.034 |
Tim | -0.031 |
emergency | -0.029 |
John | -0.028 |
Tom | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
pir | +0.035 |
violet | +0.035 |
mesmer | +0.034 |
Flor | +0.033 |
Nad | +0.033 |
Neg logit contributions | |
ruck | -0.023 |
Tim | -0.021 |
emergency | -0.020 |
tools | -0.019 |
Tom | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
tail | +0.005 |
pir | +0.005 |
Flor | +0.005 |
violet | +0.005 |
superstar | +0.005 |
Neg logit contributions | |
ruck | -0.006 |
Tim | -0.005 |
John | -0.005 |
Tom | -0.005 |
emergency | -0.005 |
Token | Let |
Token ID | 5756 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
violet | +0.025 |
pir | +0.023 |
Flor | +0.023 |
superstar | +0.022 |
ind | +0.022 |
Neg logit contributions | |
ruck | -0.022 |
emergency | -0.021 |
irens | -0.020 |
John | -0.019 |
Tim | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
violet | +0.024 |
pir | +0.023 |
Flor | +0.022 |
Sparkle | +0.020 |
Nad | +0.020 |
Neg logit contributions | |
ruck | -0.076 |
Tim | -0.070 |
John | -0.068 |
irens | -0.068 |
emergency | -0.067 |
Token | watch |
Token ID | 2342 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
violet | +0.031 |
pir | +0.031 |
Flor | +0.030 |
superstar | +0.029 |
delighted | +0.029 |
Neg logit contributions | |
ruck | -0.031 |
Tim | -0.030 |
emergency | -0.028 |
waste | -0.027 |
Tom | -0.027 |
Token | this |
Token ID | 428 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
violet | +0.092 |
pir | +0.090 |
superstar | +0.089 |
Nad | +0.089 |
Flor | +0.087 |
Neg logit contributions | |
ruck | -0.045 |
fires | -0.038 |
Tim | -0.038 |
emergency | -0.037 |
him | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
violet | +0.009 |
Flor | +0.009 |
pir | +0.009 |
Nad | +0.008 |
delighted | +0.008 |
Neg logit contributions | |
ruck | -0.017 |
irens | -0.015 |
John | -0.015 |
emergency | -0.015 |
dd | -0.015 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
violet | +0.006 |
Flor | +0.006 |
pir | +0.006 |
delighted | +0.006 |
Sparkle | +0.006 |
Neg logit contributions | |
ruck | -0.007 |
irens | -0.006 |
emergency | -0.005 |
John | -0.005 |
dd | -0.005 |
Token | my |
Token ID | 1820 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ruck | +0.064 |
irens | +0.060 |
Tim | +0.060 |
John | +0.059 |
emergency | +0.059 |
Neg logit contributions | |
violet | -0.060 |
pir | -0.057 |
superstar | -0.055 |
Flor | -0.055 |
Sparkle | -0.054 |
Token | let |
Token ID | 1309 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ruck | +0.046 |
Tim | +0.043 |
John | +0.040 |
emergency | +0.039 |
Tom | +0.039 |
Neg logit contributions | |
violet | -0.048 |
pir | -0.046 |
Flor | -0.046 |
Sparkle | -0.044 |
Nad | -0.044 |
Token | his |
Token ID | 465 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Sparkle | +0.043 |
Flor | +0.042 |
anytime | +0.042 |
pir | +0.040 |
nic | +0.040 |
Neg logit contributions | |
ruck | -0.045 |
irens | -0.041 |
dd | -0.040 |
arl | -0.040 |
John | -0.038 |
Token | sister |
Token ID | 6621 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ruck | +0.075 |
Tim | +0.070 |
emergency | +0.067 |
John | +0.065 |
Tom | +0.065 |
Neg logit contributions | |
violet | -0.065 |
Flor | -0.061 |
pir | -0.060 |
mesmer | -0.059 |
Nad | -0.057 |
Token | play |
Token ID | 711 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
violet | +0.057 |
pir | +0.056 |
Flor | +0.055 |
delighted | +0.053 |
Sparkle | +0.052 |
Neg logit contributions | |
ruck | -0.083 |
Tim | -0.077 |
John | -0.073 |
dd | -0.073 |
emergency | -0.072 |
Token | with |
Token ID | 351 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
violet | +0.021 |
pir | +0.020 |
Flor | +0.020 |
Sparkle | +0.019 |
Nad | +0.019 |
Neg logit contributions | |
ruck | -0.022 |
Tim | -0.020 |
John | -0.019 |
emergency | -0.019 |
Tom | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ruck | +0.020 |
dd | +0.018 |
arl | +0.018 |
oys | +0.018 |
Tim | +0.018 |
Neg logit contributions | |
Flor | -0.018 |
Sparkle | -0.017 |
pir | -0.016 |
