TOP ACTIVATIONS
MAX = 0.074

saw a cat named Sy lves ter trying to catch him
Fire is not a toy " on the bottom . They
. And they lived happily ever after . <|endoftext|> Once upon
, and Tom lived happily ever after in their small house
, and they lived happily ever after . <|endoftext|> Once upon
said " Do not touch " or " Keep out ".
And they all lived happily ever after . <|endoftext|> Once upon
. And they lived happily ever after . <|endoftext|> Once upon
And they all lived happily ever after . <|endoftext|> Once upon
. And they lived happily ever after . <|endoftext|> One day
. And he lived happily ever after ! <|endoftext|> Once upon
got married and lived happily ever after . <|endoftext|> Once upon
And they all lived happily ever after . <|endoftext|> S ara
, and they lived happily ever after . <|endoftext|> One day
. And they lived happily ever after . <|endoftext|> Once upon
. And they lived happily ever after . <|endoftext|> Once upon
. And they lived happily ever after . <|endoftext|> One day
. And they lived happily ever after . <|endoftext|> Once upon
. And they lived happily ever after . <|endoftext|> Once upon
couple . They lived happily ever after . <|endoftext|> Tom and

MIN ACTIVATIONS
MIN = -0.074

They also see some fancy topp ings . They see sprink
, sauce , cheese and topp ings . She showed them
it at Lily . He squee zes the spray and a
of cheese and sauce and topp ings . The people who
elephants , lions and ac rob ats . They are amazed
and squ ishy . She squee zes it and it makes
likes the helmet . She squee zes the helmet on her
clown s juggling and ac rob ats doing flips . But
and squ ishy . She squee zes it and it makes
jump and laugh . The sun is warm and the wind
they can add their own topp ings too . Sara chooses
it with water . He squee zes the bottle hard and
Mom . They put on apr ons to keep their clothes
saw clown s and ac rob ats and lions and elephants
. She hugs it and squee zes it tight . She
faces and shapes with the topp ings . "
the race . They all lined up at the starting line
the sun . But the sun is very bright and hurts
. They put on their apr ons and sat on the
and Tom put on their apr ons and washed their hands

INTERVAL 0.037 - 0.074
CONTAINS 0.558%

She took a bottle of lot ion and went to her
be dangerous ." L ily did not listen .
Tim my felt sad and cried a little bit .
was a cute little girl named Lily . She had a
Fl uffy just shrugged and l icked his paw . Lily

INTERVAL -0.000 - 0.037
CONTAINS 50.503%

listen to her mom 's recommendations . From that
J ill felt like she was getting nowhere . Then
, my boat is going to China !" Ben said .
, there was a little girl named Lily . She loved
," Lily said . " You 're welcome ,

INTERVAL -0.037 - -0.000
CONTAINS 48.514%

She was very happy and put it back on
Sam says . " We number to see who is better
Every day , it grew bigger and bigger .
, we need to organize your room . Let 's start
bear . After that , Tim realized that he

INTERVAL -0.074 - -0.037
CONTAINS 0.426%

his lap . She makes soft noises that make Ben happy
darling ". <|endoftext|> Once upon a time there was a little
friends . <|endoftext|> Once upon a time , there was a
friends . He had a big horn on his head that
others . <|endoftext|> Once upon a time , there was a
Token saw
Token ID2497
Feature activation+5.30e-03

Pos logit contributions
izzy+0.022
enny+0.019
taker+0.019
 opener+0.019
ppy+0.018
Neg logit contributions
ement-0.018
irl-0.018
 mouths-0.017
 soaring-0.017
irling-0.017
Token a
Token ID257
Feature activation-3.89e-03

Pos logit contributions
izzy+0.010
enny+0.009
ppy+0.009
 opener+0.009
ro+0.009
Neg logit contributions
ement-0.008
 soaring-0.008
 mouths-0.008
 wrists-0.008
mm-0.008
Token cat
Token ID3797
Feature activation+6.44e-03

Pos logit contributions
ement+0.008
mm+0.007
 mouths+0.007
 wrists+0.007
irling+0.007
Neg logit contributions
izzy-0.006
 opener-0.005
enny-0.005
head-0.005
guard-0.005
Token named
Token ID3706
Feature activation+4.43e-02

Pos logit contributions
izzy+0.010
ppy+0.009
 opener+0.008
enny+0.008
head+0.008
Neg logit contributions
ement-0.013
 mouths-0.013
mm-0.013
 wrists-0.013
 pic-0.012
Token Sy
Token ID1632
Feature activation+3.20e-02

Pos logit contributions
izzy+0.090
enny+0.082
guard+0.080
washer+0.079
taker+0.079
Neg logit contributions
 soaring-0.063
 wrists-0.061
 mouths-0.060
mm-0.060
 blonde-0.058
Tokenlves
Token ID31018
Feature activation+7.35e-02

Pos logit contributions
izzy+0.055
enny+0.047
ppy+0.046
 opener+0.046
taker+0.045
Neg logit contributions
ement-0.059
 wrists-0.057
 mouths-0.056
irling-0.055
irl-0.055
Tokenter
Token ID353
Feature activation+1.14e-02

Pos logit contributions
enny+0.119
izzy+0.116
 opener+0.113
taker+0.103
head+0.101
Neg logit contributions
 soaring-0.141
cks-0.129
 best-0.127
 course-0.125
ement-0.122
Token trying
Token ID2111
Feature activation-4.19e-04

Pos logit contributions
izzy+0.020
enny+0.017
ppy+0.016
 opener+0.016
taker+0.016
Neg logit contributions
ement-0.021
 wrists-0.020
 mouths-0.020
mm-0.020
irl-0.020
Token to
Token ID284
Feature activation+2.04e-02

Pos logit contributions
ement+0.001
mm+0.001
irling+0.001
irl+0.001
 wrists+0.001
Neg logit contributions
izzy-0.000
 opener-0.000
enny-0.000
ppy-0.000
eware-0.000
Token catch
Token ID4929
Feature activation+1.13e-02

Pos logit contributions
izzy+0.046
enny+0.042
taker+0.039
ppy+0.039
washer+0.039
Neg logit contributions
irl-0.028
 soaring-0.027
 wrists-0.026
irling-0.025
 conversations-0.025
Token him
Token ID683
Feature activation+1.31e-02

Pos logit contributions
izzy+0.022
enny+0.020
ppy+0.019
 opener+0.019
taker+0.019
Neg logit contributions
ement-0.018
 mouths-0.017
 wrists-0.017
irling-0.016
irl-0.016
TokenFire
Token ID13543
Feature activation-1.57e-02

Pos logit contributions
izzy+0.035
enny+0.030
ppy+0.029
taker+0.029
 opener+0.029
Neg logit contributions
ement-0.033
mm-0.032
 wrists-0.031
 mouths-0.031
irl-0.031
Token is
Token ID318
Feature activation-5.03e-03

Pos logit contributions
ement+0.027
 mouths+0.026
mm+0.025
 wrists+0.025
 soaring+0.024
Neg logit contributions
izzy-0.029
enny-0.025
taker-0.024
 opener-0.024
ppy-0.023
Token not
Token ID407
Feature activation+2.27e-02

Pos logit contributions
ement+0.008
 wrists+0.007
 mouths+0.007
irling+0.007
mm+0.007
Neg logit contributions
izzy-0.010
enny-0.009
 opener-0.009
ppy-0.009
taker-0.009
Token a
Token ID257
Feature activation+1.17e-02

Pos logit contributions
izzy+0.043
enny+0.038
ppy+0.037
 opener+0.037
taker+0.037
Neg logit contributions
ement-0.037
 wrists-0.035
 mouths-0.035
irling-0.035
mm-0.034
Token toy
Token ID13373
Feature activation+2.66e-02

Pos logit contributions
izzy+0.022
 opener+0.019
taker+0.019
enny+0.019
ro+0.019
Neg logit contributions
ement-0.019
irling-0.018
mm-0.018
 wrists-0.018
irl-0.018
Token"
Token ID1
Feature activation+7.16e-02

Pos logit contributions
izzy+0.052
enny+0.046
ppy+0.044
taker+0.042
 opener+0.042
Neg logit contributions
ement-0.043
 mouths-0.042
 wrists-0.040
mm-0.040
 soaring-0.039
Token on
Token ID319
Feature activation+8.26e-03

Pos logit contributions
izzy+0.121
taker+0.104
enny+0.102
ppy+0.099
 opener+0.097
Neg logit contributions
ement-0.127
 wrists-0.122
mm-0.120
 mouths-0.120
 conversations-0.118
Token the
Token ID262
Feature activation+3.69e-03

Pos logit contributions
izzy+0.016
enny+0.014
ppy+0.013
 opener+0.013
taker+0.013
Neg logit contributions
ement-0.013
 wrists-0.013
 mouths-0.013
irling-0.013
mm-0.012
Token bottom
Token ID4220
Feature activation+8.15e-03

Pos logit contributions
izzy+0.007
ro+0.006
 opener+0.006
taker+0.006
ppy+0.006
Neg logit contributions
ement-0.006
irling-0.006
irl-0.006
mm-0.006
 mouths-0.005
Token.
Token ID13
Feature activation+1.26e-02

Pos logit contributions
izzy+0.014
enny+0.012
ppy+0.012
taker+0.012
 opener+0.011
Neg logit contributions
ement-0.015
 mouths-0.014
 soaring-0.014
 wrists-0.014
 conversations-0.013
Token They
Token ID1119
Feature activation-3.30e-03

Pos logit contributions
izzy+0.026
enny+0.023
 opener+0.023
ppy+0.023
taker+0.023
Neg logit contributions
ement-0.018
 wrists-0.017
 mouths-0.017
irling-0.017
irl-0.017
Token.
Token ID13
Feature activation-1.67e-02

Pos logit contributions
ement+0.010
 wrists+0.009
irl+0.009
irling+0.009
 mouths+0.009
Neg logit contributions
izzy-0.008
enny-0.007
 opener-0.007
taker-0.007
ppy-0.006
Token And
Token ID843
Feature activation-1.08e-02

Pos logit contributions
ement+0.028
irling+0.026
 wrists+0.026
irl+0.026
 soaring+0.026
Neg logit contributions
izzy-0.032
enny-0.028
 opener-0.027
taker-0.027
ro-0.027
Token they
Token ID484
Feature activation-8.03e-03

Pos logit contributions
ement+0.020
irling+0.020
 wrists+0.019
 mouths+0.019
irl+0.019
Neg logit contributions
izzy-0.018
enny-0.016
 opener-0.015
taker-0.015
ro-0.015
Token lived
Token ID5615
Feature activation-5.47e-03

Pos logit contributions
ement+0.009
 mouths+0.008
 wrists+0.008
irl+0.008
 soaring+0.008
Neg logit contributions
izzy-0.020
enny-0.018
 opener-0.017
ppy-0.017
taker-0.017
Token happily
Token ID18177
Feature activation+4.33e-02

Pos logit contributions
ement+0.008
 wrists+0.007
 mouths+0.007
irl+0.007
irling+0.007
Neg logit contributions
izzy-0.012
enny-0.010
ppy-0.010
 opener-0.010
taker-0.010
Token ever
Token ID1683
Feature activation+7.11e-02

Pos logit contributions
izzy+0.066
enny+0.055
 opener+0.054
taker+0.053
ppy+0.053
Neg logit contributions
ement-0.087
 mouths-0.085
 soaring-0.084
 wrists-0.084
mm-0.083
Token after
Token ID706
Feature activation+1.01e-02

Pos logit contributions
izzy+0.116
taker+0.095
 opener+0.092
enny+0.092
washer+0.086
Neg logit contributions
 mouths-0.138
 conversations-0.137
 soaring-0.131
 disagreement-0.130
 pic-0.129
Token.
Token ID13
Feature activation-2.59e-02

Pos logit contributions
izzy+0.015
enny+0.012
 opener+0.012
taker+0.012
ppy+0.012
Neg logit contributions
ement-0.021
 wrists-0.021
 mouths-0.020
mm-0.020
irling-0.020
Token<|endoftext|>
Token ID50256
Feature activation+1.82e-02

Pos logit contributions
ement+0.050
 wrists+0.049
irling+0.049
irl+0.048
 mouths+0.047
Neg logit contributions
izzy-0.043
enny-0.036
 opener-0.035
ily-0.034
taker-0.034
TokenOnce
Token ID7454
Feature activation-1.68e-02

Pos logit contributions
izzy+0.035
enny+0.030
ppy+0.030
 opener+0.030
taker+0.029
Neg logit contributions
ement-0.029
 mouths-0.028
 wrists-0.028
irl-0.027
irling-0.027
Token upon
Token ID2402
Feature activation+8.89e-03

Pos logit contributions
ement+0.033
 mouths+0.031
 wrists+0.031
irling+0.031
irl+0.031
Neg logit contributions
izzy-0.027
enny-0.023
ppy-0.022
 opener-0.022
taker-0.022
Token,
Token ID11
Feature activation-9.33e-04

Pos logit contributions
ement+0.010
 mouths+0.009
 wrists+0.009
irling+0.009
irl+0.009
Neg logit contributions
izzy-0.015
enny-0.013
 opener-0.013
taker-0.013
ppy-0.013
Token and
Token ID290
Feature activation-6.64e-03

Pos logit contributions
ement+0.002
irling+0.002
 wrists+0.002
irl+0.002
 mouths+0.002
Neg logit contributions
izzy-0.002
enny-0.001
ppy-0.001
 opener-0.001
taker-0.001
Token Tom
Token ID4186
Feature activation-1.01e-02

Pos logit contributions
ement+0.013
irling+0.012
 wrists+0.012
irl+0.012
 mouths+0.012
Neg logit contributions
izzy-0.011
enny-0.010
 opener-0.009
ppy-0.009
taker-0.009
Token lived
Token ID5615
Feature activation+1.30e-03

Pos logit contributions
ement+0.015
 wrists+0.014
 mouths+0.014
irling+0.014
mm+0.014
Neg logit contributions
izzy-0.021
ppy-0.018
enny-0.018
taker-0.018
 opener-0.018
Token happily
Token ID18177
Feature activation+4.97e-02

Pos logit contributions
izzy+0.003
enny+0.002
ppy+0.002
 opener+0.002
taker+0.002
Neg logit contributions
ement-0.002
 mouths-0.002
 wrists-0.002
irl-0.002
irling-0.002
Token ever
Token ID1683
Feature activation+7.11e-02

Pos logit contributions
izzy+0.069
enny+0.057
ppy+0.054
 opener+0.054
taker+0.053
Neg logit contributions
ement-0.108
 mouths-0.104
 wrists-0.104
irling-0.102
irl-0.102
Token after
Token ID706
Feature activation+1.74e-02

Pos logit contributions
izzy+0.111
enny+0.092
taker+0.089
 opener+0.088
washer+0.081
Neg logit contributions
 conversations-0.142
 mouths-0.142
 soaring-0.139
 disagreement-0.136
 pic-0.135
Token in
Token ID287
Feature activation-7.05e-03

Pos logit contributions
izzy+0.026
enny+0.022
 opener+0.022
ppy+0.021
taker+0.021
Neg logit contributions
ement-0.035
 wrists-0.034
 mouths-0.034
mm-0.033
irling-0.032
Token their
Token ID511
Feature activation-1.01e-02

Pos logit contributions
ement+0.013
 wrists+0.012
 mouths+0.012
irling+0.012
mm+0.012
Neg logit contributions
izzy-0.012
 opener-0.011
enny-0.011
ppy-0.010
taker-0.010
Token small
Token ID1402
Feature activation-1.21e-02

Pos logit contributions
ement+0.017
mm+0.017
cks+0.016
heit+0.015
irling+0.015
Neg logit contributions
guard-0.016
ro-0.014
washer-0.013
mer-0.013
izzy-0.013
Token house
Token ID2156
Feature activation+6.32e-03

Pos logit contributions
mm+0.023
irling+0.023
cks+0.023
ement+0.023
irl+0.022
Neg logit contributions
izzy-0.017
ro-0.017
guard-0.017
head-0.016
enny-0.015
Token,
Token ID11
Feature activation-1.16e-02

Pos logit contributions
izzy+0.017
 opener+0.015
ro+0.014
enny+0.014
ppy+0.014
Neg logit contributions
ement-0.025
mm-0.024
 mouths-0.024
 wrists-0.024
irling-0.023
Token and
Token ID290
Feature activation-1.46e-02

Pos logit contributions
ement+0.025
heit+0.023
mm+0.023
 mouths+0.022
 wrists+0.022
Neg logit contributions
izzy-0.016
ro-0.015
 opener-0.014
t-0.014
taker-0.014
Token they
Token ID484
Feature activation-4.99e-03

Pos logit contributions
ement+0.029
irling+0.027
irl+0.026
 wrists+0.026
mm+0.025
Neg logit contributions
izzy-0.024
ro-0.020
enny-0.020
ppy-0.020
taker-0.020
Token lived
Token ID5615
Feature activation-2.88e-03

Pos logit contributions
ement+0.007
 mouths+0.007
 wrists+0.007
mm+0.007
irling+0.007
Neg logit contributions
izzy-0.010
enny-0.009
ppy-0.009
 opener-0.009
taker-0.009
Token happily
Token ID18177
Feature activation+4.40e-02

Pos logit contributions
ement+0.004
irl+0.004
 wrists+0.004
 soaring+0.004
irling+0.004
Neg logit contributions
izzy-0.006
enny-0.006
ppy-0.006
 opener-0.006
taker-0.006
Token ever
Token ID1683
Feature activation+7.10e-02

Pos logit contributions
izzy+0.068
enny+0.057
 opener+0.056
taker+0.055
ppy+0.055
Neg logit contributions
ement-0.087
 soaring-0.086
 mouths-0.085
 wrists-0.084
irling-0.083
Token after
Token ID706
Feature activation+1.11e-02

Pos logit contributions
izzy+0.119
taker+0.100
 opener+0.098
enny+0.097
washer+0.092
Neg logit contributions
 mouths-0.132
 conversations-0.131
 soaring-0.126
 disagreement-0.126
 tails-0.125
Token.
Token ID13
Feature activation-2.36e-02

Pos logit contributions
izzy+0.015
enny+0.012
 opener+0.012
taker+0.012
ppy+0.011
Neg logit contributions
ement-0.024
 mouths-0.024
 wrists-0.024
mm-0.023
aman-0.022
Token<|endoftext|>
Token ID50256
Feature activation+1.41e-02

Pos logit contributions
ement+0.046
 wrists+0.045
irling+0.045
irl+0.044
 mouths+0.043
Neg logit contributions
izzy-0.039
enny-0.034
 opener-0.032
ily-0.031
taker-0.031
TokenOnce
Token ID7454
Feature activation-1.98e-02

Pos logit contributions
izzy+0.027
enny+0.024
ppy+0.024
taker+0.023
 opener+0.023
Neg logit contributions
ement-0.022
 mouths-0.021
 wrists-0.021
irl-0.021
 soaring-0.021
Token upon
Token ID2402
Feature activation+7.15e-03

Pos logit contributions
ement+0.038
 mouths+0.036
 wrists+0.036
irl+0.036
irling+0.036
Neg logit contributions
izzy-0.032
enny-0.027
ppy-0.027
 opener-0.026
taker-0.026
Token said
Token ID531
Feature activation-3.64e-03

Pos logit contributions
izzy+0.003
enny+0.003
 opener+0.003
taker+0.003
ppy+0.003
Neg logit contributions
ement-0.003
 wrists-0.003
irling-0.003
 mouths-0.003
mm-0.003
Token "
Token ID366
Feature activation+4.31e-02

Pos logit contributions
ement+0.006
 wrists+0.006
 mouths+0.006
irling+0.005
irl+0.005
Neg logit contributions
izzy-0.007
enny-0.006
ppy-0.006
 opener-0.006
taker-0.006
TokenDo
Token ID5211
Feature activation-1.41e-02

Pos logit contributions
izzy+0.078
enny+0.067
taker+0.067
 opener+0.065
ppy+0.065
Neg logit contributions
ement-0.073
 wrists-0.070
mm-0.070
 mouths-0.069
irl-0.069
Token not
Token ID407
Feature activation+1.62e-02

Pos logit contributions
ement+0.017
 mouths+0.016
 wrists+0.016
irl+0.016
irling+0.016
Neg logit contributions
izzy-0.033
enny-0.029
ppy-0.029
 opener-0.029
taker-0.028
Token touch
Token ID3638
Feature activation+4.45e-03

Pos logit contributions
izzy+0.030
enny+0.026
ppy+0.026
 opener+0.026
taker+0.025
Neg logit contributions
ement-0.027
 mouths-0.026
 wrists-0.026
irling-0.026
irl-0.026
Token"
Token ID1
Feature activation+7.06e-02

Pos logit contributions
izzy+0.009
enny+0.008
ppy+0.007
 opener+0.007
taker+0.007
Neg logit contributions
ement-0.007
 mouths-0.007
 wrists-0.007
irling-0.007
irl-0.007
Token or
Token ID393
Feature activation+1.19e-02

Pos logit contributions
izzy+0.127
enny+0.111
ppy+0.108
taker+0.108
 opener+0.102
Neg logit contributions
ement-0.119
mm-0.113
 mouths-0.111
 wrists-0.111
 conversations-0.110
Token "
Token ID366
Feature activation+5.50e-02

Pos logit contributions
izzy+0.023
enny+0.020
ppy+0.019
 opener+0.019
taker+0.019
Neg logit contributions
ement-0.019
 wrists-0.019
 mouths-0.019
 soaring-0.018
irl-0.018
TokenKeep
Token ID15597
Feature activation-1.52e-03

Pos logit contributions
izzy+0.101
enny+0.089
taker+0.088
ppy+0.085
 opener+0.083
Neg logit contributions
ement-0.090
mm-0.087
 wrists-0.086
irl-0.085
 soaring-0.083
Token out
Token ID503
Feature activation+8.09e-03

Pos logit contributions
ement+0.002
 wrists+0.002
 mouths+0.002
irling+0.002
 soaring+0.002
Neg logit contributions
izzy-0.003
enny-0.003
ppy-0.003
 opener-0.003
taker-0.003
Token".
Token ID1911
Feature activation+7.44e-03

Pos logit contributions
izzy+0.014
enny+0.012
 opener+0.012
ro+0.011
ppy+0.011
Neg logit contributions
ement-0.015
 mouths-0.015
 soaring-0.014
irling-0.014
 wrists-0.014
Token And
Token ID843
Feature activation-2.94e-03

Pos logit contributions
ement+0.017
 wrists+0.016
 mouths+0.016
irling+0.016
irl+0.016
Neg logit contributions
izzy-0.020
enny-0.018
ppy-0.017
 opener-0.017
taker-0.017
Token they
Token ID484
Feature activation-6.05e-03

Pos logit contributions
ement+0.005
 wrists+0.005
irling+0.005
 mouths+0.005
irl+0.005
Neg logit contributions
izzy-0.005
enny-0.005
 opener-0.004
ppy-0.004
taker-0.004
Token all
Token ID477
Feature activation+1.54e-02

Pos logit contributions
ement+0.007
 wrists+0.007
 mouths+0.007
irling+0.007
irl+0.007
Neg logit contributions
izzy-0.014
enny-0.013
ppy-0.012
 opener-0.012
taker-0.012
Token lived
Token ID5615
Feature activation-6.30e-03

Pos logit contributions
izzy+0.040
enny+0.037
 opener+0.036
ro+0.036
ppy+0.035
Neg logit contributions
ement-0.013
 mouths-0.013
 wrists-0.012
irl-0.012
 soaring-0.012
Token happily
Token ID18177
Feature activation+4.49e-02

Pos logit contributions
ement+0.008
irl+0.008
 mouths+0.008
 wrists+0.008
irling+0.008
Neg logit contributions
izzy-0.014
enny-0.012
ppy-0.012
 opener-0.012
taker-0.012
Token ever
Token ID1683
Feature activation+7.05e-02

Pos logit contributions
izzy+0.065
enny+0.054
 opener+0.052
ppy+0.052
taker+0.051
Neg logit contributions
ement-0.094
 mouths-0.092
 wrists-0.091
 soaring-0.090
mm-0.090
Token after
Token ID706
Feature activation+1.39e-02

