TOP ACTIVATIONS
MAX = 6.691

Tom called out to the gol fer " Hey , why
rocks . She realized how valuable these differences were and that
noticed something strange . A gol fer was hitting golf balls
Tim my always remembered how valuable he was , even when
Every day it would mail letters to the people who lived
pond ?" The gol fer replied , " I
around and pe cking each other . The chickens
frowned when she noticed how expensive some of them were .
them tw irl around each other . Annie 's mother called
accidentally touched the light bul b and it was very hot
her arms . As she mar ached away from the garden
restore it back to its rightful place . Although Sammy was
he got it so the rightful owner could find it .
a hairy palace . Everywhere you looked there were furry walls
as he opened the ch ocol ates and started eating them
was very blue . Everywhere you looked , it was painted
, cup cakes and ch ocol ates .
He quickly hung colorful or nam ents and tw ink ling
bled up all the ch ocol ates , and she was
full of life . Everywhere you looked there were crazy creatures

MIN ACTIVATIONS
MIN = -6.163

" And it is our cloud . Let 's give it
city . Ali said ,
lets . Ali was so excited , he
thought it was the best cloud ever . And Bob never
One day , Ali received a letter in the
were happy with their new cloud . They pretended it was
realized it wasn 't a cloud at all . It was
inside , â said Ali â s mom
One day , Ali and her mum went to
said it wasn 't a cloud . She went to the
" Hi , I 'm Bee . Do you want to
bird began to tell Pen elope it 's story .
there were two friends , Ali and Pat . They were
all day with his new cloud close to him . He
harmless day with not a cloud in the sky .
do ?" Ali had an idea . She
done something good for his hive . <|endoftext|> Once upon a
" Hello , cloud !" Ellie said .
hive was the most independent hive in town . Everyone was
. The yacht remembered the cloud and thought , " Oh

INTERVAL 3.478 - 6.691
CONTAINS 0.159%

But then she saw how expensive the things were and decided
board and quickly noticed something expensive shining and gl int ing
, " Let me help you ," and squ atted down
pull the doll from each other . The doll makes a
give you this sausage if you slap me on the back

INTERVAL 0.264 - 3.478
CONTAINS 35.454%

. She sees the tower . It is very
the coffee . He sees a bottle of k etchup in
go home ." Emma knew that it was time to wait
of its hard work . From then on , it kept
She was so excited when she found it .

INTERVAL -2.949 - 0.264
CONTAINS 63.952%

. " Yes , it is ," said her mom .
named Lily . Lily loved to play outside and get dirty
to go back to their bus . They got
leaves for the nest . They all worked together and soon
dust and its mysterious beauty . <|endoftext|> Once upon a time

INTERVAL -6.163 - -2.949
CONTAINS 0.435%

every day , Tommy and Larry filled the big place with
stayed and watched for a while until he got tired .
holding his mom â s hand tight and shaking
lady saw him sne e ze and said , " B
kitten home ." M ia and her mom took
TokenTom
Token ID13787
Feature activation+2.42e-02

Pos logit contributions
 gol+0.007
 traded+0.006
 Captain+0.006
 pride+0.006
 Cody+0.006
Neg logit contributions
comb-0.007
elope-0.007
bes-0.007
we-0.007
Ali-0.006
Token called
Token ID1444
Feature activation+3.44e+00

Pos logit contributions
 gol+0.001
 Captain+0.001
 pride+0.001
 Cody+0.001
 traded+0.001
Neg logit contributions
elope-0.001
bes-0.001
Ali-0.001
comb-0.001
we-0.001
Token out
Token ID503
Feature activation+9.58e-02

Pos logit contributions
 gol+0.141
 traded+0.123
 Captain+0.114
 pride+0.113
 Cody+0.111
Neg logit contributions
elope-0.200
zed-0.193
comb-0.193
Ali-0.191
 Pen-0.191
Token to
Token ID284
Feature activation+3.70e-01

Pos logit contributions
 gol+0.003
 Captain+0.003
 traded+0.003
 pride+0.003
 Cody+0.002
Neg logit contributions
bes-0.007
elope-0.007
comb-0.006
we-0.006
Ali-0.006
Token the
Token ID262
Feature activation+7.26e-01