Violet | -0.016 |
violet | -0.016 |
Token | car |
Token ID | 1097 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
dd | +0.006 |
ruck | +0.006 |
irens | +0.006 |
John | +0.006 |
li | +0.005 |
Neg logit contributions | |
pir | -0.006 |
violet | -0.006 |
superstar | -0.005 |
highest | -0.005 |
Flor | -0.005 |
Token | too |
Token ID | 1165 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
ruck | +0.017 |
Tim | +0.016 |
emergency | +0.015 |
John | +0.015 |
Tom | +0.015 |
Neg logit contributions | |
violet | -0.016 |
pir | -0.015 |
Flor | -0.015 |
mesmer | -0.014 |
Nad | -0.014 |
Token | dog |
Token ID | 3290 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
violet | +0.013 |
pir | +0.013 |
Flor | +0.013 |
Sparkle | +0.012 |
delighted | +0.012 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
John | -0.008 |
emergency | -0.008 |
irens | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
violet | +0.041 |
pir | +0.040 |
Flor | +0.038 |
mesmer | +0.038 |
superstar | +0.037 |
Neg logit contributions | |
ruck | -0.022 |
Tim | -0.021 |
emergency | -0.019 |
Tom | -0.018 |
John | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.005 |
superstar | +0.005 |
mesmer | +0.005 |
ind | +0.005 |
Neg logit contributions | |
Tim | -0.002 |
Tom | -0.001 |
ruck | -0.001 |
John | -0.001 |
emergency | -0.001 |
Token | thinks |
Token ID | 6834 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ruck | +0.042 |
emergency | +0.040 |
Tim | +0.040 |
Tom | +0.039 |
garbage | +0.038 |
Neg logit contributions | |
violet | -0.042 |
pir | -0.040 |
superstar | -0.040 |
Flor | -0.039 |
Nad | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.017 |
John | +0.016 |
emergency | +0.016 |
Tom | +0.015 |
Neg logit contributions | |
violet | -0.019 |
pir | -0.018 |
Flor | -0.018 |
superstar | -0.017 |
mesmer | -0.017 |
Token | dog |
Token ID | 3290 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
violet | +0.068 |
pir | +0.067 |
Flor | +0.066 |
Nad | +0.063 |
mesmer | +0.063 |
Neg logit contributions | |
ruck | -0.043 |
Tim | -0.039 |
John | -0.035 |
emergency | -0.035 |
Tom | -0.035 |
Token | might |
Token ID | 1244 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
violet | +0.077 |
pir | +0.075 |
mesmer | +0.073 |
Flor | +0.070 |
superstar | +0.070 |
Neg logit contributions | |
Tim | -0.067 |
ruck | -0.066 |
Tom | -0.063 |
emergency | -0.063 |
garbage | -0.059 |
Token | bite |
Token ID | 13197 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
violet | +0.024 |
pir | +0.023 |
superstar | +0.022 |
Flor | +0.022 |
mesmer | +0.022 |
Neg logit contributions | |
ruck | -0.023 |
Tim | -0.022 |
Tom | -0.020 |
emergency | -0.020 |
waste | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
violet | +0.047 |
pir | +0.045 |
Flor | +0.044 |
superstar | +0.043 |
mesmer | +0.043 |
Neg logit contributions | |
ruck | -0.035 |
Tim | -0.032 |
John | -0.030 |
Tom | -0.029 |
emergency | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
violet | +0.009 |
pir | +0.009 |
superstar | +0.008 |
mesmer | +0.008 |
ind | +0.008 |
Neg logit contributions | |
Tim | -0.005 |
Tom | -0.004 |
John | -0.004 |
ruck | -0.004 |
emergency | -0.004 |
Token | runs |
Token ID | 4539 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
garbage | +0.026 |
emergency | +0.026 |
Stop | +0.025 |
ruck | +0.025 |
Tom | +0.025 |
Neg logit contributions | |
violet | -0.033 |
superstar | -0.031 |
ectar | -0.031 |
pir | -0.031 |
delighted | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
Flor | +0.034 |
pir | +0.034 |
violet | +0.033 |
Sparkle | +0.033 |
Nad | +0.032 |
Neg logit contributions | |
ruck | -0.038 |
Tim | -0.035 |
dd | -0.035 |
John | -0.033 |
Tom | -0.033 |
Token | rubber |
Token ID | 14239 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
violet | +0.002 |
Flor | +0.002 |
pir | +0.002 |
Nad | +0.002 |
mesmer | +0.002 |
Neg logit contributions | |
ruck | -0.002 |
Tim | -0.002 |
emergency | -0.002 |
John | -0.002 |
Tom | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