Pos logit contributions
izzy+0.115
taker+0.094
 opener+0.092
enny+0.091
guard+0.088
Neg logit contributions
 mouths-0.137
 conversations-0.136
 disagreement-0.130
 tails-0.129
 soaring-0.129
Token.
Token ID13
Feature activation-1.90e-02

Pos logit contributions
izzy+0.021
enny+0.017
 opener+0.017
taker+0.017
ppy+0.017
Neg logit contributions
ement-0.028
 wrists-0.028
 mouths-0.027
mm-0.026
 soaring-0.026
Token<|endoftext|>
Token ID50256
Feature activation+1.55e-02

Pos logit contributions
ement+0.031
 mouths+0.030
 wrists+0.030
irling+0.029
irl+0.029
Neg logit contributions
izzy-0.036
enny-0.031
ppy-0.031
 opener-0.030
taker-0.030
TokenOnce
Token ID7454
Feature activation-9.93e-03

Pos logit contributions
izzy+0.030
enny+0.026
ppy+0.026
taker+0.026
 opener+0.026
Neg logit contributions
ement-0.024
 mouths-0.023
 wrists-0.023
irl-0.023
irling-0.023
Token upon
Token ID2402
Feature activation+1.03e-02

Pos logit contributions
ement+0.019
 mouths+0.018
irl+0.018
 soaring+0.017
irling+0.017
Neg logit contributions
izzy-0.016
ppy-0.014
 opener-0.014
enny-0.014
ro-0.014
Token.
Token ID13
Feature activation-9.37e-03

Pos logit contributions
izzy+0.006
enny+0.005
ppy+0.005
taker+0.005
 opener+0.005
Neg logit contributions
ement-0.007
 mouths-0.006
 wrists-0.006
 soaring-0.006
irl-0.006
Token And
Token ID843
Feature activation-3.66e-03

Pos logit contributions
ement+0.014
 mouths+0.014
mm+0.014
 wrists+0.014
irl+0.013
Neg logit contributions
izzy-0.018
ppy-0.016
enny-0.016
 opener-0.016
taker-0.016
Token they
Token ID484
Feature activation-7.88e-03

Pos logit contributions
ement+0.007
 wrists+0.006
irling+0.006
 mouths+0.006
irl+0.006
Neg logit contributions
izzy-0.007
enny-0.006
 opener-0.006
ppy-0.005
taker-0.005
Token lived
Token ID5615
Feature activation-7.72e-03

Pos logit contributions
ement+0.010
 mouths+0.010
 wrists+0.010
irling+0.009
mm+0.009
Neg logit contributions
izzy-0.018
enny-0.016
ppy-0.016
 opener-0.015
taker-0.015
Token happily
Token ID18177
Feature activation+4.36e-02

Pos logit contributions
ement+0.010
irl+0.010
 wrists+0.010
 mouths+0.010
irling+0.010
Neg logit contributions
izzy-0.017
enny-0.015
ppy-0.015
 opener-0.015
taker-0.015
Token ever
Token ID1683
Feature activation+7.03e-02

Pos logit contributions
izzy+0.060
enny+0.049
ppy+0.048
 opener+0.048
taker+0.047
Neg logit contributions
ement-0.095
 mouths-0.092
 wrists-0.092
irling-0.090
 soaring-0.090
Token after
Token ID706
Feature activation+1.32e-02

Pos logit contributions
izzy+0.108
taker+0.087
 opener+0.086
enny+0.085
guard+0.080
Neg logit contributions
 mouths-0.143
 conversations-0.141
ement-0.137
 wrists-0.137
 soaring-0.136
Token.
Token ID13
Feature activation-1.55e-02

Pos logit contributions
izzy+0.019
enny+0.016
 opener+0.015
taker+0.015
ppy+0.015
Neg logit contributions
ement-0.027
 wrists-0.027
 mouths-0.027
mm-0.026
 soaring-0.026
Token<|endoftext|>
Token ID50256
Feature activation+1.76e-02

Pos logit contributions
ement+0.023
 mouths+0.022
mm+0.022
 wrists+0.022
 soaring+0.022
Neg logit contributions
izzy-0.031
ppy-0.027
enny-0.027
 opener-0.026
taker-0.026
TokenOnce
Token ID7454
Feature activation-1.12e-02

Pos logit contributions
izzy+0.034
enny+0.030
ppy+0.029
taker+0.029
 opener+0.029
Neg logit contributions
ement-0.028
 mouths-0.026
 wrists-0.026
irl-0.026
 soaring-0.026
Token upon
Token ID2402
Feature activation+1.19e-02

Pos logit contributions
ement+0.021
 mouths+0.020
irl+0.020
 soaring+0.019
irling+0.019
Neg logit contributions
izzy-0.018
ppy-0.016
 opener-0.016
ro-0.016
enny-0.016
Token And
Token ID843
Feature activation-9.36e-03

Pos logit contributions
ement+0.022
irling+0.021
 wrists+0.021
irl+0.021
 soaring+0.021
Neg logit contributions
izzy-0.025
enny-0.022
 opener-0.021
ppy-0.020
taker-0.020
Token they
Token ID484
Feature activation-1.23e-02

Pos logit contributions
ement+0.016
irling+0.015
 wrists+0.015
 mouths+0.015
irl+0.015
Neg logit contributions
izzy-0.018
enny-0.015
 opener-0.015
ppy-0.015
taker-0.015
Token all
Token ID477
Feature activation+9.88e-03

Pos logit contributions
ement+0.014
 wrists+0.013
irl+0.013
 mouths+0.013
 soaring+0.013
Neg logit contributions
izzy-0.029
enny-0.026
 opener-0.026
ro-0.026
head-0.026
Token lived
Token ID5615
Feature activation-6.72e-03

Pos logit contributions
izzy+0.026
enny+0.024
 opener+0.024
head+0.023
ro+0.023
Neg logit contributions
 mouths-0.008
ement-0.008
 wrists-0.008
irl-0.008
 soaring-0.008
Token happily
Token ID18177
Feature activation+4.40e-02

Pos logit contributions
ement+0.009
irl+0.008
 wrists+0.008
 soaring+0.008
 mouths+0.008
Neg logit contributions
izzy-0.015
enny-0.014
ppy-0.013
 opener-0.013
taker-0.013
Token ever
Token ID1683
Feature activation+7.03e-02

Pos logit contributions
izzy+0.067
enny+0.055
 opener+0.054
taker+0.053
ppy+0.053
Neg logit contributions
ement-0.089
 mouths-0.087
 soaring-0.086
 wrists-0.086
mm-0.085
Token after
Token ID706
Feature activation+1.19e-02

Pos logit contributions
izzy+0.120
taker+0.099
 opener+0.096
enny+0.095
washer+0.090
Neg logit contributions
 mouths-0.132
 conversations-0.131
 disagreement-0.125
 tails-0.124
 hearts-0.124
Token.
Token ID13
Feature activation-1.86e-02

Pos logit contributions
izzy+0.018
enny+0.015
 opener+0.015
ppy+0.015
taker+0.015
Neg logit contributions
ement-0.024
 wrists-0.024
 mouths-0.023
mm-0.023
 soaring-0.022
Token<|endoftext|>
Token ID50256
Feature activation+1.79e-02

Pos logit contributions
ement+0.031
 mouths+0.029
 wrists+0.029
irling+0.029
irl+0.029
Neg logit contributions
izzy-0.035
enny-0.031
ppy-0.030
 opener-0.030
taker-0.030
TokenOnce
Token ID7454
Feature activation-1.41e-02

Pos logit contributions
izzy+0.034
enny+0.030
ppy+0.029
 opener+0.029
taker+0.029
Neg logit contributions
ement-0.029
 mouths-0.028
 wrists-0.028
irling-0.027
irl-0.027
Token upon
Token ID2402
Feature activation+1.09e-02

Pos logit contributions
ement+0.027
 mouths+0.026
irl+0.025
irling+0.025
 soaring+0.025
Neg logit contributions
izzy-0.023
enny-0.019
ppy-0.019
 opener-0.019
taker-0.019
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
izzy+0.018
enny+0.015
 opener+0.015
ppy+0.015
ro+0.015
Neg logit contributions
ement-0.023
 mouths-0.022
 wrists-0.022
mm-0.021
irling-0.021
Token And
Token ID843
Feature activation-7.54e-03

Pos logit contributions
ement+0.025
 wrists+0.024
irling+0.024
 mouths+0.024
irl+0.023
Neg logit contributions
izzy-0.026
enny-0.023
 opener-0.022
ppy-0.022
taker-0.022
Token they
Token ID484
Feature activation-8.93e-03

Pos logit contributions
ement+0.013
 wrists+0.013
irling+0.013
 mouths+0.012
irl+0.012
Neg logit contributions
izzy-0.014
enny-0.012
 opener-0.012
taker-0.011
ppy-0.011
Token lived
Token ID5615
Feature activation-6.08e-03

Pos logit contributions
ement+0.011
 wrists+0.010
irl+0.010
 mouths+0.010
 soaring+0.010
Neg logit contributions
izzy-0.020
enny-0.019
 opener-0.018
head-0.018
ro-0.018
Token happily
Token ID18177
Feature activation+4.38e-02

Pos logit contributions
ement+0.008
irl+0.008
 mouths+0.007
 wrists+0.007
 soaring+0.007
Neg logit contributions
izzy-0.014
enny-0.012
ppy-0.012
 opener-0.012
taker-0.012
Token ever
Token ID1683
Feature activation+7.01e-02

Pos logit contributions
izzy+0.071
enny+0.060
 opener+0.058
taker+0.057
ppy+0.056
Neg logit contributions
ement-0.084
 soaring-0.083
 mouths-0.083
 wrists-0.082
irling-0.081
Token after
Token ID706
Feature activation+1.29e-02

Pos logit contributions
izzy+0.121
taker+0.100
enny+0.097
 opener+0.094
uster+0.090
Neg logit contributions
 mouths-0.132
 conversations-0.131
 tails-0.125
 disagreement-0.124
 soaring-0.124
Token.
Token ID13
Feature activation-1.85e-02

Pos logit contributions
izzy+0.020
enny+0.017
 opener+0.017
ppy+0.016
taker+0.016
Neg logit contributions
ement-0.026
 wrists-0.025
 mouths-0.025
mm-0.024
 soaring-0.024
Token<|endoftext|>
Token ID50256
Feature activation+2.65e-02

Pos logit contributions
ement+0.031
 wrists+0.030
 mouths+0.030
irling+0.029
irl+0.029
Neg logit contributions
izzy-0.035
enny-0.030
ppy-0.029
 opener-0.029
taker-0.029
TokenOne
Token ID3198
Feature activation+2.68e-03

Pos logit contributions
izzy+0.053
enny+0.047
ppy+0.046
taker+0.046
 opener+0.045
Neg logit contributions
ement-0.040
 mouths-0.037
irl-0.037
 soaring-0.037
 wrists-0.037
Token day
Token ID1110
Feature activation-7.61e-03

Pos logit contributions
izzy+0.006
enny+0.005
ppy+0.005
 opener+0.005
taker+0.005
Neg logit contributions
ement-0.004
 wrists-0.004
 mouths-0.003
irling-0.003
mm-0.003
Token.
Token ID13
Feature activation-1.07e-02

Pos logit contributions
izzy+0.049
ppy+0.043
enny+0.043
taker+0.041
eware+0.041
Neg logit contributions
ement-0.037
 best-0.034
 pic-0.034
 course-0.034
 mouths-0.033
Token And
Token ID843
Feature activation-8.55e-03

Pos logit contributions
ement+0.018
 wrists+0.017
 mouths+0.017
irling+0.017
irl+0.016
Neg logit contributions
izzy-0.021
enny-0.018
 opener-0.018
ppy-0.017
taker-0.017
Token he
Token ID339
Feature activation-9.86e-03

Pos logit contributions
ement+0.018
 wrists+0.018
irling+0.018
irl+0.018
 mouths+0.017
Neg logit contributions
izzy-0.012
enny-0.010
taker-0.010
 opener-0.009
ppy-0.009
Token lived
Token ID5615
Feature activation-3.58e-03

Pos logit contributions
ement+0.015
 mouths+0.014
 wrists+0.014
irl+0.014
irling+0.014
Neg logit contributions
izzy-0.020
enny-0.018
 opener-0.018
ppy-0.017
taker-0.017
Token happily
Token ID18177
Feature activation+3.87e-02

Pos logit contributions
irl+0.004
ement+0.004
 soaring+0.004
irling+0.004
 wrists+0.004
Neg logit contributions
izzy-0.008
enny-0.008
ppy-0.007
 opener-0.007
taker-0.007
Token ever
Token ID1683
Feature activation+6.98e-02

Pos logit contributions
izzy+0.056
enny+0.047
 opener+0.045
ppy+0.045
taker+0.044
Neg logit contributions
ement-0.081
 mouths-0.078
 wrists-0.078
 soaring-0.077
irling-0.077
Token after
Token ID706
Feature activation+1.89e-02

Pos logit contributions
izzy+0.126
 opener+0.102
taker+0.101
enny+0.098
washer+0.096
Neg logit contributions
 soaring-0.123
 conversations-0.121
 staring-0.119
 mouths-0.117
 doing-0.115
Token!
Token ID0
Feature activation-1.53e-02

Pos logit contributions
izzy+0.035
enny+0.030
ppy+0.029
 opener+0.029
taker+0.029
Neg logit contributions
ement-0.033
irling-0.031
irl-0.031
 soaring-0.031
 mouths-0.031
Token<|endoftext|>
Token ID50256
Feature activation+1.05e-02

Pos logit contributions
ement+0.023
mm+0.022
 mouths+0.021
 soaring+0.021
 pic+0.021
Neg logit contributions
izzy-0.031
ppy-0.027
enny-0.027
 opener-0.027
taker-0.026
TokenOnce
Token ID7454
Feature activation-1.64e-02

Pos logit contributions
izzy+0.020
enny+0.018
ppy+0.017
 opener+0.017
taker+0.017
Neg logit contributions
ement-0.017
 mouths-0.016
 wrists-0.016
irl-0.016
irling-0.016
Token upon
Token ID2402
Feature activation+9.04e-03

Pos logit contributions
ement+0.033
 mouths+0.031
 wrists+0.031
irl+0.031
irling+0.031
Neg logit contributions
izzy-0.025
enny-0.021
ppy-0.021
 opener-0.021
taker-0.020
Token got
Token ID1392
Feature activation-1.75e-03

Pos logit contributions
ement+0.004
 mouths+0.003
 wrists+0.003
irling+0.003
mm+0.003
Neg logit contributions
izzy-0.005
enny-0.004
ppy-0.004
taker-0.004
 opener-0.004
Token married
Token ID6405
Feature activation+2.18e-03

Pos logit contributions
 mouths+0.003
ement+0.003
 wrists+0.003
 soaring+0.003
 conversations+0.003
Neg logit contributions
izzy-0.003
enny-0.003
ppy-0.003
 opener-0.003
ro-0.003
Token and
Token ID290
Feature activation-9.03e-03

Pos logit contributions
izzy+0.004
enny+0.004
ppy+0.003
 opener+0.003
taker+0.003
Neg logit contributions
ement-0.004
 wrists-0.004
 mouths-0.004
 soaring-0.003
irling-0.003
Token lived
Token ID5615
Feature activation-2.35e-03

Pos logit contributions
ement+0.015
irling+0.014
 wrists+0.014
 mouths+0.013
irl+0.013
Neg logit contributions
izzy-0.018
enny-0.015
ppy-0.015
taker-0.015
 opener-0.015
Token happily
Token ID18177
Feature activation+4.16e-02

Pos logit contributions
ement+0.004
 mouths+0.003
 wrists+0.003
mm+0.003
irling+0.003
Neg logit contributions
izzy-0.005
enny-0.004
ppy-0.004
 opener-0.004
taker-0.004
Token ever
Token ID1683
Feature activation+6.98e-02

Pos logit contributions
izzy+0.059
enny+0.049
 opener+0.047
ppy+0.047
taker+0.046
Neg logit contributions
ement-0.089
 mouths-0.086
 wrists-0.086
 soaring-0.085
irling-0.084
Token after
Token ID706
Feature activation+1.58e-02

Pos logit contributions
izzy+0.117
taker+0.095
 opener+0.094
enny+0.092
washer+0.088
Neg logit contributions
 conversations-0.129
 mouths-0.128
 soaring-0.124
 disagreement-0.122
 tails-0.122
Token.
Token ID13
Feature activation-1.37e-02

Pos logit contributions
izzy+0.023
enny+0.019
 opener+0.019
taker+0.018
ppy+0.018
Neg logit contributions
ement-0.032
 wrists-0.032
 mouths-0.032
mm-0.031
irling-0.031
Token<|endoftext|>
Token ID50256
Feature activation+2.29e-02

Pos logit contributions
ement+0.021
 mouths+0.020
 wrists+0.020
mm+0.019
irl+0.019
Neg logit contributions
izzy-0.027
enny-0.024
ppy-0.024
 opener-0.023
taker-0.023
TokenOnce
Token ID7454
Feature activation-4.63e-03

Pos logit contributions
izzy+0.045
enny+0.040
ppy+0.040
taker+0.039
 opener+0.039
Neg logit contributions
ement-0.035
 mouths-0.033
irl-0.033
 wrists-0.033
 soaring-0.032
Token upon
Token ID2402
Feature activation+1.42e-02

Pos logit contributions
ement+0.009
 mouths+0.008
irl+0.008
 soaring+0.008
irling+0.008
Neg logit contributions
izzy-0.008
 opener-0.007
ppy-0.007
ro-0.007
enny-0.006
Token And
Token ID843
Feature activation-1.08e-02

Pos logit contributions
irling+0.045
ement+0.045
 wrists+0.044
irl+0.044
 soaring+0.043
Neg logit contributions
izzy-0.040
enny-0.036
 opener-0.034
ro-0.033
ily-0.033
Token they
Token ID484
Feature activation-1.33e-02

Pos logit contributions
ement+0.021
irling+0.020
 wrists+0.020
irl+0.020
 mouths+0.019
Neg logit contributions
izzy-0.017
enny-0.015
 opener-0.015
taker-0.014
guard-0.014
Token all
Token ID477
Feature activation+7.32e-03

Pos logit contributions
ement+0.017
 mouths+0.016
 wrists+0.016
irl+0.016
 soaring+0.016
Neg logit contributions
izzy-0.030
enny-0.027
 opener-0.026
ppy-0.026
taker-0.025
Token lived
Token ID5615
Feature activation-7.83e-03

Pos logit contributions
izzy+0.020
enny+0.018
 opener+0.018
ppy+0.017
head+0.017
Neg logit contributions
ement-0.006
 mouths-0.006
 wrists-0.005
irl-0.005
 soaring-0.005
Token happily
Token ID18177
Feature activation+4.06e-02

Pos logit contributions
ement+0.011
 mouths+0.011
 wrists+0.011
irling+0.011
irl+0.010
Neg logit contributions
izzy-0.016
enny-0.015
ppy-0.014
 opener-0.014
taker-0.014
Token ever
Token ID1683
Feature activation+6.98e-02

Pos logit contributions
izzy+0.058
enny+0.048
 opener+0.046
ppy+0.046
taker+0.046
Neg logit contributions
ement-0.086
 mouths-0.083
 wrists-0.083
irling-0.082
 soaring-0.082
Token after
Token ID706
Feature activation+1.21e-02

Pos logit contributions
izzy+0.117
taker+0.092
enny+0.092
 opener+0.090
washer+0.084
Neg logit contributions
 mouths-0.138
 conversations-0.135
 disagreement-0.130
 soaring-0.130
 wrists-0.129
Token.
Token ID13
Feature activation-2.78e-02

Pos logit contributions
izzy+0.016
enny+0.014
 opener+0.013
taker+0.013
ppy+0.013
Neg logit contributions
ement-0.026
 wrists-0.026
 mouths-0.025
irl-0.024
 soaring-0.024
Token<|endoftext|>
Token ID50256
Feature activation+1.79e-02

Pos logit contributions
ement+0.056
 wrists+0.056
irling+0.055
irl+0.054
 mouths+0.053
Neg logit contributions
izzy-0.044
enny-0.038
 opener-0.035
ily-0.034
taker-0.034
TokenS
Token ID50
Feature activation-1.11e-02

Pos logit contributions
izzy+0.034
enny+0.030
ppy+0.029
 opener+0.029
taker+0.029
Neg logit contributions
ement-0.029
 mouths-0.028
 wrists-0.028
irling-0.027
irl-0.027
Tokenara
Token ID3301
Feature activation+2.45e-03

Pos logit contributions
 wrists+0.016
irling+0.016
 soaring+0.016
ement+0.016
 mouths+0.015
Neg logit contributions
izzy-0.023
enny-0.021
ppy-0.020
 opener-0.019
t-0.019
Token,
Token ID11
Feature activation+6.70e-03

Pos logit contributions
izzy+0.046
enny+0.039
ppy+0.038
 opener+0.038
taker+0.038
Neg logit contributions
ement-0.048
 mouths-0.046
 wrists-0.046
irling-0.045
mm-0.045
Token and
Token ID290
Feature activation+7.91e-03

Pos logit contributions
izzy+0.011
 opener+0.010
enny+0.009
ro+0.009
ppy+0.009
Neg logit contributions
ement-0.013
irling-0.012
 wrists-0.012
irl-0.012
heit-0.012
Token they
Token ID484
Feature activation-1.45e-02

Pos logit contributions
izzy+0.011
 opener+0.010
enny+0.009
taker+0.009
ppy+0.009
Neg logit contributions
ement-0.017
irling-0.016
 wrists-0.016
irl-0.016
mm-0.016
Token lived
Token ID5615
Feature activation-5.17e-03

Pos logit contributions
ement+0.023
 mouths+0.023
 soaring+0.022
 wrists+0.022
irl+0.022
Neg logit contributions
izzy-0.027
enny-0.024
ro-0.023
ppy-0.023
head-0.023
Token happily
Token ID18177
Feature activation+4.29e-02

Pos logit contributions
irl+0.007
 soaring+0.006
irling+0.006
 best+0.006
 wrists+0.006
Neg logit contributions
izzy-0.012
enny-0.010
taker-0.010
head-0.010
ppy-0.010
Token ever
Token ID1683
Feature activation+6.97e-02

Pos logit contributions
izzy+0.068
enny+0.057
 opener+0.054
taker+0.054
ppy+0.054
Neg logit contributions
ement-0.083
 mouths-0.083
 soaring-0.082
 wrists-0.082
irling-0.081
Token after
Token ID706
Feature activation+1.62e-02

Pos logit contributions
izzy+0.115
taker+0.093
enny+0.092
 opener+0.087
uster+0.081
Neg logit contributions
 mouths-0.140
 conversations-0.135
 wrists-0.132
 disagreement-0.131
 soaring-0.129
Token.
Token ID13
Feature activation-2.35e-02

Pos logit contributions
izzy+0.025
enny+0.021
 opener+0.021
ppy+0.021
taker+0.021
Neg logit contributions
ement-0.032
 wrists-0.031
 mouths-0.031
 soaring-0.030
irling-0.030
Token<|endoftext|>
Token ID50256
Feature activation+1.92e-02

Pos logit contributions
ement+0.040
 wrists+0.038
 mouths+0.038
irling+0.037
irl+0.037
Neg logit contributions
izzy-0.044
enny-0.038
ppy-0.037
 opener-0.037
taker-0.037
TokenOne
Token ID3198
Feature activation+1.82e-03

Pos logit contributions
izzy+0.037
enny+0.032
ppy+0.032
 opener+0.031
taker+0.031
Neg logit contributions
ement-0.031
 mouths-0.029
 wrists-0.029
irl-0.029
irling-0.029
Token day
Token ID1110
Feature activation-1.01e-02

Pos logit contributions
izzy+0.004
enny+0.003
 opener+0.003
ppy+0.003
taker+0.003
Neg logit contributions
ement-0.003
 wrists-0.003
 mouths-0.003
irling-0.003
mm-0.003
Token.
Token ID13
Feature activation-1.90e-02

Pos logit contributions
ement+0.018
 wrists+0.018
 mouths+0.018
irling+0.018
irl+0.017
Neg logit contributions
izzy-0.016
enny-0.014
ppy-0.013
 opener-0.013
taker-0.013
Token And
Token ID843
Feature activation-8.17e-03

Pos logit contributions
ement+0.037
irling+0.036
 wrists+0.035
irl+0.035
 soaring+0.035
Neg logit contributions
izzy-0.031
enny-0.027
taker-0.025
 opener-0.025
ro-0.025
Token they
Token ID484
Feature activation-1.19e-02

Pos logit contributions
ement+0.015
irling+0.015
 wrists+0.015
 mouths+0.014
irl+0.014
Neg logit contributions
izzy-0.014
enny-0.012
taker-0.011
 opener-0.011
ppy-0.011
Token lived
Token ID5615
Feature activation-5.61e-03

Pos logit contributions
ement+0.016
 wrists+0.015
 mouths+0.015
irl+0.015
irling+0.015
Neg logit contributions
izzy-0.026
enny-0.023
 opener-0.023
ppy-0.023
taker-0.022
Token happily
Token ID18177
Feature activation+4.05e-02

Pos logit contributions
ement+0.008
 wrists+0.008
 mouths+0.008
irling+0.008
irl+0.008
Neg logit contributions
izzy-0.012
enny-0.010
ppy-0.010
 opener-0.010
taker-0.010
Token ever
Token ID1683
Feature activation+6.96e-02

Pos logit contributions
izzy+0.062
enny+0.051
 opener+0.051
taker+0.049
ppy+0.049
Neg logit contributions
ement-0.081
 soaring-0.080
 wrists-0.079
 mouths-0.079
irling-0.078
Token after
Token ID706
Feature activation+1.43e-02

Pos logit contributions
izzy+0.117
taker+0.097
 opener+0.095
enny+0.094
washer+0.090
Neg logit contributions
 conversations-0.130
 mouths-0.128
 soaring-0.126
 disagreement-0.123
 wrists-0.122
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
izzy+0.021
enny+0.017
 opener+0.017
ppy+0.017
taker+0.017
Neg logit contributions
ement-0.029
 wrists-0.029
 mouths-0.029
mm-0.028
irling-0.027
Token<|endoftext|>
Token ID50256
Feature activation+2.00e-02

Pos logit contributions
ement+0.038
 wrists+0.037
irling+0.036
 mouths+0.036
irl+0.036
Neg logit contributions
izzy-0.038
enny-0.033
 opener-0.031
ppy-0.031
taker-0.031
TokenOnce
Token ID7454
Feature activation-1.47e-02

Pos logit contributions
izzy+0.039
enny+0.034
ppy+0.034
taker+0.033
 opener+0.033
Neg logit contributions
ement-0.031
 mouths-0.030
 wrists-0.030
irl-0.029
 soaring-0.029
Token upon
Token ID2402
Feature activation+1.07e-02

Pos logit contributions
ement+0.029
 wrists+0.028
 mouths+0.028
irling+0.027
irl+0.027
Neg logit contributions
izzy-0.023
enny-0.019
ppy-0.019
 opener-0.019
taker-0.018
Token.
Token ID13
Feature activation-9.08e-03

Pos logit contributions
izzy+0.021
enny+0.018
ppy+0.017
 opener+0.017
taker+0.017
Neg logit contributions
ement-0.027
 wrists-0.026
irl-0.026
 mouths-0.026
irling-0.026
Token And
Token ID843
Feature activation-7.20e-03

Pos logit contributions
ement+0.014
 mouths+0.013
 wrists+0.013
mm+0.013
irl+0.013
Neg logit contributions
izzy-0.018
enny-0.016
ppy-0.016
 opener-0.016
taker-0.016
Token they
Token ID484
Feature activation-3.09e-03

Pos logit contributions
ement+0.013
irling+0.012
 wrists+0.012
 mouths+0.012
irl+0.012
Neg logit contributions
izzy-0.013
enny-0.011
 opener-0.011
ppy-0.011
taker-0.010
Token lived
Token ID5615
Feature activation-5.81e-03

Pos logit contributions
ement+0.004
 wrists+0.004
 mouths+0.004
irl+0.003
irling+0.003
Neg logit contributions
izzy-0.007
enny-0.006
 opener-0.006
ppy-0.006
taker-0.006
Token happily
Token ID18177
Feature activation+4.36e-02

Pos logit contributions
ement+0.009
 mouths+0.008
 wrists+0.008
mm+0.008
irling+0.008
Neg logit contributions
izzy-0.012
enny-0.010
ppy-0.010
 opener-0.010
taker-0.010
Token ever
Token ID1683
Feature activation+6.96e-02

Pos logit contributions
izzy+0.064
enny+0.053
 opener+0.051
ppy+0.050
taker+0.050
Neg logit contributions
ement-0.090
 mouths-0.088
 wrists-0.088
 soaring-0.087
irling-0.086
Token after
Token ID706
Feature activation+1.07e-02

Pos logit contributions
izzy+0.110
enny+0.089
taker+0.088
 opener+0.088
guard+0.081
Neg logit contributions
 mouths-0.137
 conversations-0.135
 soaring-0.132
 disagreement-0.130
ement-0.130
Token.
Token ID13
Feature activation-1.89e-02

Pos logit contributions
izzy+0.015
enny+0.012
 opener+0.012
ppy+0.012
taker+0.012
Neg logit contributions
ement-0.022
 wrists-0.022
 mouths-0.022
mm-0.021
aman-0.021
Token<|endoftext|>
Token ID50256
Feature activation+1.86e-02

Pos logit contributions
ement+0.031
 mouths+0.029
 wrists+0.029
mm+0.029
 soaring+0.028
Neg logit contributions
izzy-0.036
enny-0.032
ppy-0.031
 opener-0.031
taker-0.031
TokenOnce
Token ID7454
Feature activation-1.59e-02

Pos logit contributions
izzy+0.037
enny+0.033
ppy+0.032
taker+0.032
 opener+0.031
Neg logit contributions
ement-0.028
 mouths-0.026
irl-0.026
 wrists-0.026
 soaring-0.026
Token upon
Token ID2402
Feature activation+9.25e-03

Pos logit contributions
ement+0.031
 wrists+0.030
 mouths+0.030
irling+0.029
mm+0.029
Neg logit contributions
izzy-0.026
enny-0.022
ppy-0.021
 opener-0.021
taker-0.021
Token.
Token ID13
Feature activation-7.33e-03

Pos logit contributions
izzy+0.053
enny+0.046
ppy+0.045
 opener+0.044
taker+0.044
Neg logit contributions
ement-0.048
mm-0.045
 mouths-0.044
 wrists-0.044
 pic-0.043
Token And
Token ID843
Feature activation-3.02e-03

Pos logit contributions
ement+0.011
 mouths+0.010
mm+0.010
 wrists+0.010
 pic+0.010
Neg logit contributions
izzy-0.015
ppy-0.013
enny-0.013
taker-0.013
 opener-0.013
Token they
Token ID484
Feature activation-1.34e-02

Pos logit contributions
ement+0.006
irling+0.006
 wrists+0.006
 mouths+0.006
irl+0.005
Neg logit contributions
izzy-0.005
enny-0.004
 opener-0.004
ppy-0.004
taker-0.004
Token lived
Token ID5615
Feature activation-6.31e-03

Pos logit contributions
ement+0.017
 mouths+0.016
 wrists+0.016
irl+0.016
irling+0.016
Neg logit contributions
izzy-0.030
enny-0.027
 opener-0.026
ppy-0.026
taker-0.026
Token happily
Token ID18177
Feature activation+4.06e-02

Pos logit contributions
ement+0.009
 wrists+0.008
irl+0.008
 mouths+0.008
irling+0.008
Neg logit contributions
izzy-0.014
enny-0.012
ppy-0.012
 opener-0.012
taker-0.012
Token ever
Token ID1683
Feature activation+6.96e-02

Pos logit contributions
izzy+0.055
enny+0.045
ppy+0.044
 opener+0.043
taker+0.043
Neg logit contributions
ement-0.089
 wrists-0.086
 mouths-0.086
irling-0.085
irl-0.084
Token after
Token ID706
Feature activation+1.46e-02

Pos logit contributions
izzy+0.107
taker+0.086
enny+0.086
 opener+0.084
washer+0.078
Neg logit contributions
 mouths-0.141
 conversations-0.137
 wrists-0.137
ement-0.136
 soaring-0.135
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
izzy+0.021
enny+0.018
 opener+0.017
taker+0.017
ppy+0.017
Neg logit contributions
ement-0.030
 wrists-0.030
 mouths-0.030
 soaring-0.028
mm-0.028
Token<|endoftext|>
Token ID50256
Feature activation+2.07e-02

Pos logit contributions
ement+0.016
 mouths+0.015
mm+0.015
 wrists+0.015
 pic+0.015
Neg logit contributions
izzy-0.022
ppy-0.019
enny-0.019
 opener-0.019
taker-0.019
TokenOne
Token ID3198
Feature activation+4.83e-03

Pos logit contributions
izzy+0.040
enny+0.035
ppy+0.034
 opener+0.034
taker+0.034
Neg logit contributions
ement-0.033
 mouths-0.032
 wrists-0.032
irl-0.031
irling-0.031
Token day
Token ID1110
Feature activation-5.85e-03

Pos logit contributions
izzy+0.010
enny+0.009
ppy+0.008
 opener+0.008
taker+0.008
Neg logit contributions
ement-0.007
 wrists-0.007
 mouths-0.007
irling-0.007
mm-0.007
Token.
Token ID13
Feature activation-5.82e-03

Pos logit contributions
izzy+0.008
enny+0.007
 opener+0.007
ppy+0.006
taker+0.006
Neg logit contributions
ement-0.011
mm-0.011
irl-0.011
 wrists-0.011
irling-0.011
Token And
Token ID843
Feature activation-5.56e-03

Pos logit contributions
ement+0.010
irling+0.010
 wrists+0.010
irl+0.009
 soaring+0.009
Neg logit contributions
izzy-0.011
 opener-0.010
enny-0.010
taker-0.009
ro-0.009
Token they
Token ID484
Feature activation-9.85e-03

Pos logit contributions
ement+0.010
 wrists+0.010
irling+0.010
 mouths+0.009
irl+0.009
Neg logit contributions
izzy-0.010
enny-0.009
 opener-0.008
ppy-0.008
taker-0.008
Token lived
Token ID5615
Feature activation-4.93e-03

Pos logit contributions
ement+0.013
 mouths+0.012
 wrists+0.012
irling+0.012
mm+0.012
Neg logit contributions
izzy-0.022
enny-0.020
ppy-0.019
 opener-0.019
taker-0.019
Token happily
Token ID18177
Feature activation+4.42e-02

Pos logit contributions
ement+0.006
irl+0.006
irling+0.006
 mouths+0.006
 wrists+0.006
Neg logit contributions
izzy-0.011
enny-0.010
ppy-0.010
taker-0.010
 opener-0.010
Token ever
Token ID1683
Feature activation+6.96e-02

Pos logit contributions
izzy+0.067
enny+0.056
 opener+0.054
taker+0.054
ppy+0.053
Neg logit contributions
ement-0.089
 mouths-0.088
 soaring-0.087
 wrists-0.086
mm-0.085
Token after
Token ID706
Feature activation+9.98e-03

Pos logit contributions
izzy+0.112
taker+0.093
enny+0.090
 opener+0.089
guard+0.085
Neg logit contributions
 mouths-0.134
 conversations-0.133
 disagreement-0.127
 soaring-0.127
 tails-0.126
Token.
Token ID13
Feature activation-2.04e-02

Pos logit contributions
izzy+0.015
enny+0.012
 opener+0.012
ppy+0.012
taker+0.011
Neg logit contributions
ement-0.021
 wrists-0.020
 mouths-0.020
mm-0.019
 soaring-0.019
Token<|endoftext|>
Token ID50256
Feature activation+1.55e-02

Pos logit contributions
ement+0.038
 wrists+0.037
irling+0.036
irl+0.036
 mouths+0.036
Neg logit contributions
izzy-0.036
enny-0.030
 opener-0.029
taker-0.029
ppy-0.028
TokenOnce
Token ID7454
Feature activation-1.32e-02

Pos logit contributions
izzy+0.030
enny+0.026
ppy+0.026
taker+0.026
 opener+0.026
Neg logit contributions
ement-0.024
 mouths-0.023
 wrists-0.023
irl-0.023
 soaring-0.023
Token upon
Token ID2402
Feature activation+9.64e-03

Pos logit contributions
ement+0.025
 mouths+0.024
irl+0.024
 wrists+0.024
irling+0.023
Neg logit contributions
izzy-0.021
enny-0.018
ppy-0.018
 opener-0.018
taker-0.017
Token.
Token ID13
Feature activation-2.09e-02

Pos logit contributions
izzy+0.011
enny+0.009
ppy+0.009
 opener+0.009
taker+0.009
Neg logit contributions
ement-0.013
 mouths-0.012
 wrists-0.012
mm-0.012
irling-0.012
Token And
Token ID843
Feature activation-9.56e-03

Pos logit contributions
ement+0.040
 wrists+0.039
irling+0.039
irl+0.038
 mouths+0.037
Neg logit contributions
izzy-0.036
enny-0.030
 opener-0.029
ily-0.028
taker-0.028
Token they
Token ID484
Feature activation-1.02e-02

Pos logit contributions
ement+0.018
irling+0.017
 wrists+0.017
 mouths+0.017
irl+0.017
Neg logit contributions
izzy-0.016
enny-0.014
 opener-0.014
ppy-0.014
taker-0.013
Token lived
Token ID5615
Feature activation-8.69e-03

Pos logit contributions
ement+0.012
 wrists+0.011
 mouths+0.011
irl+0.011
irling+0.011
Neg logit contributions
izzy-0.024
enny-0.022
 opener-0.021
ppy-0.021
taker-0.021
Token happily
Token ID18177
Feature activation+4.17e-02

Pos logit contributions
ement+0.012
 mouths+0.012
 wrists+0.012
irl+0.011
irling+0.011
Neg logit contributions
izzy-0.019
enny-0.016
ppy-0.016
 opener-0.016
taker-0.016
Token ever
Token ID1683
Feature activation+6.95e-02

Pos logit contributions
izzy+0.062
enny+0.052
 opener+0.051
taker+0.050
ppy+0.049
Neg logit contributions
ement-0.085
 mouths-0.083
 soaring-0.083
 wrists-0.082
mm-0.081
Token after
Token ID706
Feature activation+1.13e-02

Pos logit contributions
izzy+0.114
taker+0.096
 opener+0.092
enny+0.092
washer+0.088
Neg logit contributions
 mouths-0.131
 conversations-0.130
 soaring-0.127
 tails-0.125
 pic-0.124
Token.
Token ID13
Feature activation-2.69e-02

Pos logit contributions
izzy+0.016
enny+0.013
 opener+0.013
taker+0.013
ppy+0.013
Neg logit contributions
ement-0.023
 wrists-0.023
 mouths-0.023
mm-0.022
irling-0.022
Token<|endoftext|>
Token ID50256
Feature activation+1.66e-02

Pos logit contributions
ement+0.049
 wrists+0.047
irling+0.046
 mouths+0.046
irl+0.046
Neg logit contributions
izzy-0.048
enny-0.041
 opener-0.040
ppy-0.039
taker-0.039
TokenOnce
Token ID7454
Feature activation-1.67e-02

Pos logit contributions
izzy+0.032
enny+0.028
ppy+0.028
taker+0.027
 opener+0.027
Neg logit contributions
ement-0.026
 mouths-0.025
 wrists-0.025
irl-0.025
irling-0.025
Token upon
Token ID2402
Feature activation+9.12e-03

Pos logit contributions
ement+0.032
 mouths+0.031
 wrists+0.031
irl+0.030
irling+0.030
Neg logit contributions
izzy-0.027
enny-0.023
ppy-0.022
 opener-0.022
taker-0.022
Token couple
Token ID3155
Feature activation-1.01e-02

Pos logit contributions
ement+0.008
irling+0.008
mm+0.008
 wrists+0.007
irl+0.007
Neg logit contributions
izzy-0.008
 opener-0.008
taker-0.007
guard-0.007
enny-0.007
Token.
Token ID13
Feature activation-4.77e-03

Pos logit contributions
ement+0.020
mm+0.020
irl+0.020
irling+0.020
 wrists+0.020
Neg logit contributions
izzy-0.015
enny-0.013
ppy-0.013
taker-0.013
 opener-0.012
Token They
Token ID1119
Feature activation+2.21e-03

Pos logit contributions
ement+0.008
irling+0.008
 soaring+0.008
irl+0.008
 wrists+0.008
Neg logit contributions
izzy-0.009
 opener-0.007
enny-0.007
ppy-0.007
ro-0.007
Token lived
Token ID5615
Feature activation-5.88e-03

Pos logit contributions
izzy+0.005
enny+0.004
 opener+0.004
ppy+0.004
taker+0.004
Neg logit contributions
ement-0.003
 wrists-0.003
 mouths-0.003
irl-0.003
 soaring-0.003
Token happily
Token ID18177
Feature activation+3.94e-02

Pos logit contributions
ement+0.009
 wrists+0.008
 mouths+0.008
irling+0.008
irl+0.008
Neg logit contributions
izzy-0.012
enny-0.011
ppy-0.010
 opener-0.010
taker-0.010
Token ever
Token ID1683
Feature activation+6.92e-02

Pos logit contributions
izzy+0.056
enny+0.047
ppy+0.045
 opener+0.045
taker+0.044
Neg logit contributions
ement-0.084
 mouths-0.081
 wrists-0.081
irling-0.080
 soaring-0.079
Token after
Token ID706
Feature activation+1.58e-02

Pos logit contributions
izzy+0.106
enny+0.085
taker+0.083
 opener+0.081
washer+0.075
Neg logit contributions
 mouths-0.142
 conversations-0.140
ement-0.139
 wrists-0.138
 soaring-0.137
Token.
Token ID13
Feature activation-7.74e-03

Pos logit contributions
izzy+0.023
enny+0.019
 opener+0.019
ppy+0.018
taker+0.018
Neg logit contributions
ement-0.033
 mouths-0.032
 wrists-0.032
mm-0.031
irling-0.031
Token<|endoftext|>
Token ID50256
Feature activation+2.66e-02

Pos logit contributions
ement+0.014
irling+0.014
 wrists+0.014
 soaring+0.013
irl+0.013
Neg logit contributions
izzy-0.013
enny-0.011
 opener-0.011
ppy-0.011
taker-0.011
TokenTom
Token ID13787
Feature activation-1.60e-02

Pos logit contributions
izzy+0.045
enny+0.039
ppy+0.038
 opener+0.037
taker+0.037
Neg logit contributions
ement-0.049
 mouths-0.047
 wrists-0.047
irling-0.046
irl-0.046
Token and
Token ID290
Feature activation-2.63e-03

Pos logit contributions
ement+0.025
 mouths+0.024
 wrists+0.024
irling+0.023
irl+0.023
Neg logit contributions
izzy-0.032
enny-0.028
 opener-0.027
ppy-0.027
taker-0.027
Token They
Token ID1119
Feature activation-1.34e-02

Pos logit contributions
izzy+0.002
 opener+0.002
enny+0.002
ro+0.002
ppy+0.002
Neg logit contributions
ement-0.002
irling-0.002
irl-0.002
 soaring-0.002
 wrists-0.002
Token also
Token ID635
Feature activation-1.26e-02

Pos logit contributions
ement+0.024
irling+0.022
 soaring+0.022
mm+0.021
 conversations+0.021
Neg logit contributions
izzy-0.024
 opener-0.021
ppy-0.021
taker-0.020
ro-0.020
Token see
Token ID766
Feature activation-1.77e-02

Pos logit contributions
ement+0.028
irling+0.026
mm+0.026
 soaring+0.026
irl+0.025
Neg logit contributions
izzy-0.016
 opener-0.014
ppy-0.014
ro-0.013
taker-0.013
Token some
Token ID617
Feature activation-6.80e-03

Pos logit contributions
irling+0.033
irl+0.033
ement+0.032
 soaring+0.030
 disagreement+0.030
Neg logit contributions
izzy-0.028
head-0.024
taker-0.024
ily-0.024
ppy-0.023
Token fancy
Token ID14996
Feature activation-2.40e-02

Pos logit contributions
irling+0.011
irl+0.011
 soaring+0.011
 wrists+0.010
ement+0.010
Neg logit contributions
izzy-0.012
guard-0.011
 opener-0.010
head-0.010
taker-0.010
Token topp
Token ID23126
Feature activation-7.42e-02

Pos logit contributions
irling+0.031
irl+0.031
 soaring+0.030
ement+0.029
 disagreement+0.028
Neg logit contributions
izzy-0.050
ro-0.047
head-0.046
guard-0.045
 opener-0.045
Tokenings
Token ID654
Feature activation+1.07e-02

Pos logit contributions
 soaring+0.119
 pic+0.114
irling+0.113
ement+0.113
 conversations+0.111
Neg logit contributions
izzy-0.138
ro-0.125
 opener-0.120
ppy-0.119
enny-0.117
Token.
Token ID13
Feature activation+3.64e-03

Pos logit contributions
izzy+0.019
enny+0.016
ppy+0.016
 opener+0.015
taker+0.015
Neg logit contributions
ement-0.019
 mouths-0.018
 wrists-0.018
mm-0.018
 soaring-0.018
Token They
Token ID1119
Feature activation-1.50e-02

Pos logit contributions
izzy+0.007
 opener+0.006
enny+0.006
ro+0.006
head+0.005
Neg logit contributions
ement-0.006
irling-0.006
irl-0.006
 soaring-0.006
 wrists-0.006
Token see
Token ID766
Feature activation-1.76e-02

Pos logit contributions
ement+0.027
irling+0.025
mm+0.025
 soaring+0.025
 mouths+0.024
Neg logit contributions
izzy-0.026
 opener-0.023
ppy-0.023
taker-0.022
ro-0.022
Token sprink
Token ID27562
Feature activation-2.51e-02

Pos logit contributions
irling+0.034
irl+0.033
ement+0.032
 soaring+0.031
 disagreement+0.030
Neg logit contributions
izzy-0.027
head-0.023
taker-0.023
ily-0.023
ppy-0.022
Token,
Token ID11
Feature activation-8.20e-03

Pos logit contributions
 mouths+0.022
 wrists+0.021
ement+0.020
mm+0.019
 best+0.019
Neg logit contributions
izzy-0.030
enny-0.027
ppy-0.025
taker-0.025
head-0.025
Token sauce
Token ID10746
Feature activation-6.26e-03

Pos logit contributions
ement+0.014
irling+0.014
irl+0.013
 soaring+0.013
 conversations+0.013
Neg logit contributions
izzy-0.015
 opener-0.014
ppy-0.013
enny-0.013
taker-0.012
Token,
Token ID11
Feature activation-1.22e-02

Pos logit contributions
ement+0.009
 mouths+0.009
 wrists+0.009
mm+0.009
irl+0.008
Neg logit contributions
izzy-0.013
enny-0.012
ppy-0.011
taker-0.011
head-0.011
Token cheese
Token ID9891
Feature activation-1.37e-02

Pos logit contributions
ement+0.021
irling+0.020
 wrists+0.020
irl+0.020
 soaring+0.020
Neg logit contributions
izzy-0.022
 opener-0.019
ppy-0.019
enny-0.019
ro-0.018
Token and
Token ID290
Feature activation+8.53e-03

Pos logit contributions
 mouths+0.019
ement+0.018
 wrists+0.018
mm+0.018
 pic+0.017
Neg logit contributions
izzy-0.030
enny-0.027
taker-0.025
ppy-0.025
head-0.024
Token topp
Token ID23126
Feature activation-7.13e-02

Pos logit contributions
izzy+0.017
enny+0.015
 opener+0.015
ppy+0.015
taker+0.014
Neg logit contributions
ement-0.013
irling-0.012
 wrists-0.012
 mouths-0.012
irl-0.012
Tokenings
Token ID654
Feature activation+1.51e-02

Pos logit contributions
ement+0.103
 soaring+0.101
irling+0.097
 pic+0.096
 wrists+0.095
Neg logit contributions
izzy-0.147
ppy-0.130
enny-0.129
ro-0.127
 opener-0.127
Token.
Token ID13
Feature activation+5.11e-03