violet | +0.009 |
pir | +0.008 |
Flor | +0.008 |
superstar | +0.008 |
Sparkle | +0.008 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
John | -0.009 |
irens | -0.008 |
Tom | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ruck | +0.002 |
Tim | +0.002 |
John | +0.001 |
emergency | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
violet | -0.002 |
pir | -0.002 |
Flor | -0.002 |
Sparkle | -0.002 |
Nad | -0.002 |
Token | neighbour |
Token ID | 12250 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
ruck | +0.010 |
dd | +0.009 |
John | +0.009 |
Tim | +0.009 |
irens | +0.009 |
Neg logit contributions | |
violet | -0.008 |
delighted | -0.007 |
Flor | -0.007 |
pir | -0.007 |
Sparkle | -0.007 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.014 |
Flor | +0.014 |
Sparkle | +0.013 |
Nad | +0.013 |
Neg logit contributions | |
ruck | -0.019 |
Tim | -0.018 |
John | -0.017 |
emergency | -0.016 |
Tom | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
violet | +0.079 |
pir | +0.075 |
Flor | +0.073 |
tail | +0.071 |
Nad | +0.070 |
Neg logit contributions | |
ruck | -0.052 |
Tim | -0.045 |
John | -0.043 |
emergency | -0.042 |
Tom | -0.041 |
Token | said |
Token ID | 531 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ruck | +0.013 |
Tim | +0.013 |
John | +0.012 |
Tom | +0.012 |
dd | +0.011 |
Neg logit contributions | |
violet | -0.014 |
pir | -0.014 |
tail | -0.014 |
Flor | -0.013 |
superstar | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
ruck | +0.007 |
Tim | +0.006 |
emergency | +0.006 |
irens | +0.006 |
John | +0.006 |
Neg logit contributions | |
Flor | -0.005 |
violet | -0.005 |
delighted | -0.005 |
Sparkle | -0.005 |
pir | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
violet | +0.018 |
Flor | +0.018 |
pir | +0.018 |
Sparkle | +0.017 |
delighted | +0.017 |
Neg logit contributions | |
ruck | -0.016 |
Tim | -0.014 |
John | -0.013 |
emergency | -0.013 |
irens | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
violet | +0.057 |
pir | +0.055 |
Flor | +0.054 |
Nad | +0.051 |
tail | +0.051 |
Neg logit contributions | |
ruck | -0.048 |
Tim | -0.045 |
John | -0.042 |
Tom | -0.041 |
dd | -0.040 |
Token | 't |
Token ID | 470 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
ruck | +0.023 |
Tim | +0.021 |
John | +0.020 |
emergency | +0.020 |
Tom | +0.019 |
Neg logit contributions | |
violet | -0.012 |
pir | -0.012 |
Flor | -0.011 |
Sparkle | -0.011 |
Nad | -0.011 |
Token | listen |
Token ID | 6004 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
irens | +0.021 |
John | +0.021 |
ruck | +0.021 |
Tim | +0.020 |
emergency | +0.020 |
Neg logit contributions | |
violet | -0.009 |
superstar | -0.009 |
pir | -0.009 |
tail | -0.009 |
Flor | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
delighted | +0.028 |
pir | +0.028 |
Sparkle | +0.027 |
violet | +0.027 |
Flor | +0.027 |
Neg logit contributions | |
ruck | -0.054 |
Tim | -0.050 |
emergency | -0.048 |
John | -0.048 |
irens | -0.047 |
Token | accidentally |
Token ID | 14716 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ruck | +0.006 |
Tim | +0.005 |
John | +0.005 |
irens | +0.005 |
emergency | +0.005 |
Neg logit contributions | |
violet | -0.005 |
Flor | -0.005 |
pir | -0.005 |
delighted | -0.004 |
Sparkle | -0.004 |
Token | knocked |
Token ID | 13642 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
ruck | +0.079 |
Tim | +0.071 |
John | +0.070 |
emergency | +0.068 |
irens | +0.066 |
Neg logit contributions | |
violet | -0.072 |
pir | -0.071 |
Flor | -0.069 |
Sparkle | -0.066 |
Nad | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ruck | +0.020 |
dd | +0.019 |
emergency | +0.018 |
John | +0.018 |
irens | +0.018 |
Neg logit contributions | |
anytime | -0.006 |
Want | -0.006 |
pro | -0.006 |
violet | -0.006 |
Flor | -0.006 |
Token | glass |
Token ID | 5405 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
violet | +0.053 |
pir | +0.051 |
Flor | +0.050 |
Sparkle | +0.048 |
Nad | +0.047 |
Neg logit contributions | |