Pos logit contributions
izzy+0.029
enny+0.026
ppy+0.025
taker+0.024
 opener+0.024
Neg logit contributions
ement-0.024
 mouths-0.024
 wrists-0.023
mm-0.022
 conversations-0.022
Token She
Token ID1375
Feature activation-1.11e-03

Pos logit contributions
izzy+0.010
ppy+0.009
enny+0.009
guard+0.009
taker+0.009
Neg logit contributions
 mouths-0.008
ement-0.008
 wrists-0.008
mm-0.007
 pic-0.007
Token showed
Token ID3751
Feature activation-3.96e-04

Pos logit contributions
 mouths+0.002
 wrists+0.002
ement+0.002
irl+0.002
mm+0.002
Neg logit contributions
izzy-0.002
enny-0.002
taker-0.002
ppy-0.002
ro-0.002
Token them
Token ID606
Feature activation-1.10e-03

Pos logit contributions
 mouths+0.000
ement+0.000
 wrists+0.000
 noses+0.000
 conversations+0.000
Neg logit contributions
izzy-0.001
 opener-0.001
ppy-0.001
ro-0.001
enny-0.001
Token it
Token ID340
Feature activation+1.47e-02

Pos logit contributions
ement+0.024
 wrists+0.023
mm+0.023
irling+0.023
 mouths+0.022
Neg logit contributions
izzy-0.013
enny-0.010
ppy-0.010
 opener-0.010
taker-0.010
Token at
Token ID379
Feature activation+2.20e-03

Pos logit contributions
izzy+0.023
enny+0.020
ppy+0.019
 opener+0.019
taker+0.019
Neg logit contributions
ement-0.029
 mouths-0.028
 wrists-0.028
irling-0.027
irl-0.027
Token Lily
Token ID20037
Feature activation-3.60e-03

Pos logit contributions
izzy+0.004
enny+0.004
ppy+0.004
taker+0.004
 opener+0.004
Neg logit contributions
ement-0.003
 mouths-0.003
 wrists-0.003
irl-0.003
 soaring-0.003
Token.
Token ID13
Feature activation+2.73e-02

Pos logit contributions
ement+0.006
 mouths+0.006
 wrists+0.006
irling+0.006
mm+0.006
Neg logit contributions
izzy-0.007
enny-0.006
ppy-0.006
 opener-0.006
taker-0.005
Token He
Token ID679
Feature activation-7.45e-03

Pos logit contributions
izzy+0.056
ppy+0.056
guard+0.051
ba+0.051
eware+0.050
Neg logit contributions
 mouths-0.037
 wrists-0.034
ement-0.034
 -0.033
 pic-0.032
Token squee
Token ID13170
Feature activation-6.86e-02

Pos logit contributions
ement+0.010
 wrists+0.009
 mouths+0.009
mm+0.009
irling+0.009
Neg logit contributions
izzy-0.016
enny-0.015
ppy-0.014
 opener-0.014
taker-0.014
Tokenzes
Token ID12271
Feature activation-1.58e-02

Pos logit contributions
 soaring+0.109
ement+0.101
 difference+0.100
 pic+0.097
 narrative+0.095
Neg logit contributions
izzy-0.124
ppy-0.116
ro-0.113
ed-0.109
enny-0.107
Token the
Token ID262
Feature activation+1.92e-03

Pos logit contributions
 mouths+0.020
ement+0.019
 wrists+0.019
irl+0.018
 hearts+0.017
Neg logit contributions
izzy-0.036
enny-0.033
ppy-0.032
 opener-0.032
taker-0.031
Token spray
Token ID11662
Feature activation-2.10e-03

Pos logit contributions
izzy+0.004
enny+0.003
ppy+0.003
 opener+0.003
taker+0.003
Neg logit contributions
ement-0.003
 mouths-0.003
 wrists-0.003
irling-0.003
irl-0.003
Token and
Token ID290
Feature activation-1.86e-02

Pos logit contributions
 mouths+0.003
ement+0.003
 wrists+0.003
 soaring+0.003
irl+0.003
Neg logit contributions
izzy-0.004
enny-0.004
ppy-0.004
taker-0.003
 opener-0.003
Token a
Token ID257
Feature activation-8.43e-03

Pos logit contributions
ement+0.031
mm+0.028
irling+0.027
 conversations+0.027
aman+0.027
Neg logit contributions
izzy-0.035
 opener-0.031
ro-0.030
ppy-0.030
taker-0.030
Token of
Token ID286
Feature activation+7.72e-04

Pos logit contributions
izzy+0.065
enny+0.060
ppy+0.058
ba+0.050
unny+0.050
Neg logit contributions
ement-0.092
 mouths-0.090
 course-0.087
 pic-0.087
mm-0.086
Token cheese
Token ID9891
Feature activation+3.63e-03

Pos logit contributions
izzy+0.002
 opener+0.001
taker+0.001
ro+0.001
head+0.001
Neg logit contributions
ement-0.001
irling-0.001
mm-0.001
 wrists-0.001
 soaring-0.001
Token and
Token ID290
Feature activation+1.42e-03

Pos logit contributions
izzy+0.007
enny+0.007
taker+0.006
ppy+0.006
 opener+0.006
Neg logit contributions
 mouths-0.005
 wrists-0.005
ement-0.005
 pic-0.005
mm-0.005
Token sauce
Token ID10746
Feature activation+1.54e-02

Pos logit contributions
izzy+0.003
enny+0.003
 opener+0.002
ppy+0.002
taker+0.002
Neg logit contributions
ement-0.002
 wrists-0.002
irling-0.002
 mouths-0.002
irl-0.002
Token and
Token ID290
Feature activation+5.43e-04

Pos logit contributions
izzy+0.030
enny+0.027
taker+0.025
ppy+0.025
 opener+0.025
Neg logit contributions
 mouths-0.023
ement-0.023
 wrists-0.022
mm-0.022
 pic-0.022
Token topp
Token ID23126
Feature activation-6.86e-02

Pos logit contributions
izzy+0.001
 opener+0.001
ppy+0.001
enny+0.001
taker+0.001
Neg logit contributions
ement-0.001
irling-0.001
irl-0.001
 wrists-0.001
 soaring-0.001
Tokenings
Token ID654
Feature activation+1.89e-02

Pos logit contributions
ement+0.101
 soaring+0.100
irling+0.096
 pic+0.094
 conversations+0.093
Neg logit contributions
izzy-0.137
ppy-0.123
ro-0.120
enny-0.119
 opener-0.118
Token.
Token ID13
Feature activation-8.33e-03

Pos logit contributions
izzy+0.035
enny+0.031
 opener+0.029
ppy+0.029
taker+0.029
Neg logit contributions
ement-0.031
 mouths-0.031
 wrists-0.030
mm-0.030
 soaring-0.029
Token The
Token ID383
Feature activation-5.18e-03

Pos logit contributions
ement+0.011
 mouths+0.011
mm+0.011
 wrists+0.011
 pic+0.010
Neg logit contributions
izzy-0.018
enny-0.016
ppy-0.016
taker-0.016
 opener-0.015
Token people
Token ID661
Feature activation-2.51e-02

Pos logit contributions
ement+0.008
irling+0.008
irl+0.007
 wrists+0.007
 soaring+0.007
Neg logit contributions
izzy-0.010
 opener-0.009
taker-0.009
ro-0.009
enny-0.009
Token who
Token ID508
Feature activation-2.88e-02

Pos logit contributions
ement+0.041
 wrists+0.039
 mouths+0.039
irling+0.038
mm+0.038
Neg logit contributions
izzy-0.048
ppy-0.041
enny-0.041
 opener-0.041
taker-0.041
Token elephants
Token ID25368
Feature activation-2.42e-02

Pos logit contributions
ement+0.023
irling+0.021
 wrists+0.021
 mouths+0.021
irl+0.021
Neg logit contributions
izzy-0.023
enny-0.020
ppy-0.020
 opener-0.019
taker-0.019
Token,
Token ID11
Feature activation-1.85e-02

Pos logit contributions
ement+0.044
irl+0.044
irling+0.043
 wrists+0.043
mm+0.042
Neg logit contributions
izzy-0.040
 opener-0.035
ppy-0.035
ro-0.034
enny-0.034
Token lions
Token ID31420
Feature activation-3.57e-02

Pos logit contributions
ement+0.035
irling+0.033
irl+0.032
 wrists+0.032
mm+0.032
Neg logit contributions
izzy-0.031
ppy-0.027
 opener-0.026
ro-0.026
enny-0.026
Token and
Token ID290
Feature activation+5.43e-03

Pos logit contributions
ement+0.065
irl+0.064
irling+0.063
 wrists+0.062
mm+0.062
Neg logit contributions
izzy-0.059
ppy-0.052
ro-0.052
 opener-0.051
enny-0.049
Token ac
Token ID936
Feature activation-8.10e-03

Pos logit contributions
izzy+0.011
enny+0.010
ppy+0.009
 opener+0.009
taker+0.009
Neg logit contributions
ement-0.008
 mouths-0.008
 wrists-0.008
irling-0.008
irl-0.008
Tokenrob
Token ID22609
Feature activation-6.84e-02

Pos logit contributions
ement+0.007
 mouths+0.006
 wrists+0.006
irling+0.006
irl+0.006
Neg logit contributions
izzy-0.022
enny-0.020
ppy-0.019
 opener-0.019
taker-0.019
Tokenats
Token ID1381
Feature activation-9.95e-03

Pos logit contributions
 difference+0.139
 soaring+0.139
 amaz+0.137
ement+0.133
 shining+0.129
Neg logit contributions
izzy-0.098
ppy-0.087
enny-0.084
ives-0.078
ave-0.077
Token.
Token ID13
Feature activation+4.40e-03

Pos logit contributions
ement+0.018
 mouths+0.017
 wrists+0.017
irling+0.017
 soaring+0.017
Neg logit contributions
izzy-0.017
enny-0.015
ppy-0.014
 opener-0.014
taker-0.014
Token They
Token ID1119
Feature activation-1.74e-02

Pos logit contributions
izzy+0.010
enny+0.009
ppy+0.009
taker+0.009
 opener+0.009
Neg logit contributions
ement-0.006
 mouths-0.006
 wrists-0.005
mm-0.005
 conversations-0.005
Token are
Token ID389
Feature activation-2.49e-02

Pos logit contributions
ement+0.029
 mouths+0.027
mm+0.027
 wrists+0.027
irling+0.027
Neg logit contributions
izzy-0.033
ppy-0.028
enny-0.028
 opener-0.028
taker-0.028
Token amazed
Token ID24562
Feature activation+1.36e-03

Pos logit contributions
ement+0.040
mm+0.038
 wrists+0.036
irl+0.035
irling+0.035
Neg logit contributions
izzy-0.049
taker-0.043
ppy-0.042
 opener-0.042
enny-0.040
Token and
Token ID290
Feature activation-2.32e-02

Pos logit contributions
ement+0.006
 mouths+0.006
 wrists+0.006
irling+0.006
irl+0.006
Neg logit contributions
izzy-0.006
enny-0.005
ppy-0.005
 opener-0.005
taker-0.005
Token squ
Token ID2809
Feature activation-9.30e-03

Pos logit contributions
ement+0.041
aman+0.037
 conversations+0.036
irling+0.035
 disagreement+0.034
Neg logit contributions
izzy-0.043
 opener-0.040
taker-0.038
ro-0.038
ppy-0.037
Tokenishy
Token ID49785
Feature activation+6.87e-03

Pos logit contributions
ement+0.017
 mouths+0.016
 wrists+0.016
irling+0.016
irl+0.016
Neg logit contributions
izzy-0.016
enny-0.014
 opener-0.014
taker-0.014
ppy-0.014
Token.
Token ID13
Feature activation+9.99e-03

Pos logit contributions
izzy+0.014
enny+0.012
ppy+0.011
 opener+0.011
taker+0.011
Neg logit contributions
ement-0.011
 mouths-0.011
 wrists-0.011
 soaring-0.010
mm-0.010
Token She
Token ID1375
Feature activation+7.04e-03

Pos logit contributions
izzy+0.022
ppy+0.020
guard+0.020
washer+0.019
enny+0.019
Neg logit contributions
ement-0.013
mm-0.013
 mouths-0.013
 wrists-0.012
 blonde-0.012
Token squee
Token ID13170
Feature activation-6.83e-02

Pos logit contributions
izzy+0.015
ppy+0.013
 opener+0.013
enny+0.013
ro+0.013
Neg logit contributions
ement-0.010
mm-0.009
irling-0.009
 soaring-0.009
 conversations-0.009
Tokenzes
Token ID12271
Feature activation-1.71e-02

Pos logit contributions
 soaring+0.109
ement+0.102
 difference+0.101
 pic+0.100
 narrative+0.098
Neg logit contributions
izzy-0.122
ppy-0.115
ro-0.113
ed-0.107
enny-0.103
Token it
Token ID340
Feature activation+1.23e-02

Pos logit contributions
 mouths+0.021
ement+0.021
 wrists+0.021
 soaring+0.019
irl+0.019
Neg logit contributions
izzy-0.040
enny-0.036
 opener-0.035
ppy-0.035
taker-0.034
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
izzy+0.021
 opener+0.018
ppy+0.018
enny+0.018
ro+0.018
Neg logit contributions
ement-0.022
mm-0.021
irling-0.021
 mouths-0.021
 wrists-0.021
Token it
Token ID340
Feature activation+3.43e-03

Pos logit contributions
ement+0.028
 conversations+0.025
irling+0.025
aman+0.024
mm+0.024
Neg logit contributions
izzy-0.029
ro-0.027
 opener-0.026
ppy-0.026
taker-0.025
Token makes
Token ID1838
Feature activation+2.45e-04

Pos logit contributions
izzy+0.007
 opener+0.006
ro+0.006
ppy+0.006
taker+0.006
Neg logit contributions
ement-0.006
mm-0.005
irling-0.005
 pic-0.005
 wrists-0.005
Token likes
Token ID7832
Feature activation-2.71e-03

Pos logit contributions
izzy+0.017
ppy+0.015
 opener+0.015
enny+0.015
ro+0.015
Neg logit contributions
ement-0.012
 soaring-0.012
mm-0.011
irling-0.011
 conversations-0.011
Token the
Token ID262
Feature activation-1.19e-02

Pos logit contributions
ement+0.005
mm+0.005
irling+0.005
 wrists+0.005
irl+0.005
Neg logit contributions
izzy-0.005
 opener-0.004
enny-0.004
ppy-0.004
taker-0.004
Token helmet
Token ID14335
Feature activation-1.30e-02

Pos logit contributions
irling+0.021
 wrists+0.021
mm+0.021
ement+0.020
irl+0.020
Neg logit contributions
izzy-0.019
taker-0.018
 opener-0.018
ro-0.017
head-0.017
Token.
Token ID13
Feature activation+4.68e-03

Pos logit contributions
ement+0.026
irling+0.026
irl+0.026
 wrists+0.025
mm+0.025
Neg logit contributions
izzy-0.019
 opener-0.016
ppy-0.016
enny-0.016
taker-0.016
Token She
Token ID1375
Feature activation+7.81e-03

Pos logit contributions
izzy+0.009
ppy+0.008
taker+0.008
enny+0.008
guard+0.008
Neg logit contributions
ement-0.007
 mouths-0.007
mm-0.006
 wrists-0.006
 pic-0.006
Token squee
Token ID13170
Feature activation-6.75e-02

Pos logit contributions
izzy+0.016
ppy+0.014
 opener+0.014
enny+0.014
ro+0.014
Neg logit contributions
ement-0.011
 soaring-0.011
mm-0.011
irling-0.011
 conversations-0.010
Tokenzes
Token ID12271
Feature activation-1.85e-02

Pos logit contributions
 soaring+0.105
ement+0.102
 difference+0.100
 pic+0.096
 conversations+0.096
Neg logit contributions
izzy-0.120
ppy-0.115
ro-0.111
ed-0.105
enny-0.101
Token the
Token ID262
Feature activation-9.72e-03

Pos logit contributions
 mouths+0.024
ement+0.023
 wrists+0.023
 soaring+0.022
irl+0.022
Neg logit contributions
izzy-0.042
enny-0.038
ppy-0.037
 opener-0.037
taker-0.036
Token helmet
Token ID14335
Feature activation-1.13e-02

Pos logit contributions
ement+0.014
irling+0.014
mm+0.013
 pic+0.013
irl+0.013
Neg logit contributions
izzy-0.020
taker-0.018
ro-0.018
 opener-0.017
ppy-0.017
Token on
Token ID319
Feature activation-5.81e-03

Pos logit contributions
ement+0.021
irling+0.020
 wrists+0.020
 mouths+0.020
mm+0.020
Neg logit contributions
izzy-0.019
 opener-0.016
ppy-0.016
enny-0.016
ro-0.016
Token her
Token ID607
Feature activation+2.02e-04

Pos logit contributions
ement+0.009
 mouths+0.008
 wrists+0.008
 soaring+0.008
irl+0.008
Neg logit contributions
izzy-0.012
enny-0.010
ppy-0.010
 opener-0.010
taker-0.010
Token clown
Token ID25573
Feature activation-3.16e-02

Pos logit contributions
ement+0.019
 mouths+0.018
 wrists+0.018
mm+0.018
irling+0.018
Neg logit contributions
izzy-0.022
enny-0.019
taker-0.018
ppy-0.018
 opener-0.018
Tokens
Token ID82
Feature activation-1.34e-02

Pos logit contributions
ement+0.058
mm+0.057
 wrists+0.056
 mouths+0.055
irl+0.055
Neg logit contributions
izzy-0.054
enny-0.047
ppy-0.046
 opener-0.043
guard-0.043
Token juggling
Token ID48097
Feature activation-2.43e-02

Pos logit contributions
mm+0.024
ement+0.024
irl+0.023
irling+0.023
 wrists+0.023
Neg logit contributions
izzy-0.022
ro-0.019
enny-0.019
guard-0.019
 opener-0.018
Token and
Token ID290
Feature activation-9.64e-03

Pos logit contributions
ement+0.038
 wrists+0.036
 mouths+0.036
irling+0.035
mm+0.035
Neg logit contributions
izzy-0.048
enny-0.042
ppy-0.042
 opener-0.041
taker-0.041
Token ac
Token ID936
Feature activation-4.04e-04

Pos logit contributions
ement+0.013
mm+0.012
irl+0.011
 mouths+0.011
irling+0.011
Neg logit contributions
izzy-0.022
enny-0.019
ppy-0.019
taker-0.019
 opener-0.019
Tokenrob
Token ID22609
Feature activation-6.72e-02

Pos logit contributions
ement+0.000
 wrists+0.000
irling+0.000
mm+0.000
irl+0.000
Neg logit contributions
izzy-0.001
enny-0.001
ppy-0.001
 opener-0.001
taker-0.001
Tokenats
Token ID1381
Feature activation-2.93e-03

Pos logit contributions
 difference+0.127
 soaring+0.125
 amaz+0.122
 wrists+0.118
ement+0.114
Neg logit contributions
izzy-0.108
enny-0.099
ppy-0.091
ave-0.091
ives-0.086
Token doing
Token ID1804
Feature activation-2.72e-02

Pos logit contributions
ement+0.005
 mouths+0.005
 wrists+0.005
mm+0.005
irl+0.005
Neg logit contributions
izzy-0.005
enny-0.004
ppy-0.004
 opener-0.004
taker-0.004
Token flips
Token ID45971
Feature activation+4.34e-03

Pos logit contributions
mm+0.045
ement+0.044
aman+0.040
 narrative+0.039
 mouths+0.039
Neg logit contributions
izzy-0.047
taker-0.043
ro-0.042
head-0.042
 opener-0.042
Token.
Token ID13
Feature activation-9.60e-03

Pos logit contributions
izzy+0.008
enny+0.007
ppy+0.006
 opener+0.006
taker+0.006
Neg logit contributions
ement-0.008
 soaring-0.007
 wrists-0.007
 mouths-0.007
irling-0.007
Token But
Token ID887
Feature activation+6.44e-04

Pos logit contributions
ement+0.015
irling+0.015
 mouths+0.014
 wrists+0.014
irl+0.014
Neg logit contributions
izzy-0.019
enny-0.017
 opener-0.016
taker-0.016
ppy-0.016
Token and
Token ID290
Feature activation-2.39e-02

Pos logit contributions
ement+0.013
 mouths+0.012
 wrists+0.012
irling+0.012
irl+0.012
Neg logit contributions
izzy-0.013
enny-0.012
ppy-0.011
 opener-0.011
taker-0.011
Token squ
Token ID2809
Feature activation-7.53e-03

Pos logit contributions
ement+0.042
aman+0.038
 conversations+0.037
irling+0.037
 disagreement+0.036
Neg logit contributions
izzy-0.045
 opener-0.041
taker-0.039
ro-0.039
ppy-0.038
Tokenishy
Token ID49785
Feature activation+6.08e-03

Pos logit contributions
ement+0.013
 mouths+0.013
 wrists+0.012
irl+0.012
irling+0.012
Neg logit contributions
izzy-0.014
enny-0.012
 opener-0.012
taker-0.012
ppy-0.011
Token.
Token ID13
Feature activation+4.58e-03

Pos logit contributions
izzy+0.012
enny+0.010
ppy+0.010
 opener+0.010
taker+0.009
Neg logit contributions
ement-0.010
 mouths-0.010
 wrists-0.010
mm-0.009
 soaring-0.009
Token She
Token ID1375
Feature activation+6.31e-03

Pos logit contributions
izzy+0.009
ppy+0.009
guard+0.008
taker+0.008
enny+0.008
Neg logit contributions
mm-0.006
ement-0.006
 mouths-0.006
 wrists-0.006
 pic-0.006
Token squee
Token ID13170
Feature activation-6.66e-02

Pos logit contributions
izzy+0.014
enny+0.012
 opener+0.012
ppy+0.012
taker+0.012
Neg logit contributions
ement-0.008
irling-0.008
mm-0.008
 wrists-0.008
 mouths-0.008
Tokenzes
Token ID12271
Feature activation-1.78e-02

Pos logit contributions
 soaring+0.105
ement+0.099
 difference+0.096
 pic+0.093
 narrative+0.093
Neg logit contributions
izzy-0.121
ppy-0.114
ro-0.112
ed-0.105
enny-0.102
Token it
Token ID340
Feature activation+1.13e-02

Pos logit contributions
 mouths+0.023
 wrists+0.023
ement+0.023
 soaring+0.021
irl+0.021
Neg logit contributions
izzy-0.040
enny-0.036
ppy-0.035
 opener-0.035
taker-0.034
Token and
Token ID290
Feature activation-1.68e-02

Pos logit contributions
izzy+0.019
 opener+0.017
ro+0.017
ppy+0.017
taker+0.016
Neg logit contributions
ement-0.021
mm-0.020
irling-0.019
 mouths-0.019
 wrists-0.019
Token it
Token ID340
Feature activation+6.13e-04

Pos logit contributions
ement+0.028
 conversations+0.025
irling+0.025
aman+0.025
mm+0.025
Neg logit contributions
izzy-0.030
ro-0.028
 opener-0.028
ppy-0.027
taker-0.026
Token makes
Token ID1838
Feature activation-1.03e-03

Pos logit contributions
izzy+0.001
 opener+0.001
ro+0.001
ppy+0.001
taker+0.001
Neg logit contributions
ement-0.001
mm-0.001
irling-0.001
 pic-0.001
aman-0.001
Token jump
Token ID4391
Feature activation+9.22e-03

Pos logit contributions
ement+0.001
mm+0.001
 mouths+0.001
 wrists+0.001
irling+0.001
Neg logit contributions
izzy-0.002
enny-0.001
 opener-0.001
ppy-0.001
taker-0.001
Token and
Token ID290
Feature activation-7.94e-06

Pos logit contributions
izzy+0.020
enny+0.018
ppy+0.017
taker+0.017
 opener+0.017
Neg logit contributions
ement-0.013
irl-0.012
 soaring-0.012
 wrists-0.012
 mouths-0.012
Token laugh
Token ID6487
Feature activation+5.93e-03

Feature not active on prev token;
no predictions were affected.
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
izzy+0.011
enny+0.009
 opener+0.009
ppy+0.009
taker+0.009
Neg logit contributions
ement-0.010
 wrists-0.010
 mouths-0.010
 soaring-0.010
irl-0.010
Token The
Token ID383
Feature activation-1.01e-02

Pos logit contributions
ement+0.022
 soaring+0.021
irling+0.021
mm+0.020
opl+0.020
Neg logit contributions
izzy-0.016
enny-0.014
ro-0.013
 opener-0.013
ppy-0.013
Token sun
Token ID4252
Feature activation-6.62e-02

Pos logit contributions
ement+0.015
 mouths+0.014
 wrists+0.014
irling+0.014
irl+0.013
Neg logit contributions
izzy-0.021
enny-0.019
ppy-0.018
 opener-0.018
taker-0.018
Token is
Token ID318
Feature activation-1.53e-02

Pos logit contributions
ement+0.098
 wrists+0.096
 blonde+0.093
 conversations+0.093
irling+0.092
Neg logit contributions
izzy-0.137
ro-0.116
guard-0.113
 opener-0.113
head-0.109
Token warm
Token ID5814
Feature activation-1.13e-02

Pos logit contributions
 wrists+0.020
ement+0.020
 mouths+0.019
mm+0.019
heit+0.018
Neg logit contributions
izzy-0.032
head-0.029
ppy-0.028
 opener-0.028
taker-0.028
Token and
Token ID290
Feature activation-2.96e-02

Pos logit contributions
irling+0.023
 wrists+0.023
irl+0.023
ement+0.022
 mouths+0.022
Neg logit contributions
izzy-0.016
head-0.014
ppy-0.014
 opener-0.013
taker-0.013
Token the
Token ID262
Feature activation-6.70e-03

Pos logit contributions
ement+0.063
irling+0.055
 wrists+0.054
 conversations+0.054
 sincere+0.054
Neg logit contributions
izzy-0.042
head-0.038
ppy-0.033
taker-0.033
 opener-0.033
Token wind
Token ID2344
Feature activation-4.30e-02

Pos logit contributions
ement+0.012
irling+0.012
mm+0.011
irl+0.011
cks+0.011
Neg logit contributions
izzy-0.012
ro-0.010
head-0.010
taker-0.010
ppy-0.010
Token they
Token ID484
Feature activation-3.69e-02

Pos logit contributions
ement+0.054
irling+0.052
 wrists+0.052
irl+0.051
 soaring+0.051
Neg logit contributions
izzy-0.057
enny-0.050
 opener-0.049
taker-0.048
head-0.048
Token can
Token ID460
Feature activation-1.50e-02

Pos logit contributions
ement+0.057
 mouths+0.057
 wrists+0.056
irl+0.055
mm+0.054
Neg logit contributions
izzy-0.071
enny-0.063
ro-0.060
ppy-0.060
 opener-0.060
Token add
Token ID751
Feature activation-7.26e-03

Pos logit contributions
ement+0.025
 mouths+0.024
 wrists+0.024
irl+0.024
irling+0.024
Neg logit contributions
izzy-0.028
enny-0.024
ppy-0.024
taker-0.023
 opener-0.023
Token their
Token ID511
Feature activation+4.35e-03

Pos logit contributions
ement+0.012
irling+0.012
 wrists+0.012
 soaring+0.011
irl+0.011
Neg logit contributions
izzy-0.013
 opener-0.012
enny-0.012
ppy-0.011
taker-0.011
Token own
Token ID898
Feature activation+4.55e-03

Pos logit contributions
izzy+0.009
 opener+0.008
ro+0.008
ppy+0.008
enny+0.007
Neg logit contributions
ement-0.007
irling-0.006
 soaring-0.006
irl-0.006
mm-0.006
Token topp
Token ID23126
Feature activation-6.62e-02

Pos logit contributions
izzy+0.010
 opener+0.009
enny+0.009
ppy+0.009
ro+0.009
Neg logit contributions
ement-0.006
irling-0.006
 wrists-0.006
mm-0.006
 soaring-0.006
Tokenings
Token ID654
Feature activation+8.49e-03

Pos logit contributions
ement+0.090
 soaring+0.089
irling+0.087
 wrists+0.084
irl+0.082
Neg logit contributions
izzy-0.140
enny-0.126
 opener-0.125
ro-0.124
ppy-0.123
Token too
Token ID1165
Feature activation+1.81e-02

Pos logit contributions
izzy+0.016
enny+0.014
taker+0.014
ppy+0.014
 opener+0.013
Neg logit contributions
ement-0.014
mm-0.013
 mouths-0.013
 wrists-0.013
 pic-0.012
Token.
Token ID13
Feature activation-1.89e-02

Pos logit contributions
izzy+0.034
enny+0.030
ppy+0.029
 opener+0.029
taker+0.028
Neg logit contributions
ement-0.030
 mouths-0.029
 wrists-0.029
mm-0.028
irling-0.028
Token Sara
Token ID24799
Feature activation-1.15e-02

Pos logit contributions
 soaring+0.038
ement+0.037
irling+0.037
irl+0.036
cking+0.035
Neg logit contributions
izzy-0.029
enny-0.025
ro-0.024
 opener-0.024
head-0.023
Token chooses
Token ID19769
Feature activation-9.21e-03

Pos logit contributions
ement+0.015
 mouths+0.014
 wrists+0.014
irl+0.014
irling+0.014
Neg logit contributions
izzy-0.026
enny-0.023
ppy-0.023
 opener-0.022
taker-0.022
Token it
Token ID340
Feature activation+1.85e-04

Pos logit contributions
 wrists+0.028
ement+0.028
 mouths+0.028
irl+0.027
 soaring+0.026
Neg logit contributions
izzy-0.053
enny-0.048
ppy-0.047
taker-0.045
 opener-0.045
Token with
Token ID351
Feature activation-1.24e-02

Pos logit contributions
izzy+0.000
enny+0.000
ppy+0.000
 opener+0.000
taker+0.000
Neg logit contributions
ement-0.000
 wrists-0.000
 mouths-0.000
irl-0.000
irling-0.000
Token water
Token ID1660
Feature activation-1.06e-02

Pos logit contributions
ement+0.023
 wrists+0.022
irling+0.022
 mouths+0.022
mm+0.022
Neg logit contributions
izzy-0.021
enny-0.017
 opener-0.017
ppy-0.017
taker-0.017
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
 mouths+0.017
ement+0.017
 wrists+0.017
 soaring+0.016
irl+0.016
Neg logit contributions
izzy-0.020
enny-0.018
ppy-0.017
taker-0.016
 opener-0.016
Token He
Token ID679
Feature activation-1.62e-03

Pos logit contributions
izzy+0.046
ppy+0.046
enny+0.042
ba+0.040
guard+0.039
Neg logit contributions
 mouths-0.033
 wrists-0.029
ement-0.029
mm-0.028
 pic-0.027
Token squee
Token ID13170
Feature activation-6.62e-02

Pos logit contributions
ement+0.002
 mouths+0.002
 wrists+0.002
irl+0.002
irling+0.002
Neg logit contributions
izzy-0.004
enny-0.003
ppy-0.003
taker-0.003
 opener-0.003
Tokenzes
Token ID12271
Feature activation-1.44e-02

Pos logit contributions
ement+0.098
 soaring+0.097
 difference+0.092
 conversations+0.090
 pic+0.089
Neg logit contributions
izzy-0.128
ppy-0.120
ro-0.116
enny-0.110
ed-0.109
Token the
Token ID262
Feature activation+5.53e-03

Pos logit contributions
 mouths+0.017
 wrists+0.016
ement+0.016
 soaring+0.015
 hearts+0.014
Neg logit contributions
izzy-0.034
enny-0.032
ppy-0.030
taker-0.030
 opener-0.030
Token bottle
Token ID9294
Feature activation+9.29e-03

Pos logit contributions
izzy+0.011
enny+0.010
ppy+0.009
taker+0.009
 opener+0.009
Neg logit contributions
ement-0.009
 mouths-0.008
 wrists-0.008
 soaring-0.008
irl-0.008
Token hard
Token ID1327
Feature activation+8.24e-03

Pos logit contributions
izzy+0.018
enny+0.016
ppy+0.016
taker+0.015
eware+0.015
Neg logit contributions
ement-0.014
 mouths-0.014
 soaring-0.014
 wrists-0.014
irl-0.013
Token and
Token ID290
Feature activation-3.89e-03

Pos logit contributions
izzy+0.016
enny+0.014
ppy+0.013
taker+0.013
 opener+0.013
Neg logit contributions
ement-0.014
 mouths-0.013
 wrists-0.013
 soaring-0.012
irling-0.012
Token Mom
Token ID11254
Feature activation-2.24e-02

Pos logit contributions
izzy+0.012
 opener+0.011
enny+0.011
ppy+0.011
ro+0.010
Neg logit contributions
ement-0.008
 soaring-0.007
irling-0.007
 wrists-0.007
irl-0.007
Token.
Token ID13
Feature activation+1.83e-03

Pos logit contributions
ement+0.038
 wrists+0.036
 mouths+0.036
irling+0.035
irl+0.035
Neg logit contributions
izzy-0.042
enny-0.037
ppy-0.036
 opener-0.036
taker-0.035
Token They
Token ID1119
Feature activation-8.78e-05

Pos logit contributions
izzy+0.004
enny+0.003
ppy+0.003
taker+0.003
 opener+0.003
Neg logit contributions
ement-0.003
 mouths-0.003
 wrists-0.003
irl-0.003
irling-0.003
Token put
Token ID1234
Feature activation-3.38e-02

Pos logit contributions
 wrists+0.000
 mouths+0.000
ement+0.000
irl+0.000
 disagreement+0.000
Neg logit contributions
izzy-0.000
enny-0.000
ro-0.000
taker-0.000
eware-0.000
Token on
Token ID319
Feature activation-2.52e-02

Pos logit contributions
irling+0.061
ement+0.061
 soaring+0.058
irl+0.057
mm+0.057
Neg logit contributions
izzy-0.059
 opener-0.050
taker-0.049
ppy-0.049
head-0.048
Token apr
Token ID46593
Feature activation-6.62e-02

Pos logit contributions
ement+0.053
irling+0.050
opl+0.050
 soaring+0.050
mm+0.048
Neg logit contributions
izzy-0.033
 opener-0.031
ro-0.029
head-0.029
ily-0.027
Tokenons
Token ID684
Feature activation-1.39e-02

Pos logit contributions
 soaring+0.103
 wrists+0.100
 difference+0.097
 sincere+0.097
 mouths+0.096
Neg logit contributions
izzy-0.130
enny-0.114
 opener-0.113
washer-0.109
up-0.108
Token to
Token ID284
Feature activation-8.59e-03

Pos logit contributions
ement+0.019
 wrists+0.019
 mouths+0.018
 soaring+0.018
irl+0.017
Neg logit contributions
izzy-0.029
enny-0.026
taker-0.025
eware-0.024
ppy-0.024
Token keep
Token ID1394
Feature activation-3.51e-02

Pos logit contributions
ement+0.015
 wrists+0.014
 mouths+0.014
irl+0.014
irling+0.014
Neg logit contributions
izzy-0.016
enny-0.014
ppy-0.013
taker-0.013
 opener-0.013
Token their
Token ID511
Feature activation-1.00e-02

Pos logit contributions
ement+0.059
 difference+0.053
 soaring+0.053
mm+0.053
irling+0.053
Neg logit contributions
izzy-0.067
ppy-0.058
 opener-0.056
head-0.054
washer-0.054
Token clothes
Token ID8242
Feature activation-9.62e-03

Pos logit contributions
ement+0.015
irling+0.014
 soaring+0.014
irl+0.013
mm+0.013
Neg logit contributions
izzy-0.021
ro-0.018
 opener-0.018
ppy-0.018
taker-0.017
Token saw
Token ID2497
Feature activation-2.49e-03

Pos logit contributions
ement+0.015
 mouths+0.014
 wrists+0.014
irling+0.014
irl+0.014
Neg logit contributions
izzy-0.018
enny-0.016
ppy-0.015
 opener-0.015
taker-0.015
Token clown
Token ID25573
Feature activation-3.58e-02

Pos logit contributions
ement+0.004
 mouths+0.004
 wrists+0.004
 soaring+0.003
 conversations+0.003
Neg logit contributions
izzy-0.005
enny-0.005
ppy-0.004
 opener-0.004
taker-0.004
Tokens
Token ID82
Feature activation-2.23e-02

Pos logit contributions
ement+0.066
 wrists+0.063
mm+0.063
irl+0.062
irling+0.062
Neg logit contributions
izzy-0.062
enny-0.053
ppy-0.053
 opener-0.051
ro-0.050
Token and
Token ID290
Feature activation-1.13e-02

Pos logit contributions
mm+0.049
ement+0.047
irling+0.047
 wrists+0.047
irl+0.046
Neg logit contributions
izzy-0.026
 opener-0.024
ro-0.024
guard-0.022
ed-0.021
Token ac
Token ID936
Feature activation-1.27e-02

Pos logit contributions
ement+0.018
 wrists+0.016
irling+0.016
 mouths+0.016
mm+0.016
Neg logit contributions
izzy-0.022
enny-0.020
ppy-0.019
 opener-0.019
taker-0.019
Tokenrob
Token ID22609
Feature activation-6.58e-02

Pos logit contributions
ement+0.013
 mouths+0.012
 wrists+0.012
irling+0.011
irl+0.011
Neg logit contributions
izzy-0.032
enny-0.029
ppy-0.029
 opener-0.029
taker-0.028
Tokenats
Token ID1381
Feature activation-1.32e-02

Pos logit contributions
 soaring+0.131
 difference+0.128
 amaz+0.123
 wrists+0.121
ement+0.120
Neg logit contributions
izzy-0.100
enny-0.088
ppy-0.086
ave-0.080
ives-0.077
Token and
Token ID290
Feature activation-1.15e-02

Pos logit contributions
ement+0.024
 wrists+0.023
 mouths+0.023
irling+0.023
mm+0.023
Neg logit contributions
izzy-0.023
enny-0.019
ppy-0.019
 opener-0.019
taker-0.019
Token lions
Token ID31420
Feature activation-2.49e-02

Pos logit contributions
ement+0.017
irling+0.016
irl+0.016
mm+0.016
 wrists+0.016
Neg logit contributions
izzy-0.024
enny-0.021
ppy-0.020
 opener-0.020
taker-0.020
Token and
Token ID290
Feature activation+2.62e-03

Pos logit contributions
ement+0.051
irl+0.050
mm+0.050
irling+0.050
 wrists+0.049
Neg logit contributions
izzy-0.035
ppy-0.030
 opener-0.030
ro-0.030
taker-0.028
Token elephants
Token ID25368
Feature activation-1.24e-02

Pos logit contributions
izzy+0.006
enny+0.005
ppy+0.005
 opener+0.005
taker+0.005
Neg logit contributions
ement-0.004
 mouths-0.004
 wrists-0.004
 soaring-0.003
irling-0.003
Token.
Token ID13
Feature activation-9.17e-03

Pos logit contributions
ement+0.013
 mouths+0.012
 wrists+0.012
 soaring+0.012
irling+0.012
Neg logit contributions
izzy-0.013
enny-0.011
ppy-0.011
 opener-0.011
taker-0.011
Token She
Token ID1375
Feature activation-4.46e-03

Pos logit contributions
ement+0.014
 wrists+0.013
irling+0.013
 mouths+0.013
 soaring+0.013
Neg logit contributions
izzy-0.019
enny-0.017
 opener-0.016
ppy-0.016
taker-0.016
Token hugs
Token ID40657
Feature activation-6.54e-03

Pos logit contributions
ement+0.006
 wrists+0.005
 mouths+0.005
irling+0.005
mm+0.005
Neg logit contributions
izzy-0.010
enny-0.009
ppy-0.009
 opener-0.009
taker-0.009
Token it
Token ID340
Feature activation-3.30e-03

Pos logit contributions
ement+0.008
 wrists+0.008
 mouths+0.008
 soaring+0.008
 conversations+0.007
Neg logit contributions
izzy-0.015
enny-0.014
 opener-0.013
taker-0.013
ppy-0.013
Token and
Token ID290
Feature activation-2.13e-02

Pos logit contributions
ement+0.006
 mouths+0.005
 wrists+0.005
irling+0.005
irl+0.005
Neg logit contributions
izzy-0.006
enny-0.005
ppy-0.005
 opener-0.005
taker-0.005
Token squee
Token ID13170
Feature activation-6.46e-02

Pos logit contributions
ement+0.035
irling+0.030
aman+0.029
 disagreement+0.028
mm+0.028
Neg logit contributions
izzy-0.040
taker-0.037
 opener-0.036
ppy-0.036
ro-0.035
Tokenzes
Token ID12271
Feature activation-2.03e-02

Pos logit contributions
 soaring+0.101
ement+0.098
 difference+0.093
 narrative+0.091
 best+0.088
Neg logit contributions
izzy-0.114
ppy-0.112
ro-0.107
ed-0.103
enny-0.100
Token it
Token ID340
Feature activation+8.48e-03

Pos logit contributions
ement+0.026
 mouths+0.025
 wrists+0.025
 soaring+0.024
irl+0.024
Neg logit contributions
izzy-0.046
enny-0.041
 opener-0.040
ppy-0.040
taker-0.040
Token tight
Token ID5381
Feature activation+1.57e-02

Pos logit contributions
izzy+0.015
enny+0.013
ppy+0.013
 opener+0.013
taker+0.013
Neg logit contributions
ement-0.015
 mouths-0.014
 wrists-0.014
mm-0.014
irling-0.014
Token.
Token ID13
Feature activation-9.64e-03

Pos logit contributions
izzy+0.025
enny+0.021
ppy+0.021
 opener+0.021
taker+0.021
Neg logit contributions
ement-0.030
 mouths-0.029
 wrists-0.029
irling-0.029
irl-0.029
Token She
Token ID1375
Feature activation-6.69e-03

Pos logit contributions
ement+0.018
irling+0.018
 soaring+0.017
irl+0.017
 wrists+0.017
Neg logit contributions
izzy-0.016
enny-0.014
 opener-0.013
ro-0.013
ppy-0.013
Token faces
Token ID6698
Feature activation-1.29e-02

Pos logit contributions
ement+0.059
irling+0.057
aman+0.056
 soaring+0.056
irl+0.055
Neg logit contributions
izzy-0.081
head-0.076
 opener-0.074
taker-0.073
washer-0.072
Token and
Token ID290
Feature activation-1.10e-02

Pos logit contributions
ement+0.022
 mouths+0.021
 wrists+0.021
irling+0.021
 soaring+0.021
Neg logit contributions
izzy-0.023
enny-0.020
ppy-0.020
 opener-0.020
taker-0.019
Token shapes
Token ID15268
Feature activation-1.44e-02

Pos logit contributions
ement+0.018
irling+0.016
mm+0.016
irl+0.016
 soaring+0.016
Neg logit contributions
izzy-0.021
 opener-0.020
taker-0.019
ro-0.019
ppy-0.019
Token with
Token ID351
Feature activation-2.21e-02

Pos logit contributions
ement+0.028
 wrists+0.027
 mouths+0.027
irling+0.026
irl+0.026
Neg logit contributions
izzy-0.023
 opener-0.019
enny-0.019
ppy-0.019
taker-0.019
Token the
Token ID262
Feature activation-3.46e-03

Pos logit contributions
irling+0.040
ement+0.040
irl+0.038
mm+0.038
 soaring+0.037
Neg logit contributions
izzy-0.035
 opener-0.032
taker-0.031
head-0.029
ppy-0.029
Token topp
Token ID23126
Feature activation-6.46e-02

Pos logit contributions
irling+0.005
ement+0.005
irl+0.005
 wrists+0.005
 soaring+0.005
Neg logit contributions
izzy-0.007
 opener-0.006
taker-0.006
ro-0.006
ppy-0.006
Tokenings
Token ID654
Feature activation+1.82e-02

Pos logit contributions
 soaring+0.099
ement+0.095
irling+0.093
 pic+0.091
 wrists+0.089
Neg logit contributions
izzy-0.126
ro-0.115
 opener-0.113
enny-0.111
ppy-0.111
Token.
Token ID13
Feature activation-9.95e-03

Pos logit contributions
izzy+0.034
enny+0.030
ppy+0.029
 opener+0.028
taker+0.028
Neg logit contributions
ement-0.031
 mouths-0.029
 wrists-0.029
mm-0.028
 soaring-0.027
Token
Token ID198
Feature activation+2.83e-03

Pos logit contributions
ement+0.018
 soaring+0.018
irling+0.017
 wrists+0.017
irl+0.017
Neg logit contributions
izzy-0.018
enny-0.015
 opener-0.015
ro-0.014
ppy-0.014
Token
Token ID198
Feature activation-1.11e-03

Pos logit contributions
izzy+0.005
enny+0.005
ppy+0.005
 opener+0.005
taker+0.005
Neg logit contributions
ement-0.005
 mouths-0.004
 wrists-0.004
irl-0.004
irling-0.004
Token"
Token ID1
Feature activation-1.52e-03

Pos logit contributions
ement+0.002
 mouths+0.002
 wrists+0.002
 soaring+0.002
mm+0.002
Neg logit contributions
izzy-0.002
enny-0.002
ppy-0.002
 opener-0.002
taker-0.002
Token the
Token ID262
Feature activation+4.28e-03

Pos logit contributions
ement+0.025
 mouths+0.024
 wrists+0.024
mm+0.024
irling+0.024
Neg logit contributions
izzy-0.031
enny-0.027
ppy-0.027
 opener-0.026
taker-0.026
Token race
Token ID3234
Feature activation-9.34e-04

Pos logit contributions
izzy+0.008
enny+0.007
ppy+0.007
 opener+0.007
taker+0.007
Neg logit contributions
ement-0.007
 mouths-0.007
 wrists-0.007
 soaring-0.007
 conversations-0.007
Token.
Token ID13
Feature activation-2.02e-03

Pos logit contributions
ement+0.002
 wrists+0.002
 mouths+0.002
 soaring+0.002
irling+0.001
Neg logit contributions
izzy-0.002
enny-0.001
ppy-0.001
 opener-0.001
taker-0.001
Token They
Token ID1119
Feature activation-1.07e-02

Pos logit contributions
ement+0.003
 mouths+0.003
 wrists+0.003
mm+0.003
 soaring+0.003
Neg logit contributions
izzy-0.004
enny-0.003
ppy-0.003
 opener-0.003
taker-0.003
Token all
Token ID477
Feature activation+6.02e-03

Pos logit contributions
ement+0.016
 mouths+0.015
 wrists+0.015
mm+0.015
irling+0.015
Neg logit contributions
izzy-0.022
enny-0.019
ppy-0.019
 opener-0.019
taker-0.019
Token lined
Token ID16566
Feature activation-6.45e-02

Pos logit contributions
izzy+0.012
enny+0.010
ppy+0.010
 opener+0.010
taker+0.010
Neg logit contributions
ement-0.010
 mouths-0.009
 wrists-0.009
irling-0.009
irl-0.009
Token up
Token ID510
Feature activation-3.57e-02

Pos logit contributions
ement+0.125
mm+0.124
 difference+0.120
 mouths+0.118
 conversations+0.117
Neg logit contributions
izzy-0.094
guard-0.080
taker-0.079
ed-0.079
 opener-0.079
Token at
Token ID379
Feature activation-2.16e-02

Pos logit contributions
mm+0.070
ement+0.069
 wrists+0.066
irling+0.065
irl+0.065
Neg logit contributions
izzy-0.052
ro-0.046
 opener-0.045
guard-0.044
enny-0.044
Token the
Token ID262
Feature activation+6.38e-03

Pos logit contributions
ement+0.042
mm+0.040
irling+0.040
 mouths+0.039
irl+0.038
Neg logit contributions
izzy-0.035
ppy-0.029
 opener-0.029
ro-0.029
enny-0.028
Token starting
Token ID3599
Feature activation+7.00e-03

Pos logit contributions
izzy+0.015
enny+0.013
ppy+0.013
 opener+0.012
taker+0.012
Neg logit contributions
 mouths-0.008
ement-0.008
 soaring-0.008
 wrists-0.008
 best-0.008
Token line
Token ID1627
Feature activation-7.32e-03

Pos logit contributions
izzy+0.018
enny+0.016
ppy+0.016
taker+0.015
 opener+0.015
Neg logit contributions
ement-0.007
 mouths-0.007
 wrists-0.007
 soaring-0.007
irl-0.007
Token the
Token ID262
Feature activation-2.53e-02