ruck | -0.069 |
Tim | -0.065 |
emergency | -0.060 |
John | -0.060 |
Tom | -0.060 |
Token | over |
Token ID | 625 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
violet | +0.044 |
Flor | +0.043 |
pir | +0.042 |
Sparkle | +0.040 |
Nad | +0.039 |
Neg logit contributions | |
ruck | -0.061 |
John | -0.056 |
Tim | -0.055 |
dd | -0.053 |
emergency | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
too | +0.029 |
mouth | +0.028 |
anytime | +0.028 |
again | +0.028 |
so | +0.027 |
Neg logit contributions | |
ruck | -0.067 |
dd | -0.064 |
agons | -0.061 |
emergency | -0.060 |
Enough | -0.059 |
Token | It |
Token ID | 632 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
violet | +0.005 |
delighted | +0.005 |
pir | +0.005 |
Flor | +0.005 |
Sparkle | +0.005 |
Neg logit contributions | |
ruck | -0.006 |
dd | -0.006 |
emergency | -0.005 |
Tim | -0.005 |
John | -0.005 |
Token | shattered |
Token ID | 23273 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
violet | +0.010 |
pir | +0.009 |
Flor | +0.009 |
Sparkle | +0.009 |
delighted | +0.009 |
Neg logit contributions | |
ruck | -0.007 |
Tim | -0.006 |
John | -0.006 |
emergency | -0.006 |
Tom | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
violet | +0.001 |
pir | +0.001 |
Flor | +0.001 |
Sparkle | +0.001 |
Nad | +0.001 |
Neg logit contributions | |
ruck | -0.001 |
Tim | -0.001 |
John | -0.001 |
emergency | -0.001 |
Tom | -0.001 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
violet | +0.015 |
pir | +0.014 |
Flor | +0.014 |
superstar | +0.013 |
delighted | +0.013 |
Neg logit contributions | |
ruck | -0.011 |
Tim | -0.011 |
John | -0.010 |
Tom | -0.010 |
emergency | -0.009 |
Token | keeps |
Token ID | 7622 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
violet | +0.023 |
pir | +0.023 |
Nice | +0.023 |
superstar | +0.022 |
mesmer | +0.022 |
Neg logit contributions | |
ruck | -0.022 |
Tom | -0.021 |
Tim | -0.020 |
tools | -0.019 |
waste | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ruck | +0.008 |
Tim | +0.007 |
John | +0.007 |
emergency | +0.006 |
Tom | +0.006 |
Neg logit contributions | |
violet | -0.007 |
pir | -0.007 |
Flor | -0.007 |
Sparkle | -0.006 |
superstar | -0.006 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
violet | +0.012 |
pir | +0.011 |
Flor | +0.011 |
Sparkle | +0.010 |
Nad | +0.010 |
Neg logit contributions | |
ruck | -0.010 |
Tim | -0.009 |
John | -0.009 |
emergency | -0.008 |
Tom | -0.008 |
Token | doll |
Token ID | 3654 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
violet | +0.052 |
pir | +0.050 |
Flor | +0.050 |
Sparkle | +0.048 |
Nad | +0.047 |
Neg logit contributions | |
ruck | -0.031 |
Tim | -0.028 |
John | -0.026 |
emergency | -0.025 |
Tom | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
violet | +0.083 |
pir | +0.080 |
Flor | +0.078 |
mesmer | +0.077 |
superstar | +0.076 |
Neg logit contributions | |
ruck | -0.055 |
Tim | -0.052 |
emergency | -0.047 |
Tom | -0.046 |
John | -0.045 |
Token | Tom |
Token ID | 4186 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
ruck | +0.018 |
Tim | +0.018 |
Tom | +0.017 |
John | +0.016 |
irens | +0.015 |
Neg logit contributions | |
violet | -0.018 |
pir | -0.018 |
Flor | -0.017 |
superstar | -0.017 |
mesmer | -0.016 |
Token | keeps |
Token ID | 7622 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ruck | +0.019 |
Tim | +0.018 |
Tom | +0.017 |
tools | +0.016 |
John | +0.016 |
Neg logit contributions | |
violet | -0.017 |
pir | -0.016 |
superstar | -0.016 |
mesmer | -0.016 |
tail | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
violet | +0.005 |
pir | +0.005 |
Flor | +0.004 |
Sparkle | +0.004 |
Nad | +0.004 |
Neg logit contributions | |
ruck | -0.004 |
Tim | -0.004 |
John | -0.004 |
emergency | -0.004 |
Tom | -0.004 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ruck | +0.028 |
Tim | +0.026 |
emergency | +0.024 |
John | +0.024 |
Tom | +0.023 |
Neg logit contributions | |
violet | -0.033 |
pir | -0.031 |
Flor | -0.031 |
Nad | -0.030 |
mesmer | -0.030 |