Pos logit contributions
ement+0.059
mm+0.055
 wrists+0.053
 mouths+0.053
irling+0.052
Neg logit contributions
izzy-0.034
 opener-0.027
head-0.025
enny-0.025
guard-0.025
Token sun
Token ID4252
Feature activation-3.40e-02

Pos logit contributions
ement+0.040
 wrists+0.038
mm+0.036
 mouths+0.035
irling+0.034
Neg logit contributions
izzy-0.052
enny-0.043
head-0.043
ro-0.043
 opener-0.043
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
irling+0.078
ement+0.078
heit+0.077
irl+0.075
 soaring+0.073
Neg logit contributions
izzy-0.041
ro-0.036
ppy-0.033
 opener-0.032
head-0.030
Token But
Token ID887
Feature activation-5.76e-03

Pos logit contributions
ement+0.019
irling+0.019
 soaring+0.019
 wrists+0.018
cking+0.017
Neg logit contributions
izzy-0.027
 opener-0.024
enny-0.023
ro-0.023
ppy-0.023
Token the
Token ID262
Feature activation-8.53e-03

Pos logit contributions
ement+0.013
irling+0.011
 wrists+0.011
 conversations+0.011
 soaring+0.011
Neg logit contributions
izzy-0.008
ppy-0.007
ro-0.007
ily-0.007
 opener-0.007
Token sun
Token ID4252
Feature activation-6.45e-02

Pos logit contributions
ement+0.014
irling+0.014
mm+0.014
 wrists+0.014
irl+0.013
Neg logit contributions
izzy-0.016
ro-0.013
taker-0.013
 opener-0.013
head-0.013
Token is
Token ID318
Feature activation-1.64e-02

Pos logit contributions
ement+0.105
 wrists+0.105
heit+0.104
 blonde+0.103
irling+0.102
Neg logit contributions
izzy-0.117
ro-0.101
guard-0.096
t-0.096
washer-0.095
Token very
Token ID845
Feature activation-3.66e-03

Pos logit contributions
ement+0.030
 wrists+0.029
mm+0.029
irling+0.027
 mouths+0.026
Neg logit contributions
izzy-0.028
 opener-0.025
t-0.024
taker-0.023
head-0.023
Token bright
Token ID6016
Feature activation+7.84e-03

Pos logit contributions
ement+0.006
 wrists+0.006
mm+0.006
 mouths+0.006
 conversations+0.006
Neg logit contributions
izzy-0.007
 opener-0.006
taker-0.006
ppy-0.006
ro-0.006
Token and
Token ID290
Feature activation-2.14e-02

Pos logit contributions
izzy+0.012
 opener+0.010
head+0.010
enny+0.010
ppy+0.010
Neg logit contributions
 wrists-0.015
irling-0.015
ement-0.015
irl-0.015
 mouths-0.015
Token hurts
Token ID20406
Feature activation+8.30e-03

Pos logit contributions
ement+0.047
irling+0.044
 conversations+0.043
 wrists+0.042
aman+0.041
Neg logit contributions
izzy-0.027
head-0.025
taker-0.022
 opener-0.021
guard-0.021
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
izzy+0.001
enny+0.001
ppy+0.001
taker+0.001
 opener+0.001
Neg logit contributions
ement-0.001
 mouths-0.001
 wrists-0.001
 soaring-0.001
irling-0.001
Token They
Token ID1119
Feature activation+1.58e-03

Pos logit contributions
ement+0.022
 soaring+0.022
irling+0.022
irl+0.021
 wrists+0.021
Neg logit contributions
izzy-0.016
enny-0.014
 opener-0.013
ppy-0.013
ro-0.013
Token put
Token ID1234
Feature activation-3.11e-02

Pos logit contributions
izzy+0.003
enny+0.003
 opener+0.003
taker+0.003
ppy+0.003
Neg logit contributions
 wrists-0.002
 mouths-0.002
ement-0.002
irl-0.002
irling-0.002
Token on
Token ID319
Feature activation-2.88e-02

Pos logit contributions
ement+0.048
irling+0.047
mm+0.045
 soaring+0.044
 wrists+0.043
Neg logit contributions
izzy-0.063
 opener-0.055
ppy-0.054
taker-0.053
ro-0.053
Token their
Token ID511
Feature activation+4.49e-04

Pos logit contributions
ement+0.056
mm+0.052
opl+0.052
irling+0.051
 difference+0.051
Neg logit contributions
izzy-0.042
ro-0.039
 opener-0.038
head-0.036
ppy-0.034
Token apr
Token ID46593
Feature activation-6.38e-02

Pos logit contributions
izzy+0.001
ppy+0.001
ro+0.001
 opener+0.001
enny+0.001
Neg logit contributions
ement-0.001
mm-0.001
irling-0.001
 soaring-0.001
aman-0.001
Tokenons
Token ID684
Feature activation-1.63e-02

Pos logit contributions
 soaring+0.099
 sincere+0.098
 wrists+0.094
 mouths+0.093
ement+0.091
Neg logit contributions
izzy-0.127
enny-0.111
 opener-0.110
washer-0.105
up-0.105
Token and
Token ID290
Feature activation-1.70e-02

Pos logit contributions
ement+0.026
 wrists+0.025
 mouths+0.025
 soaring+0.024
irling+0.024
Neg logit contributions
izzy-0.032
enny-0.028
ppy-0.027
taker-0.027
 opener-0.027
Token sat
Token ID3332
Feature activation-2.27e-02

Pos logit contributions
ement+0.028
irling+0.026
 wrists+0.025
mm+0.025
 mouths+0.025
Neg logit contributions
izzy-0.033
enny-0.029
ppy-0.028
 opener-0.028
taker-0.028
Token on
Token ID319
Feature activation-1.25e-02

Pos logit contributions
ement+0.040
 mouths+0.038
 wrists+0.038
mm+0.038
irling+0.038
Neg logit contributions
izzy-0.040
enny-0.033
ppy-0.033
 opener-0.033
taker-0.033
Token the
Token ID262
Feature activation+6.60e-03

Pos logit contributions
ement+0.029
irling+0.028
mm+0.028
 soaring+0.027
heit+0.027
Neg logit contributions
izzy-0.012
 opener-0.012
ro-0.011
head-0.011
ily-0.009
Token and
Token ID290
Feature activation-1.43e-02

Pos logit contributions
izzy+0.028
enny+0.024
taker+0.024
ppy+0.024
 opener+0.023
Neg logit contributions
ement-0.023
 wrists-0.022
 mouths-0.022
irling-0.021
irl-0.021
Token Tom
Token ID4186
Feature activation-8.57e-05

Pos logit contributions
ement+0.029
irling+0.029
irl+0.028
 soaring+0.028
 conversations+0.027
Neg logit contributions
izzy-0.021
enny-0.018
ppy-0.017
ro-0.017
 opener-0.017
Token put
Token ID1234
Feature activation-3.14e-02

Pos logit contributions
ement+0.000
irling+0.000
 soaring+0.000
irl+0.000
mm+0.000
Neg logit contributions
izzy-0.000
ppy-0.000
enny-0.000
 opener-0.000
taker-0.000
Token on
Token ID319
Feature activation-2.11e-02

Pos logit contributions
ement+0.056
irling+0.055
 soaring+0.054
 wrists+0.054
irl+0.053
Neg logit contributions
izzy-0.055
 opener-0.046
enny-0.046
ppy-0.046
taker-0.045
Token their
Token ID511
Feature activation-1.45e-02

Pos logit contributions
ement+0.039
irling+0.039
 soaring+0.038
mm+0.036
opl+0.036
Neg logit contributions
izzy-0.032
 opener-0.029
ro-0.029
head-0.028
ppy-0.026
Token apr
Token ID46593
Feature activation-6.38e-02

Pos logit contributions
ement+0.023
 soaring+0.023
irling+0.023
opl+0.021
mm+0.021
Neg logit contributions
izzy-0.025
 opener-0.023
ily-0.022
washer-0.022
ro-0.022
Tokenons
Token ID684
Feature activation-1.02e-02

Pos logit contributions
 soaring+0.101
 wrists+0.089
 sincere+0.089
 mouths+0.088
 difference+0.086
Neg logit contributions
izzy-0.127
 opener-0.113
enny-0.112
washer-0.108
up-0.107
Token and
Token ID290
Feature activation-1.97e-02

Pos logit contributions
ement+0.018
 mouths+0.017
 wrists+0.017
irling+0.017
 soaring+0.017
Neg logit contributions
izzy-0.018
enny-0.016
ppy-0.015
 opener-0.015
taker-0.015
Token washed
Token ID18989
Feature activation-2.31e-02

Pos logit contributions
ement+0.034
irling+0.031
 soaring+0.031
irl+0.031
mm+0.031
Neg logit contributions
izzy-0.036
ppy-0.031
 opener-0.031
enny-0.031
ro-0.030
Token their
Token ID511
Feature activation-2.12e-02

Pos logit contributions
ement+0.034
irling+0.033
 soaring+0.033
 wrists+0.032
mm+0.032
Neg logit contributions
izzy-0.047
enny-0.041
ppy-0.041
 opener-0.041
taker-0.040
Token hands
Token ID2832
Feature activation-1.12e-02

Pos logit contributions
 soaring+0.031
irling+0.031
ement+0.030
irl+0.028
mm+0.027
Neg logit contributions
izzy-0.042
ro-0.039
 opener-0.037
ppy-0.036
taker-0.036
Token She
Token ID1375
Feature activation+1.78e-02

Pos logit contributions
ement+0.015
 wrists+0.014
 mouths+0.014
 blonde+0.013
 conversations+0.013
Neg logit contributions
izzy-0.020
ppy-0.018
taker-0.017
guard-0.017
 opener-0.017
Token took
Token ID1718
Feature activation+3.05e-03

Pos logit contributions
izzy+0.034
enny+0.030
taker+0.030
 opener+0.030
ppy+0.029
Neg logit contributions
irl-0.027
 wrists-0.027
ement-0.027
 mouths-0.026
irling-0.026
Token a
Token ID257
Feature activation+2.42e-02

Pos logit contributions
izzy+0.006
enny+0.006
ppy+0.006
 opener+0.006
taker+0.005
Neg logit contributions
ement-0.004
irl-0.004
 wrists-0.004
 mouths-0.004
 soaring-0.004
Token bottle
Token ID9294
Feature activation+1.37e-02

Pos logit contributions
izzy+0.050
enny+0.044
ppy+0.044
taker+0.043
ro+0.042
Neg logit contributions
ement-0.034
irl-0.033
 soaring-0.033
 mouths-0.033
 wrists-0.033
Token of
Token ID286
Feature activation+6.07e-03

Pos logit contributions
izzy+0.022
ppy+0.019
eware+0.019
rex+0.018
enny+0.018
Neg logit contributions
 soaring-0.022
 best-0.021
ement-0.021
irl-0.020
 course-0.020
Token lot
Token ID1256
Feature activation+4.46e-02

Pos logit contributions
izzy+0.012
enny+0.011
 opener+0.011
ppy+0.011
taker+0.010
Neg logit contributions
ement-0.009
 wrists-0.009
 mouths-0.009
irling-0.009
mm-0.009
Tokenion
Token ID295
Feature activation+9.06e-03

Pos logit contributions
izzy+0.070
ppy+0.065
eware+0.065
rex+0.063
ive+0.060
Neg logit contributions
ement-0.078
 course-0.071
irl-0.069
irling-0.068
 best-0.066
Token and
Token ID290
Feature activation+1.53e-03

Pos logit contributions
izzy+0.017
enny+0.015
ppy+0.014
taker+0.014
rex+0.014
Neg logit contributions
ement-0.015
 wrists-0.014
 mouths-0.014
 soaring-0.014
 best-0.013
Token went
Token ID1816
Feature activation+2.18e-02

Pos logit contributions
izzy+0.003
enny+0.003
taker+0.002
 opener+0.002
ppy+0.002
Neg logit contributions
 wrists-0.002
 mouths-0.002
irl-0.002
irling-0.002
 pic-0.002
Token to
Token ID284
Feature activation+1.24e-02

Pos logit contributions
izzy+0.033
ppy+0.028
enny+0.027
taker+0.026
head+0.026
Neg logit contributions
 soaring-0.044
irl-0.042
irling-0.042
 wrists-0.042
 conversations-0.042
Token her
Token ID607
Feature activation-3.23e-04

Pos logit contributions
izzy+0.024
enny+0.021
ppy+0.021
taker+0.020
 opener+0.020
Neg logit contributions
ement-0.020
 wrists-0.019
irl-0.019
 mouths-0.019
 soaring-0.019
Token be
Token ID307
Feature activation+6.65e-03

Pos logit contributions
 soaring+0.015
 mouths+0.015
ement+0.015
irl+0.015
 wrists+0.014
Neg logit contributions
izzy-0.024
enny-0.022
taker-0.021
ppy-0.021
 opener-0.020
Token dangerous
Token ID4923
Feature activation+1.93e-02

Pos logit contributions
izzy+0.013
ppy+0.011
 opener+0.011
enny+0.011
taker+0.011
Neg logit contributions
ement-0.011
 wrists-0.010
mm-0.010
 mouths-0.010
irling-0.010
Token."
Token ID526
Feature activation+2.90e-03

Pos logit contributions
izzy+0.042
enny+0.038
 opener+0.034
taker+0.034
ppy+0.033
Neg logit contributions
 soaring-0.027
ement-0.027
 conversations-0.026
 best-0.026
 mouths-0.026
Token
Token ID198
Feature activation+5.86e-03

Pos logit contributions
izzy+0.007
ppy+0.006
enny+0.006
taker+0.006
guard+0.006
Neg logit contributions
ement-0.003
mm-0.003
 mouths-0.003
 pic-0.003
irl-0.003
Token
Token ID198
Feature activation+9.48e-03

Pos logit contributions
izzy+0.013
ppy+0.012
enny+0.011
taker+0.011
ro+0.011
Neg logit contributions
ement-0.007
irl-0.007
mm-0.007
irling-0.007
 mouths-0.007
TokenL
Token ID43
Feature activation+4.48e-02

Pos logit contributions
izzy+0.022
taker+0.019
enny+0.019
ppy+0.018
 opener+0.018
Neg logit contributions
irling-0.011
irl-0.011
 wrists-0.011
mm-0.011
ement-0.011
Tokenily
Token ID813
Feature activation+1.03e-02

Pos logit contributions
eware+0.047
izzy+0.045
bel+0.045
unny+0.044
washer+0.044
Neg logit contributions
ement-0.100
mm-0.096
 course-0.092
irl-0.092
 narrative-0.090
Token did
Token ID750
Feature activation-2.22e-02

Pos logit contributions
izzy+0.021
enny+0.018
 opener+0.018
ppy+0.018
taker+0.018
Neg logit contributions
ement-0.016
 wrists-0.015
 mouths-0.015
irling-0.014
irl-0.014
Token not
Token ID407
Feature activation+2.08e-02

Pos logit contributions
ement+0.034
 wrists+0.033
 mouths+0.032
 conversations+0.031
irling+0.031
Neg logit contributions
izzy-0.044
 opener-0.039
ppy-0.038
taker-0.038
enny-0.038
Token listen
Token ID6004
Feature activation-1.05e-02

Pos logit contributions
izzy+0.045
enny+0.044
washer+0.041
taker+0.038
head+0.037
Neg logit contributions
irl-0.025
 difference-0.023
 best-0.022
 soaring-0.022
 conversations-0.022
Token.
Token ID13
Feature activation+1.67e-02

Pos logit contributions
ement+0.021
 mouths+0.020
 wrists+0.020
 conversations+0.019
irling+0.019
Neg logit contributions
izzy-0.017
enny-0.014
ppy-0.013
 opener-0.013
taker-0.013
Token Tim
Token ID5045
Feature activation-9.30e-03

Pos logit contributions
ement+0.007
irling+0.007
 wrists+0.007
irl+0.007
 mouths+0.007
Neg logit contributions
izzy-0.008
enny-0.007
 opener-0.007
ro-0.007
taker-0.007
Tokenmy
Token ID1820
Feature activation+2.20e-03

Pos logit contributions
ement+0.015
 wrists+0.015
 mouths+0.015
irling+0.014
mm+0.014
Neg logit contributions
izzy-0.018
enny-0.016
ppy-0.015
 opener-0.015
taker-0.015
Token felt
Token ID2936
Feature activation+1.26e-02

Pos logit contributions
izzy+0.004
enny+0.004
ppy+0.003
 opener+0.003
taker+0.003
Neg logit contributions
ement-0.004
 wrists-0.004
 mouths-0.004
mm-0.004
 soaring-0.004
Token sad
Token ID6507
Feature activation+1.84e-02

Pos logit contributions
izzy+0.028
enny+0.025
ppy+0.025
 opener+0.024
taker+0.024
Neg logit contributions
ement-0.017
 mouths-0.016
 wrists-0.016
 soaring-0.016
irling-0.016
Token and
Token ID290
Feature activation-1.19e-03

Pos logit contributions
izzy+0.036
enny+0.031
ppy+0.031
 opener+0.030
taker+0.030
Neg logit contributions
ement-0.030
 mouths-0.028
mm-0.027
 soaring-0.027
 wrists-0.027
Token cried
Token ID16896
Feature activation+4.10e-02

Pos logit contributions
ement+0.002
 mouths+0.002
 wrists+0.002
irling+0.002
 soaring+0.002
Neg logit contributions
izzy-0.002
enny-0.002
 opener-0.002
ppy-0.002
taker-0.002
Token a
Token ID257
Feature activation+1.22e-02

Pos logit contributions
izzy+0.083
enny+0.073
guard+0.071
ro+0.069
ppy+0.069
Neg logit contributions
ement-0.062
 mouths-0.061
 soaring-0.058
 best-0.057
 conversations-0.057
Token little
Token ID1310
Feature activation+2.33e-02

Pos logit contributions
izzy+0.033
enny+0.030
ppy+0.029
 opener+0.029
taker+0.029
Neg logit contributions
ement-0.010
 mouths-0.009
 wrists-0.009
 soaring-0.009
irling-0.009
Token bit
Token ID1643
Feature activation+3.09e-02

Pos logit contributions
izzy+0.038
enny+0.032
ppy+0.031
 opener+0.031
taker+0.030
Neg logit contributions
ement-0.045
 mouths-0.044
 wrists-0.043
 soaring-0.042
irling-0.042
Token.
Token ID13
Feature activation-5.13e-03

Pos logit contributions
izzy+0.064
enny+0.057
 opener+0.055
ro+0.055
taker+0.053
Neg logit contributions
ement-0.045
 mouths-0.042
 disagreement-0.040
 best-0.039
 conversations-0.039
Token
Token ID220
Feature activation+1.52e-02

Pos logit contributions
ement+0.008
irling+0.008
 wrists+0.008
irl+0.008
 soaring+0.008
Neg logit contributions
izzy-0.010
enny-0.009
 opener-0.009
ro-0.008
taker-0.008
Token was
Token ID373
Feature activation+1.53e-03

Pos logit contributions
 wrists+0.047
ement+0.045
irling+0.044
 mouths+0.044
 soaring+0.043
Neg logit contributions
izzy-0.039
enny-0.033
 opener-0.031
ily-0.030
ro-0.030
Token a
Token ID257
Feature activation-2.73e-03

Pos logit contributions
izzy+0.002
enny+0.002
ppy+0.002
 opener+0.002
taker+0.002
Neg logit contributions
ement-0.003
 wrists-0.003
 mouths-0.003
irling-0.003
irl-0.003
Token cute
Token ID13779
Feature activation+2.70e-03

Pos logit contributions
ement+0.005
 mouths+0.005
 wrists+0.005
irling+0.005
irl+0.005
Neg logit contributions
izzy-0.005
enny-0.004
ppy-0.004
 opener-0.004
taker-0.004
Token little
Token ID1310
Feature activation+1.01e-03

Pos logit contributions
izzy+0.005
enny+0.004
 opener+0.004
taker+0.004
ppy+0.004
Neg logit contributions
ement-0.004
 mouths-0.004
 wrists-0.004
 pic-0.004
mm-0.004
Token girl
Token ID2576
Feature activation+9.20e-03

Pos logit contributions
izzy+0.002
enny+0.001
 opener+0.001
ppy+0.001
taker+0.001
Neg logit contributions
ement-0.002
 mouths-0.002
 wrists-0.002
mm-0.002
 soaring-0.002
Token named
Token ID3706
Feature activation+4.13e-02

Pos logit contributions
izzy+0.018
enny+0.016
 opener+0.015
ppy+0.015
taker+0.015
Neg logit contributions
ement-0.015
 mouths-0.014
 wrists-0.014
irling-0.014
irl-0.014
Token Lily
Token ID20037
Feature activation+2.24e-02

Pos logit contributions
izzy+0.060
enny+0.050
 opener+0.049
taker+0.049
ppy+0.048
Neg logit contributions
ement-0.085
 wrists-0.083
 mouths-0.083
mm-0.082
irl-0.081
Token.
Token ID13
Feature activation+9.81e-03

Pos logit contributions
izzy+0.040
enny+0.034
 opener+0.034
taker+0.033
ppy+0.033
Neg logit contributions
ement-0.039
 wrists-0.038
 mouths-0.038
 soaring-0.037
irling-0.037
Token She
Token ID1375
Feature activation+9.32e-03

Pos logit contributions
izzy+0.015
enny+0.013
 opener+0.012
ppy+0.012
ro+0.012
Neg logit contributions
ement-0.020
irling-0.020
 wrists-0.019
 mouths-0.019
 soaring-0.019
Token had
Token ID550
Feature activation+4.09e-03

Pos logit contributions
izzy+0.021
enny+0.019
 opener+0.019
ppy+0.019
taker+0.019
Neg logit contributions
ement-0.011
 mouths-0.011
 wrists-0.011
irl-0.011
irling-0.011
Token a
Token ID257
Feature activation-1.45e-02

Pos logit contributions
izzy+0.006
enny+0.005
ppy+0.005
ily+0.005
head+0.005
Neg logit contributions
ement-0.009
irling-0.008
mm-0.008
 mouths-0.008
irl-0.008
TokenFl
Token ID7414
Feature activation-6.58e-03

Pos logit contributions
ement+0.001
 wrists+0.001
irling+0.001
 mouths+0.001
irl+0.001
Neg logit contributions
izzy-0.001
enny-0.001
taker-0.001
 opener-0.001
ppy-0.001
Tokenuffy
Token ID15352
Feature activation+3.09e-03

Pos logit contributions
ement+0.009
 wrists+0.009
 mouths+0.009
 soaring+0.009
irling+0.009
Neg logit contributions
izzy-0.014
enny-0.013
ppy-0.012
 opener-0.012
taker-0.012
Token just
Token ID655
Feature activation+2.40e-03

Pos logit contributions
izzy+0.006
enny+0.005
ppy+0.005
 opener+0.005
taker+0.005
Neg logit contributions
ement-0.005
 mouths-0.005
mm-0.005
 wrists-0.005
irling-0.005
Token shrugged
Token ID28271
Feature activation-1.85e-06

Pos logit contributions
izzy+0.005
ppy+0.004
enny+0.004
 opener+0.004
taker+0.004
Neg logit contributions
ement-0.004
 pic-0.004
irling-0.004
irl-0.004
mm-0.004
Token and
Token ID290
Feature activation+1.07e-02

Feature not active on prev token;
no predictions were affected.
Token l
Token ID300
Feature activation+3.86e-02

Pos logit contributions
izzy+0.021
enny+0.019
 opener+0.018
ppy+0.018
taker+0.018
Neg logit contributions
ement-0.017
 wrists-0.016
 mouths-0.016
mm-0.016
irl-0.016
Tokenicked
Token ID9484
Feature activation-1.90e-02

Pos logit contributions
izzy+0.058
enny+0.049
 opener+0.048
ppy+0.047
taker+0.047
Neg logit contributions
ement-0.079
 mouths-0.075
 wrists-0.075
irling-0.074
irl-0.074
Token his
Token ID465
Feature activation-1.63e-02

Pos logit contributions
ement+0.026
 mouths+0.025
 wrists+0.025
irl+0.024
mm+0.024
Neg logit contributions
izzy-0.041
enny-0.037
 opener-0.036
taker-0.036
ppy-0.036
Token paw
Token ID41827
Feature activation-7.74e-03

Pos logit contributions
ement+0.025
irling+0.025
mm+0.024
irl+0.024
 pic+0.024
Neg logit contributions
izzy-0.032
ppy-0.029
ro-0.028
 opener-0.028
taker-0.028
Token.
Token ID13
Feature activation+1.53e-02

Pos logit contributions
ement+0.014
 mouths+0.013
 wrists+0.013
 soaring+0.013
irling+0.013
Neg logit contributions
izzy-0.014
enny-0.012
ppy-0.011
 opener-0.011
taker-0.011
Token Lily
Token ID20037
Feature activation+2.81e-03

Pos logit contributions
izzy+0.030
enny+0.026
ppy+0.025
 opener+0.025
taker+0.025
Neg logit contributions
ement-0.024
 mouths-0.024
 wrists-0.024
mm-0.023
 soaring-0.023
Token listen
Token ID6004
Feature activation-5.97e-03

Pos logit contributions
izzy+0.010
enny+0.009
 opener+0.008
ppy+0.008
taker+0.008
Neg logit contributions
ement-0.009
 mouths-0.008
mm-0.008
 wrists-0.008
irling-0.008
Token to
Token ID284
Feature activation-1.79e-02

Pos logit contributions
ement+0.013
 mouths+0.013
 wrists+0.013
irling+0.012
 soaring+0.012
Neg logit contributions
izzy-0.008
 opener-0.006
enny-0.006
ppy-0.006
taker-0.006
Token her
Token ID607
Feature activation+1.01e-02

Pos logit contributions
ement+0.033
mm+0.030
 mouths+0.029
irling+0.029
 wrists+0.029
Neg logit contributions
izzy-0.031
ppy-0.027
enny-0.027
taker-0.027
 opener-0.026
Token mom
Token ID1995
Feature activation-1.19e-02

Pos logit contributions
izzy+0.018
enny+0.016
 opener+0.016
ppy+0.016
taker+0.015
Neg logit contributions
ement-0.018
irling-0.016
 wrists-0.016
 mouths-0.016
 soaring-0.016
Token's
Token ID338
Feature activation-3.64e-03

Pos logit contributions
ement+0.024
irling+0.023
irl+0.023
 wrists+0.023
 mouths+0.023
Neg logit contributions
izzy-0.018
ppy-0.016
enny-0.015
 opener-0.015
taker-0.014
Token recommendations
Token ID10763
Feature activation+1.73e-02

Pos logit contributions
ement+0.007
mm+0.006
irling+0.006
 mouths+0.006
 wrists+0.006
Neg logit contributions
izzy-0.006
enny-0.005
 opener-0.005
taker-0.005
ro-0.005
Token.
Token ID13
Feature activation-1.82e-02

Pos logit contributions
izzy+0.031
enny+0.027
ppy+0.026
 opener+0.026
taker+0.025
Neg logit contributions
ement-0.030
 mouths-0.028
 wrists-0.028
 soaring-0.028
mm-0.027
Token
Token ID198
Feature activation-1.85e-02

Pos logit contributions
ement+0.030
 wrists+0.029
irling+0.029
irl+0.029
 mouths+0.029
Neg logit contributions
izzy-0.035
enny-0.031
 opener-0.029
taker-0.029
ppy-0.029
Token
Token ID198
Feature activation-1.54e-02

Pos logit contributions
ement+0.026
 wrists+0.025
 mouths+0.025
irling+0.024
 soaring+0.024
Neg logit contributions
izzy-0.040
enny-0.035
 opener-0.034
ppy-0.034
taker-0.034
TokenFrom
Token ID4863
Feature activation+1.43e-02

Pos logit contributions
ement+0.023
 mouths+0.023
 wrists+0.022
 soaring+0.021
irling+0.021
Neg logit contributions
izzy-0.032
enny-0.028
 opener-0.027
ppy-0.027
taker-0.027
Token that
Token ID326
Feature activation-1.93e-02

Pos logit contributions
izzy+0.023
enny+0.020
ppy+0.019
 opener+0.019
taker+0.019
Neg logit contributions
ement-0.028
 wrists-0.026
 mouths-0.026
irling-0.026
irl-0.026
Token
Token ID198
Feature activation-3.39e-03

Pos logit contributions
ement+0.001
irling+0.001
irl+0.001
 conversations+0.000
mm+0.000
Neg logit contributions
izzy-0.001
ppy-0.001
ro-0.001
taker-0.001
 opener-0.001
TokenJ
Token ID41
Feature activation+1.77e-02

Pos logit contributions
ement+0.006
irling+0.006
irl+0.006
 conversations+0.006
mm+0.005
Neg logit contributions
izzy-0.006
ppy-0.005
ro-0.005
 opener-0.005
taker-0.005
Tokenill
Token ID359
Feature activation+1.91e-02

Pos logit contributions
 opener+0.023
izzy+0.022
guard+0.021
head+0.021
taker+0.020
Neg logit contributions
ement-0.038
mm-0.033
aman-0.032
irling-0.032
 soaring-0.032
Token felt
Token ID2936
Feature activation+1.68e-02

Pos logit contributions
izzy+0.036
enny+0.032
 opener+0.031
taker+0.031
ppy+0.030
Neg logit contributions
ement-0.031
 wrists-0.030
 mouths-0.030
irling-0.029
irl-0.029
Token like
Token ID588
Feature activation+2.09e-02

Pos logit contributions
izzy+0.036
enny+0.033
ppy+0.032
 opener+0.031
ro+0.031
Neg logit contributions
ement-0.024
 soaring-0.022
 mouths-0.022
irling-0.022
irl-0.022
Token she
Token ID673
Feature activation+1.37e-02

Pos logit contributions
izzy+0.039
enny+0.033
ppy+0.033
 opener+0.033
taker+0.032
Neg logit contributions
ement-0.035
 soaring-0.034
 mouths-0.034
 wrists-0.034
irling-0.033
Token was
Token ID373
Feature activation+1.48e-02

Pos logit contributions
izzy+0.028
enny+0.024
 opener+0.024
taker+0.024
ppy+0.024
Neg logit contributions
ement-0.021
 mouths-0.020
 wrists-0.020
irling-0.019
 soaring-0.019
Token getting
Token ID1972
Feature activation+1.03e-02

Pos logit contributions
izzy+0.034
enny+0.030
 opener+0.030
ppy+0.029
taker+0.029
Neg logit contributions
ement-0.019
 soaring-0.018
irling-0.018
 wrists-0.018
 mouths-0.018
Token nowhere
Token ID12062
Feature activation+1.54e-02

Pos logit contributions
izzy+0.023
enny+0.021
ppy+0.020
ro+0.020
 opener+0.019
Neg logit contributions
 soaring-0.014
ement-0.013
 mouths-0.013
 best-0.013
irling-0.013
Token.
Token ID13
Feature activation+3.77e-03

Pos logit contributions
izzy+0.022
ppy+0.018
taker+0.018
enny+0.018
ro+0.017
Neg logit contributions
 soaring-0.032
ement-0.031
irling-0.030
 conversations-0.030
 pic-0.030
Token Then
Token ID3244
Feature activation-6.56e-03

Pos logit contributions
izzy+0.007
ppy+0.006
enny+0.006
 opener+0.006
taker+0.006
Neg logit contributions
ement-0.006
 mouths-0.006
 wrists-0.006
mm-0.006
 soaring-0.006
Token,
Token ID11
Feature activation+2.07e-04

Pos logit contributions
ement+0.041
 mouths+0.039
 wrists+0.039
irl+0.038
mm+0.038
Neg logit contributions
izzy-0.059
enny-0.052
 opener-0.052
taker-0.051
ppy-0.051
Token my
Token ID616
Feature activation+1.90e-04

Pos logit contributions
izzy+0.000
enny+0.000
ppy+0.000
 opener+0.000
taker+0.000
Neg logit contributions
ement-0.000
 mouths-0.000
 wrists-0.000
mm-0.000
irl-0.000
Token boat
Token ID8848
Feature activation-4.44e-02

Pos logit contributions
izzy+0.000
enny+0.000
ppy+0.000
 opener+0.000
taker+0.000
Neg logit contributions
ement-0.000
 mouths-0.000
 wrists-0.000
irling-0.000
irl-0.000
Token is
Token ID318
Feature activation-7.01e-03

Pos logit contributions
ement+0.054
 wrists+0.051
 mouths+0.051
irling+0.050
mm+0.049
Neg logit contributions
izzy-0.103
enny-0.091
ppy-0.090
 opener-0.090
taker-0.089
Token going
Token ID1016
Feature activation+3.96e-03

Pos logit contributions
ement+0.011
 mouths+0.010
 wrists+0.010
mm+0.010
irling+0.010
Neg logit contributions
izzy-0.014
 opener-0.012
taker-0.012
ppy-0.012
enny-0.012
Token to
Token ID284
Feature activation+1.02e-02

Pos logit contributions
izzy+0.006
enny+0.005
ppy+0.005
taker+0.005
 opener+0.005
Neg logit contributions
ement-0.008
 soaring-0.008
 mouths-0.007
 wrists-0.007
irl-0.007
Token China
Token ID2807
Feature activation+8.31e-03

Pos logit contributions
izzy+0.021
enny+0.018
ppy+0.018
taker+0.018
 opener+0.017
Neg logit contributions
ement-0.015
 mouths-0.015
 wrists-0.015
 soaring-0.015
irl-0.015
Token!"
Token ID2474
Feature activation+1.36e-03

Pos logit contributions
izzy+0.015
enny+0.013
ppy+0.012
taker+0.012
 opener+0.012
Neg logit contributions
ement-0.015
 wrists-0.014
 soaring-0.014
irl-0.014
 mouths-0.014
Token Ben
Token ID3932
Feature activation+1.39e-02

Pos logit contributions
izzy+0.002
enny+0.002
ppy+0.002
 opener+0.002
taker+0.002
Neg logit contributions
ement-0.002
 mouths-0.002
 wrists-0.002
irl-0.002
mm-0.002
Token said
Token ID531
Feature activation+9.30e-03

Pos logit contributions
izzy+0.030
enny+0.026
taker+0.026
ppy+0.025
head+0.025
Neg logit contributions
 wrists-0.019
ement-0.019
 mouths-0.018
 conversations-0.017
 soaring-0.017
Token.
Token ID13
Feature activation+3.60e-02

Pos logit contributions
izzy+0.019
enny+0.016
ppy+0.016
 opener+0.015
head+0.015
Neg logit contributions
ement-0.014
 mouths-0.013
 wrists-0.013
 soaring-0.013
 conversations-0.013
Token,
Token ID11
Feature activation+6.64e-03

Pos logit contributions
 wrists+0.036
ement+0.034
 mouths+0.034
irling+0.033
irl+0.033
Neg logit contributions
izzy-0.035
enny-0.031
ppy-0.028
 opener-0.028
taker-0.027
Token there
Token ID612
Feature activation-2.68e-02

Pos logit contributions
izzy+0.011
enny+0.009
ppy+0.009
 opener+0.009
taker+0.009
Neg logit contributions
ement-0.013
 wrists-0.013
 mouths-0.012
irling-0.012
 conversations-0.012
Token was
Token ID373
Feature activation-6.73e-04

Pos logit contributions
 wrists+0.059
irling+0.056
ement+0.056
 mouths+0.055
 soaring+0.054
Neg logit contributions
izzy-0.040
enny-0.032
 opener-0.030
ily-0.029
t-0.029
Token a
Token ID257
Feature activation-7.90e-04

Pos logit contributions
ement+0.001
 wrists+0.001
 mouths+0.001
irling+0.001
irl+0.001
Neg logit contributions
izzy-0.001
enny-0.001
 opener-0.001
ily-0.001
ppy-0.001
Token little
Token ID1310
Feature activation+1.64e-03

Pos logit contributions
ement+0.001
 mouths+0.001
 wrists+0.001
irling+0.001
irl+0.001
Neg logit contributions
izzy-0.001
enny-0.001
ppy-0.001
 opener-0.001
taker-0.001
Token girl
Token ID2576
Feature activation+1.07e-02

Pos logit contributions
izzy+0.003
enny+0.002
 opener+0.002
ppy+0.002
taker+0.002
Neg logit contributions
ement-0.003
 mouths-0.003
 wrists-0.003
 soaring-0.003
mm-0.003
Token named
Token ID3706
Feature activation+4.54e-02

Pos logit contributions
izzy+0.022
enny+0.019
 opener+0.019
taker+0.019
ppy+0.019
Neg logit contributions
ement-0.015
 wrists-0.015
 mouths-0.015
irling-0.015
irl-0.015
Token Lily
Token ID20037
Feature activation+2.28e-02

Pos logit contributions
izzy+0.074
taker+0.066
 opener+0.065
guard+0.065
enny+0.064
Neg logit contributions
 wrists-0.078
 mouths-0.078
mm-0.078
 pic-0.077
ement-0.076
Token.
Token ID13
Feature activation+1.12e-02

Pos logit contributions
izzy+0.039
enny+0.034
 opener+0.033
ppy+0.033
taker+0.032
Neg logit contributions
ement-0.041
 wrists-0.040
 mouths-0.040
irling-0.039
 soaring-0.039
Token She
Token ID1375
Feature activation+9.84e-03

Pos logit contributions
izzy+0.020
enny+0.017
ppy+0.016
 opener+0.016
taker+0.016
Neg logit contributions
ement-0.020
 mouths-0.020
 wrists-0.020
mm-0.019
irling-0.019
Token loved
Token ID6151
Feature activation+1.88e-03

Pos logit contributions
izzy+0.023
enny+0.021
 opener+0.021
ppy+0.020
taker+0.020
Neg logit contributions
irl-0.011
ement-0.011
irling-0.011
 mouths-0.011
 wrists-0.011
Token,"
Token ID553
Feature activation-1.56e-03

Pos logit contributions
izzy+0.010
enny+0.008
ppy+0.008
 opener+0.008
taker+0.008
Neg logit contributions
ement-0.012
 mouths-0.011
 wrists-0.011
irling-0.011
irl-0.011
Token Lily
Token ID20037
Feature activation+3.18e-02

Pos logit contributions
ement+0.003
 mouths+0.003
 wrists+0.003
mm+0.003
 soaring+0.003
Neg logit contributions
izzy-0.003
ppy-0.002
enny-0.002
ro-0.002
 opener-0.002
Token said
Token ID531
Feature activation+8.20e-03

Pos logit contributions
izzy+0.073
eware+0.063
enny+0.063
taker+0.062
 opener+0.062
Neg logit contributions
 wrists-0.039
ement-0.038
 mouths-0.036
 soaring-0.034
irling-0.033
Token.
Token ID13
Feature activation+2.28e-02

Pos logit contributions
izzy+0.015
enny+0.012
ppy+0.012
 opener+0.012
taker+0.012
Neg logit contributions
ement-0.015
 wrists-0.014
 mouths-0.014
 soaring-0.014
irling-0.013
Token
Token ID198
Feature activation-2.44e-03

Pos logit contributions
izzy+0.052
ppy+0.047
enny+0.045
taker+0.045
washer+0.044
Neg logit contributions
ement-0.027
 wrists-0.026
 soaring-0.026
 mouths-0.026
 conversations-0.025
Token
Token ID198
Feature activation+1.00e-03

Pos logit contributions
ement+0.003
irling+0.003
irl+0.003
mm+0.003
 soaring+0.003
Neg logit contributions
izzy-0.005
ppy-0.005
enny-0.005
head-0.005
taker-0.005
Token"
Token ID1
Feature activation+8.39e-03

Pos logit contributions
izzy+0.002
taker+0.002
enny+0.002
eware+0.002
ppy+0.002
Neg logit contributions
irling-0.001
 wrists-0.001
ement-0.001
mm-0.001
irl-0.001
TokenYou
Token ID1639
Feature activation+6.56e-04

Pos logit contributions
izzy+0.015
enny+0.013
 opener+0.013
ppy+0.013
taker+0.013
Neg logit contributions
ement-0.015
 mouths-0.014
 wrists-0.014
irling-0.014
irl-0.014
Token're
Token ID821
Feature activation-2.85e-02

Pos logit contributions
izzy+0.002
ro+0.002
enny+0.002
guard+0.002
head+0.002
Neg logit contributions
 best-0.001
 mouths-0.001
mm-0.001
irl-0.001
ement-0.001
Token welcome
Token ID7062
Feature activation-1.51e-03

Pos logit contributions
ement+0.047
 soaring+0.045
 mouths+0.044
mm+0.044
irl+0.044
Neg logit contributions
izzy-0.054
enny-0.048
ro-0.046
ppy-0.046
 opener-0.046
Token,
Token ID11
Feature activation+8.79e-03

Pos logit contributions
ement+0.002
 mouths+0.002
mm+0.002
 wrists+0.002
 conversations+0.002
Neg logit contributions
izzy-0.003
enny-0.003
 opener-0.003
taker-0.003
ro-0.003
Token
Token ID198
Feature activation-7.69e-03

Pos logit contributions
izzy+0.007
ppy+0.006
enny+0.006
 opener+0.006
taker+0.006
Neg logit contributions
ement-0.005
 mouths-0.005
mm-0.005
 wrists-0.005
 conversations-0.005
Token
Token ID198
Feature activation-8.07e-03

Pos logit contributions
ement+0.011
irl+0.010
irling+0.010
mm+0.010
 mouths+0.010
Neg logit contributions
izzy-0.016
ppy-0.014
enny-0.014
ro-0.014
 opener-0.014
TokenShe
Token ID3347
Feature activation+1.33e-02

Pos logit contributions
ement+0.013
irling+0.012
mm+0.012
irl+0.012
 wrists+0.012
Neg logit contributions
izzy-0.016
ppy-0.014
enny-0.014
 opener-0.014
ro-0.013
Token was
Token ID373
Feature activation-7.55e-03

Pos logit contributions
izzy+0.026
enny+0.023
 opener+0.022
ppy+0.022
taker+0.022
Neg logit contributions
ement-0.021
 wrists-0.021
 mouths-0.020
irl-0.020
irling-0.020
Token very
Token ID845
Feature activation-6.12e-03

Pos logit contributions
ement+0.014
mm+0.013
 mouths+0.013
 wrists+0.013
irl+0.013
Neg logit contributions
izzy-0.013
taker-0.011
ppy-0.011
enny-0.011
 opener-0.011
Token happy
Token ID3772
Feature activation-9.73e-03

Pos logit contributions
ement+0.007
 mouths+0.007
 wrists+0.007
irling+0.006
irl+0.006
Neg logit contributions
izzy-0.015
enny-0.013
ppy-0.013
 opener-0.013
taker-0.013
Token and
Token ID290
Feature activation-2.20e-04

Pos logit contributions
ement+0.017
 wrists+0.017
 mouths+0.017
 soaring+0.016
irling+0.016
Neg logit contributions
izzy-0.018
enny-0.015
ppy-0.015
 opener-0.014
taker-0.014
Token put
Token ID1234
Feature activation-2.39e-02

Pos logit contributions
ement+0.000
 mouths+0.000
 wrists+0.000
irling+0.000
irl+0.000
Neg logit contributions
izzy-0.000
enny-0.000
taker-0.000
ppy-0.000
 opener-0.000
Token it
Token ID340
Feature activation+1.77e-02

Pos logit contributions
ement+0.040
irling+0.039
 mouths+0.039
mm+0.038
 wrists+0.038
Neg logit contributions
izzy-0.044
taker-0.038
enny-0.037
ppy-0.037
 opener-0.037
Token back
Token ID736
Feature activation+7.73e-03

Pos logit contributions
izzy+0.031
enny+0.027
 opener+0.026
ppy+0.025
taker+0.025
Neg logit contributions
ement-0.032
 soaring-0.031
 wrists-0.031
 mouths-0.030
irl-0.030
Token on
Token ID319
Feature activation+1.02e-02

Pos logit contributions
izzy+0.011
enny+0.009
ppy+0.009
ro+0.009
taker+0.009
Neg logit contributions
ement-0.016
 mouths-0.015
mm-0.015
 wrists-0.015
irling-0.015
Token Sam
Token ID3409
Feature activation+4.09e-03

Pos logit contributions
ement+0.002
 mouths+0.002
 wrists+0.002
mm+0.002
irl+0.002
Neg logit contributions
izzy-0.002
enny-0.001
ppy-0.001
taker-0.001
 opener-0.001
Token says
Token ID1139
Feature activation+3.45e-03

Pos logit contributions
izzy+0.008
 opener+0.007
ppy+0.007
taker+0.007
enny+0.007
Neg logit contributions
ement-0.006
irling-0.006
 mouths-0.006
mm-0.006
 soaring-0.006
Token.
Token ID13
Feature activation+3.09e-02

Pos logit contributions
izzy+0.007
enny+0.006
ppy+0.006
 opener+0.005
ro+0.005
Neg logit contributions
ement-0.006
 wrists-0.005
 mouths-0.005
 soaring-0.005
irling-0.005
Token "
Token ID366
Feature activation+9.41e-03

Pos logit contributions
izzy+0.071
ppy+0.066
enny+0.064
taker+0.062
guard+0.061
Neg logit contributions
ement-0.037
 mouths-0.034
 wrists-0.032
 soaring-0.032
mm-0.032
TokenWe
Token ID1135
Feature activation-8.81e-03

Pos logit contributions
izzy+0.020
enny+0.018
ppy+0.017
taker+0.017
 opener+0.017
Neg logit contributions
ement-0.013
 wrists-0.013
mm-0.012
irl-0.012
irling-0.012
Token number
Token ID1271
Feature activation-1.71e-02

Pos logit contributions
ement+0.013
 mouths+0.012
 wrists+0.012
irl+0.012
 soaring+0.012
Neg logit contributions
izzy-0.018
enny-0.016
ppy-0.016
taker-0.016
 opener-0.016
Token to
Token ID284
Feature activation-9.47e-03

Pos logit contributions
ement+0.029
irling+0.028
irl+0.028
mm+0.027
 mouths+0.027
Neg logit contributions
izzy-0.030
enny-0.026
ppy-0.026
 opener-0.026
ro-0.025
Token see
Token ID766
Feature activation-1.68e-02

Pos logit contributions
ement+0.017
irling+0.016
 mouths+0.016
mm+0.016
irl+0.016
Neg logit contributions
izzy-0.016
ppy-0.014
enny-0.014
 opener-0.014
ro-0.013
Token who
Token ID508
Feature activation-2.10e-02

Pos logit contributions
ement+0.032
irling+0.032
irl+0.031
 mouths+0.031
mm+0.030
Neg logit contributions
izzy-0.025
ppy-0.022
enny-0.021
taker-0.021
 opener-0.021
Token is
Token ID318
Feature activation+1.21e-03

Pos logit contributions
ement+0.032
irling+0.030
 wrists+0.030
 mouths+0.030
mm+0.030
Neg logit contributions
izzy-0.042
enny-0.037
ppy-0.037
 opener-0.036
taker-0.036
Token better
Token ID1365
Feature activation+5.53e-03

Pos logit contributions
izzy+0.002
 opener+0.002
ppy+0.002
enny+0.002
taker+0.002
Neg logit contributions
ement-0.002
mm-0.002
 mouths-0.002
 wrists-0.002
irling-0.002
Token Every
Token ID3887
Feature activation+6.37e-03

Pos logit contributions
irling+0.004
ement+0.004
 wrists+0.003
irl+0.003
 mouths+0.003
Neg logit contributions
izzy-0.003
 opener-0.003
ro-0.003
enny-0.002
head-0.002
Token day
Token ID1110
Feature activation+4.41e-03

Pos logit contributions
izzy+0.013
enny+0.012
 opener+0.011
ppy+0.011
ro+0.011
Neg logit contributions
ement-0.010
 wrists-0.009
 mouths-0.009
irling-0.009
mm-0.009
Token,
Token ID11
Feature activation+7.22e-03

Pos logit contributions
izzy+0.008
enny+0.007
 opener+0.007
ppy+0.007
head+0.007
Neg logit contributions
ement-0.007
 wrists-0.007
irling-0.007
 mouths-0.007
irl-0.007
Token it
Token ID340
Feature activation-3.92e-03

Pos logit contributions
izzy+0.011
head+0.010
 opener+0.010
taker+0.010
enny+0.009
Neg logit contributions
ement-0.014
irling-0.013
 wrists-0.013
 mouths-0.013
irl-0.013
Token grew
Token ID6348
Feature activation+1.14e-02

Pos logit contributions
irl+0.005
 mouths+0.005
 pic+0.005
 soaring+0.005
irling+0.004
Neg logit contributions
izzy-0.009
enny-0.008
taker-0.008
 opener-0.008
uster-0.008
Token bigger
Token ID5749
Feature activation-9.76e-03

Pos logit contributions
izzy+0.025
enny+0.023
ppy+0.021
taker+0.021
 opener+0.021
Neg logit contributions
ement-0.015
 mouths-0.015
 soaring-0.015
irl-0.015
irling-0.014
Token and
Token ID290
Feature activation+1.23e-02

Pos logit contributions
 mouths+0.013
ement+0.013
 wrists+0.013
 soaring+0.013
 conversations+0.012
Neg logit contributions
izzy-0.022
enny-0.020
taker-0.019
 opener-0.018
ppy-0.018
Token bigger
Token ID5749
Feature activation-3.74e-03

Pos logit contributions
izzy+0.022
enny+0.019
 opener+0.019
ppy+0.018
taker+0.018
Neg logit contributions
ement-0.022
 mouths-0.021
 wrists-0.021
irling-0.020
mm-0.020
Token.
Token ID13
Feature activation-7.84e-03

Pos logit contributions
 mouths+0.006
ement+0.006
 wrists+0.006
 soaring+0.006
 conversations+0.006
Neg logit contributions
izzy-0.008
enny-0.007
ppy-0.006
taker-0.006
 opener-0.006
Token
Token ID220
Feature activation+1.74e-02

Pos logit contributions
irling+0.017
ement+0.016
cking+0.015
irl+0.015
heit+0.015
Neg logit contributions
izzy-0.012
 opener-0.010
ro-0.010
enny-0.010
head-0.010
Token
Token ID198
Feature activation+8.12e-03

Pos logit contributions
izzy+0.033
enny+0.028
 opener+0.027
ppy+0.027
taker+0.027
Neg logit contributions
ement-0.029
 wrists-0.028
 mouths-0.028
irling-0.027
irl-0.027
Token,
Token ID11
Feature activation-1.08e-02

Pos logit contributions
ement+0.032
 mouths+0.030
 wrists+0.030
irling+0.030
irl+0.029
Neg logit contributions
izzy-0.043
enny-0.038
ppy-0.037
 opener-0.037
taker-0.037
Token we
Token ID356
Feature activation-1.49e-02

Pos logit contributions
ement+0.018
 mouths+0.017
 wrists+0.017
mm+0.017
 soaring+0.017
Neg logit contributions
izzy-0.020
enny-0.017
 opener-0.017
ppy-0.017
taker-0.016
Token need
Token ID761
Feature activation+2.52e-02

Pos logit contributions
ement+0.019
irl+0.019
 mouths+0.019
 wrists+0.018
 disagreement+0.018
Neg logit contributions
izzy-0.033
enny-0.030
 opener-0.029
ro-0.029
taker-0.029
Token to
Token ID284
Feature activation+2.10e-03

Pos logit contributions
izzy+0.033
enny+0.026
ppy+0.026
taker+0.025
 opener+0.024
Neg logit contributions
ement-0.056
 mouths-0.056
 wrists-0.056
 soaring-0.055
 conversations-0.054
Token organize
Token ID16481
Feature activation+1.76e-03

Pos logit contributions
izzy+0.004
enny+0.003
ppy+0.003
 opener+0.003
taker+0.003
Neg logit contributions
ement-0.004
 mouths-0.004
 wrists-0.003
irling-0.003
mm-0.003
Token your
Token ID534
Feature activation-3.17e-03

Pos logit contributions
izzy+0.004
enny+0.003
ppy+0.003
 opener+0.003
taker+0.003
Neg logit contributions
ement-0.003
 mouths-0.002
 wrists-0.002
irling-0.002
 soaring-0.002
Token room
Token ID2119
Feature activation+3.15e-03

Pos logit contributions
ement+0.005
mm+0.004
irling+0.004
 soaring+0.004
 wrists+0.004
Neg logit contributions
izzy-0.007
enny-0.006
 opener-0.006
taker-0.006
ppy-0.006
Token.
Token ID13
Feature activation-1.84e-05

Pos logit contributions
izzy+0.006
enny+0.005
ppy+0.005
 opener+0.005
taker+0.005
Neg logit contributions
ement-0.005
 wrists-0.005
 mouths-0.005
irl-0.005
 pic-0.005
Token Let
Token ID3914
Feature activation-5.00e-03

Pos logit contributions
mm+0.000
 mouths+0.000
 wrists+0.000
ement+0.000
 pic+0.000
Neg logit contributions
izzy-0.000
enny-0.000
ppy-0.000
taker-0.000
guard-0.000
Token's
Token ID338
Feature activation-4.30e-03

Pos logit contributions
ement+0.006
 mouths+0.005
 wrists+0.005
irling+0.005
irl+0.005
Neg logit contributions
izzy-0.012
enny-0.011
ppy-0.011
 opener-0.011
taker-0.010
Token start
Token ID923
Feature activation-2.64e-03

Pos logit contributions
ement+0.007
irl+0.007
 wrists+0.007
 mouths+0.006
irling+0.006
Neg logit contributions
izzy-0.008
enny-0.007
ppy-0.007
taker-0.007
 opener-0.007
Token bear
Token ID6842
Feature activation+8.34e-03

Pos logit contributions
izzy+0.006
enny+0.006
ppy+0.006
 opener+0.005
taker+0.005
Neg logit contributions
ement-0.005
 mouths-0.005
 wrists-0.005
 soaring-0.005
 difference-0.005
Token.
Token ID13
Feature activation+1.31e-03

Pos logit contributions
izzy+0.015
enny+0.013
ppy+0.013
 opener+0.013
taker+0.013
Neg logit contributions
ement-0.014
 mouths-0.014
 soaring-0.013
 wrists-0.013
irling-0.013
Token
Token ID198
Feature activation-1.30e-03

Pos logit contributions
izzy+0.003
ppy+0.002
enny+0.002
 opener+0.002
taker+0.002
Neg logit contributions
ement-0.002
 mouths-0.002
mm-0.002
 wrists-0.002
 soaring-0.002
Token
Token ID198
Feature activation-2.40e-03

Pos logit contributions
ement+0.002
irl+0.002
irling+0.002
 soaring+0.002
mm+0.002
Neg logit contributions
izzy-0.003
ppy-0.003
enny-0.003
ro-0.002
head-0.002
TokenAfter
Token ID3260
Feature activation+7.10e-03

Pos logit contributions
irling+0.003
ement+0.003
irl+0.003
mm+0.003
 soaring+0.003
Neg logit contributions
izzy-0.005
ppy-0.004
enny-0.004
 opener-0.004
taker-0.004
Token that
Token ID326
Feature activation-1.04e-02

Pos logit contributions
izzy+0.012
 opener+0.010
enny+0.010
taker+0.010
ppy+0.010
Neg logit contributions
ement-0.013
 wrists-0.013
 mouths-0.013
irling-0.013
irl-0.013
Token,
Token ID11
Feature activation+5.08e-03

Pos logit contributions
 wrists+0.022
irling+0.021
ement+0.021
 mouths+0.020
irl+0.020
Neg logit contributions
izzy-0.016
taker-0.014
enny-0.013
 opener-0.013
t-0.013
Token Tim
Token ID5045
Feature activation+4.76e-03

Pos logit contributions
izzy+0.008
taker+0.007
enny+0.007
 opener+0.007
head+0.006
Neg logit contributions
ement-0.010
 wrists-0.010
irling-0.010
irl-0.009
 mouths-0.009
Token realized
Token ID6939
Feature activation+1.86e-02

Pos logit contributions
izzy+0.010
 opener+0.009
taker+0.009
enny+0.009
head+0.009
Neg logit contributions
ement-0.006
 mouths-0.006
 soaring-0.006
irling-0.006
 wrists-0.006
Token that
Token ID326
Feature activation-3.73e-03

Pos logit contributions
izzy+0.032
enny+0.027
ppy+0.026
 opener+0.026
ro+0.025
Neg logit contributions
ement-0.035
 mouths-0.033
 soaring-0.033
 wrists-0.033
irling-0.033
Token he
Token ID339
Feature activation-8.51e-03

Pos logit contributions
ement+0.008
 wrists+0.008
irling+0.008
irl+0.008
mm+0.008
Neg logit contributions
izzy-0.005
taker-0.004
 opener-0.004
guard-0.004
head-0.004
Token his
Token ID465
Feature activation-2.19e-03

Pos logit contributions
ement+0.017
irling+0.016
mm+0.016
 mouths+0.016
 wrists+0.016
Neg logit contributions
izzy-0.016
 opener-0.013
ro-0.013
enny-0.013
taker-0.013
Token lap
Token ID14779
Feature activation-5.10e-03

Pos logit contributions
ement+0.003
mm+0.003
irling+0.003
irl+0.003
 soaring+0.003
Neg logit contributions
izzy-0.004
ppy-0.004
ro-0.004
enny-0.004
 opener-0.004
Token.
Token ID13
Feature activation-3.38e-03

Pos logit contributions
ement+0.009
 mouths+0.008
 wrists+0.008
 conversations+0.008
mm+0.008
Neg logit contributions
izzy-0.009
enny-0.008
ppy-0.008
 opener-0.008
taker-0.008
Token She
Token ID1375
Feature activation-3.07e-04

Pos logit contributions
ement+0.006
 wrists+0.006
 mouths+0.006
irling+0.006
irl+0.006
Neg logit contributions
izzy-0.006
enny-0.005
 opener-0.005
ppy-0.005
taker-0.005
Token makes
Token ID1838
Feature activation-9.79e-03

Pos logit contributions
ement+0.000
mm+0.000
 wrists+0.000
irling+0.000
 soaring+0.000
Neg logit contributions
izzy-0.001
ppy-0.001
enny-0.001
 opener-0.001
ro-0.001
Token soft
Token ID2705
Feature activation-4.08e-02

Pos logit contributions
ement+0.014
 mouths+0.014
 wrists+0.014
irl+0.013
 soaring+0.013
Neg logit contributions
izzy-0.020
enny-0.018
 opener-0.018
ppy-0.018
taker-0.017
Token noises
Token ID26782
Feature activation-1.51e-02

Pos logit contributions
ement+0.060
 wrists+0.056
 mouths+0.056
irling+0.056
irl+0.055
Neg logit contributions
izzy-0.084
ppy-0.073
enny-0.073
taker-0.072
ro-0.072
Token that
Token ID326
Feature activation-1.11e-02

Pos logit contributions
ement+0.024
 soaring+0.023
 mouths+0.023
 wrists+0.022
irling+0.022
Neg logit contributions
izzy-0.029
enny-0.026
ppy-0.025
 opener-0.024
taker-0.024
Token make
Token ID787
Feature activation-1.19e-02

Pos logit contributions
ement+0.018
 wrists+0.017
irling+0.017
 mouths+0.016
mm+0.016
Neg logit contributions
izzy-0.022
enny-0.019
 opener-0.019
ppy-0.019
taker-0.018
Token Ben
Token ID3932
Feature activation-2.53e-02

Pos logit contributions
ement+0.017
 mouths+0.016
 wrists+0.016
irling+0.016
irl+0.016
Neg logit contributions
izzy-0.025
enny-0.022
ppy-0.022
 opener-0.022
taker-0.022
Token happy
Token ID3772
Feature activation-7.35e-03

Pos logit contributions
ement+0.042
mm+0.039
 wrists+0.037
 pic+0.037
irling+0.037
Neg logit contributions
izzy-0.050
ppy-0.046
taker-0.043
 opener-0.043
enny-0.042
Token darling
Token ID40003
Feature activation-3.95e-03

Feature not active on prev token;
no predictions were affected.
Token".
Token ID1911
Feature activation-8.70e-03

Pos logit contributions
ement+0.007
 wrists+0.007
 mouths+0.007
irling+0.007
mm+0.007
Neg logit contributions
izzy-0.007
enny-0.006
 opener-0.006
ppy-0.006
taker-0.005
Token<|endoftext|>
Token ID50256
Feature activation+1.44e-02

Pos logit contributions
ement+0.012
 mouths+0.011
 wrists+0.011
mm+0.011
irling+0.011
Neg logit contributions
izzy-0.019
enny-0.017
ppy-0.017
 opener-0.017
taker-0.016
TokenOnce
Token ID7454
Feature activation-1.21e-02

Pos logit contributions
izzy+0.026
enny+0.023
ppy+0.022
taker+0.022
 opener+0.022
Neg logit contributions
ement-0.025
 mouths-0.023
 wrists-0.023
 soaring-0.023
irl-0.023
Token upon
Token ID2402
Feature activation+7.62e-03

Pos logit contributions
ement+0.023
 mouths+0.022
irl+0.021
mm+0.021
irling+0.021
Neg logit contributions
izzy-0.019
 opener-0.017
ppy-0.017
enny-0.016
ro-0.016
Token a
Token ID257
Feature activation-3.98e-02

Pos logit contributions
izzy+0.012
enny+0.011
 opener+0.010
ppy+0.010
taker+0.010
Neg logit contributions
ement-0.015
 wrists-0.014
 mouths-0.014
irling-0.014
mm-0.014
Token time
Token ID640
Feature activation-1.86e-02

Pos logit contributions
 wrists+0.065
 mouths+0.060
 soaring+0.059
ement+0.059
 bicycles+0.055
Neg logit contributions
izzy-0.079
enny-0.073
ppy-0.073
t-0.069
ily-0.068
Token there
Token ID612
Feature activation-2.18e-02

Pos logit contributions
 wrists+0.033
ement+0.032
 mouths+0.032
irling+0.031
irl+0.030
Neg logit contributions
izzy-0.034
enny-0.030
ppy-0.028
 opener-0.028
taker-0.028
Token was
Token ID373
Feature activation-1.01e-03

Pos logit contributions
 wrists+0.043
irling+0.042
ement+0.042
 mouths+0.041
 soaring+0.040
Neg logit contributions
izzy-0.037
enny-0.030
 opener-0.028
ily-0.028
ro-0.027
Token a
Token ID257
Feature activation-8.39e-05

Pos logit contributions
ement+0.002
 wrists+0.002
 mouths+0.002
irling+0.002
mm+0.002
Neg logit contributions
izzy-0.001
enny-0.001
ily-0.001
 opener-0.001
ppy-0.001
Token little
Token ID1310
Feature activation+5.17e-03

Pos logit contributions
ement+0.000
 mouths+0.000
 wrists+0.000
irling+0.000
irl+0.000
Neg logit contributions
izzy-0.000
enny-0.000
ppy-0.000
 opener-0.000
taker-0.000
Token friends
Token ID2460
Feature activation+3.45e-03

Pos logit contributions
izzy+0.001
enny+0.001
ppy+0.001
 opener+0.001
taker+0.001
Neg logit contributions
ement-0.000
 wrists-0.000
 mouths-0.000
irling-0.000
mm-0.000
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
izzy+0.006
enny+0.005
ppy+0.005
 opener+0.005
taker+0.004
Neg logit contributions
ement-0.007
 mouths-0.006
 wrists-0.006
irling-0.006
mm-0.006
Token<|endoftext|>
Token ID50256
Feature activation+7.25e-03

Pos logit contributions
ement+0.023
 wrists+0.022
 mouths+0.022
irling+0.022
irl+0.021
Neg logit contributions
izzy-0.028
enny-0.024
ppy-0.023
 opener-0.023
taker-0.023
TokenOnce
Token ID7454
Feature activation-1.43e-02

Pos logit contributions
izzy+0.013
enny+0.011
ppy+0.011
 opener+0.011
taker+0.011
Neg logit contributions
ement-0.013
 mouths-0.012
 wrists-0.012
irling-0.012
irl-0.012
Token upon
Token ID2402
Feature activation+1.32e-02

Pos logit contributions
ement+0.028
 mouths+0.027
irl+0.026
 wrists+0.026
irling+0.026
Neg logit contributions
izzy-0.022
enny-0.019
 opener-0.019
ppy-0.019
taker-0.018
Token a
Token ID257
Feature activation-3.77e-02

Pos logit contributions
izzy+0.024
enny+0.021
ppy+0.021
taker+0.021
 opener+0.020
Neg logit contributions
ement-0.022
 soaring-0.021
 mouths-0.021
irl-0.021
 wrists-0.021
Token time
Token ID640
Feature activation-2.11e-02

Pos logit contributions
 wrists+0.057
ement+0.053
 soaring+0.052
 mouths+0.051
 bicycles+0.048
Neg logit contributions
izzy-0.078
ppy-0.075
enny-0.072
ily-0.069
ro-0.067
Token,
Token ID11
Feature activation+9.37e-03

Pos logit contributions
 wrists+0.039
ement+0.037
 mouths+0.037
irling+0.036
irl+0.035
Neg logit contributions
izzy-0.038
enny-0.033
ppy-0.031
 opener-0.031
t-0.030
Token there
Token ID612
Feature activation-2.33e-02

Pos logit contributions
izzy+0.016
enny+0.013
ppy+0.013
 opener+0.013
taker+0.013
Neg logit contributions
ement-0.018
 wrists-0.017
 mouths-0.017
mm-0.017
 conversations-0.017
Token was
Token ID373
Feature activation+2.94e-03

Pos logit contributions
 wrists+0.045
ement+0.044
irling+0.043
 mouths+0.043
 soaring+0.042
Neg logit contributions
izzy-0.040
enny-0.033
 opener-0.032
ro-0.031
ppy-0.031
Token a
Token ID257
Feature activation-2.95e-04

Pos logit contributions
izzy+0.005
enny+0.004
ppy+0.004
 opener+0.004
taker+0.004
Neg logit contributions
ement-0.006
 wrists-0.006
 mouths-0.006
irling-0.006
mm-0.006
Token friends
Token ID2460
Feature activation-2.09e-04

Pos logit contributions
ement+0.009
irling+0.008
mm+0.008
irl+0.008
 soaring+0.008
Neg logit contributions
izzy-0.009
ro-0.008
ppy-0.008
 opener-0.008
unny-0.008
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
ement+0.000
 mouths+0.000
 wrists+0.000
irling+0.000
irl+0.000
Neg logit contributions
izzy-0.000
enny-0.000
ppy-0.000
 opener-0.000
taker-0.000
Token He
Token ID679
Feature activation-9.72e-03

Pos logit contributions
ement+0.014
 wrists+0.013
irling+0.013
 mouths+0.013
 soaring+0.012
Neg logit contributions
izzy-0.026
enny-0.024
 opener-0.023
ppy-0.023
ro-0.023
Token had
Token ID550
Feature activation-8.05e-04

Pos logit contributions
ement+0.015
 wrists+0.014
 mouths+0.014
irling+0.014
mm+0.014
Neg logit contributions
izzy-0.019
enny-0.017
ppy-0.017
 opener-0.016
taker-0.016
Token a
Token ID257
Feature activation-1.97e-02

Pos logit contributions
ement+0.002
mm+0.002
irling+0.002
irl+0.002
 wrists+0.002
Neg logit contributions
izzy-0.001
ily-0.001
ppy-0.001
 opener-0.001
ro-0.001
Token big
Token ID1263
Feature activation-4.93e-02

Pos logit contributions
ement+0.046
cks+0.041
mm+0.041
irling+0.039
cking+0.038
Neg logit contributions
izzy-0.026
 opener-0.024
ro-0.023
unny-0.022
rex-0.021
Token horn
Token ID12718
Feature activation-1.92e-02

Pos logit contributions
ement+0.103
cks+0.096
irling+0.095
cking+0.093
mm+0.091
Neg logit contributions
izzy-0.062
ro-0.061
 opener-0.058
ppy-0.056
rex-0.054
Token on
Token ID319
Feature activation-3.80e-03

Pos logit contributions
ement+0.031
 mouths+0.030
 soaring+0.030
 wrists+0.029
mm+0.028
Neg logit contributions
izzy-0.038
enny-0.034
ppy-0.032
taker-0.031
 opener-0.031
Token his
Token ID465
Feature activation-4.68e-03

Pos logit contributions
ement+0.007
irling+0.007
 wrists+0.007
mm+0.007
 mouths+0.006
Neg logit contributions
izzy-0.006
 opener-0.006
ro-0.006
taker-0.005
head-0.005
Token head
Token ID1182
Feature activation-6.94e-03

Pos logit contributions
ement+0.008
mm+0.007
irling+0.007
irl+0.007
 soaring+0.006
Neg logit contributions
izzy-0.009
ppy-0.008
ro-0.008
 opener-0.008
enny-0.008
Token that
Token ID326
Feature activation-8.77e-03

Pos logit contributions
ement+0.012
 mouths+0.011
 wrists+0.011
 soaring+0.011
mm+0.011
Neg logit contributions
izzy-0.013
enny-0.011
ppy-0.011
taker-0.011
 opener-0.011
Token others
Token ID1854
Feature activation+6.84e-03

Pos logit contributions
ement+0.000
 wrists+0.000
irling+0.000
irl+0.000
mm+0.000
Neg logit contributions
izzy-0.000
ppy-0.000
enny-0.000
 opener-0.000
taker-0.000
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
izzy+0.011
enny+0.010
ppy+0.010
 opener+0.009
taker+0.009
Neg logit contributions
ement-0.013
 wrists-0.012
 mouths-0.012
mm-0.012
irling-0.012
Token<|endoftext|>
Token ID50256
Feature activation+1.95e-02

Pos logit contributions
ement+0.023
 mouths+0.022
mm+0.022
 wrists+0.021
 soaring+0.021
Neg logit contributions
izzy-0.030
ppy-0.026
enny-0.026
 opener-0.026
taker-0.025
TokenOnce
Token ID7454
Feature activation-1.77e-02

Pos logit contributions
izzy+0.038
enny+0.033
ppy+0.033
taker+0.032
 opener+0.032
Neg logit contributions
ement-0.031
 mouths-0.029
 wrists-0.029
irl-0.029
 soaring-0.028
Token upon
Token ID2402
Feature activation+1.57e-02

Pos logit contributions
ement+0.035
 mouths+0.034
 wrists+0.034
irling+0.033
irl+0.033
Neg logit contributions
izzy-0.027
enny-0.023
ppy-0.023
 opener-0.022
taker-0.022
Token a
Token ID257
Feature activation-4.03e-02

Pos logit contributions
izzy+0.027
enny+0.023
ppy+0.023
 opener+0.023
taker+0.022
Neg logit contributions
ement-0.028
 mouths-0.027
 wrists-0.027
irl-0.027
irling-0.027
Token time
Token ID640
Feature activation-2.20e-02

Pos logit contributions
 wrists+0.067
 mouths+0.061
ement+0.060
 soaring+0.060
mm+0.056
Neg logit contributions
izzy-0.079
ppy-0.074
enny-0.074
t-0.071
ro-0.069
Token,
Token ID11
Feature activation+6.99e-03

Pos logit contributions
 wrists+0.041
ement+0.039
 mouths+0.039
irling+0.039
irl+0.038
Neg logit contributions
izzy-0.039
enny-0.034
 opener-0.032
ppy-0.031
t-0.031
Token there
Token ID612
Feature activation-2.52e-02

Pos logit contributions
izzy+0.012
enny+0.010
ppy+0.009
 opener+0.009
ily+0.009
Neg logit contributions
ement-0.014
 wrists-0.014
 mouths-0.013
irling-0.013
mm-0.013
Token was
Token ID373
Feature activation+1.75e-04

Pos logit contributions
 wrists+0.053
irling+0.050
ement+0.050
 mouths+0.049
 soaring+0.048
Neg logit contributions
izzy-0.040
enny-0.033
 opener-0.030
ily-0.030
ro-0.030
Token a
Token ID257
Feature activation+1.08e-03

Pos logit contributions
izzy+0.000
enny+0.000
 opener+0.000
ily+0.000
ppy+0.000
Neg logit contributions
ement-0.000
 wrists-0.000
 mouths-0.000
irling-0.000
mm-0.000