Pos logit contributions
 gol+0.017
 traded+0.015
 pride+0.015
 Captain+0.014
vious+0.014
Neg logit contributions
elope-0.019
Ali-0.018
zed-0.018
 Pen-0.017
we-0.017
Token gol
Token ID43791
Feature activation+5.83e+00

Pos logit contributions
 online+0.036
 written+0.031
 pride+0.031
old+0.031
year+0.030
Neg logit contributions
ich-0.029
 cloud-0.028
 edge-0.028
 song-0.027
 shoulder-0.026
Tokenfer
Token ID2232
Feature activation+3.79e-01

Pos logit contributions
 gol+0.368
 traded+0.353
 Captain+0.352
 pride+0.335
 Cody+0.333
Neg logit contributions
elope-0.215
bes-0.211
comb-0.207
Ali-0.201
we-0.196
Token "
Token ID366
Feature activation-5.48e-01

Pos logit contributions
 gol+0.015
 Captain+0.014
 traded+0.014
 pride+0.014
 Cody+0.013
Neg logit contributions
elope-0.023
bes-0.022
comb-0.022
Ali-0.021
we-0.021
TokenHey
Token ID10814
Feature activation+1.07e+00

Pos logit contributions
elope+0.026
bes+0.026
comb+0.025
we+0.025
Ali+0.025
Neg logit contributions
 gol-0.028
 Captain-0.027
 traded-0.027
 pride-0.026
 Cody-0.025
Token,
Token ID11
Feature activation-2.44e-01

Pos logit contributions
 pride+0.051
 traded+0.047
 online+0.047
 Captain+0.044
 gol+0.044
Neg logit contributions
ggy-0.046
we-0.045
elope-0.044
 cloud-0.043
ze-0.043
Token why
Token ID1521
Feature activation-1.46e+00

Pos logit contributions
 cloud+0.009
ggy+0.009
we+0.009
Ali+0.009
ze+0.009
Neg logit contributions
 traded-0.012
 pride-0.011
 online-0.011
 gol-0.011
 written-0.011
Token rocks
Token ID12586
Feature activation+1.72e+00

Pos logit contributions
 gol+0.034
 traded+0.031
 Captain+0.031
 Cody+0.029
 pride+0.029
Neg logit contributions
elope-0.039
bes-0.039
comb-0.038
we-0.038
Ali-0.037
Token.
Token ID13
Feature activation+1.94e-01

Pos logit contributions
 gol+0.084
 Captain+0.081
 traded+0.079
 pride+0.075
 Cody+0.073
Neg logit contributions
bes-0.086
comb-0.086
elope-0.086
we-0.084
Ali-0.081
Token She
Token ID1375
Feature activation+1.56e-01

Pos logit contributions
 gol+0.010
 traded+0.009
 Captain+0.009
 Cody+0.008
 pride+0.008
Neg logit contributions
elope-0.010
Ali-0.010
bes-0.009
we-0.009
comb-0.009
Token realized
Token ID6939
Feature activation+1.32e+00

Pos logit contributions
 gol+0.007
 Captain+0.007
 traded+0.006
 Cody+0.006
 pride+0.006
Neg logit contributions
elope-0.009
bes-0.008
comb-0.008
Ali-0.008
we-0.008
Token how
Token ID703
Feature activation+5.55e-02

Pos logit contributions
 gol+0.075
 traded+0.075
 Captain+0.068
 pride+0.066
 Cody+0.063
Neg logit contributions
elope-0.053
we-0.053
zed-0.053
bes-0.052
comb-0.052
Token valuable
Token ID8119
Feature activation+5.69e+00

Pos logit contributions
 gol+0.002
 traded+0.002
 Captain+0.002
 Cody+0.002
 pride+0.002
Neg logit contributions
elope-0.003
we-0.003
bes-0.003
zed-0.003
Ali-0.003
Token these
Token ID777
Feature activation+1.48e+00

Pos logit contributions
 gol+0.268
 traded+0.258
 Captain+0.251
 pride+0.235
 Cody+0.232
Neg logit contributions
elope-0.303
bes-0.298
we-0.292
comb-0.291
Ali-0.284
Token differences
Token ID5400
Feature activation+2.03e+00

Pos logit contributions
 gol+0.067
 Captain+0.063
 traded+0.063
 pride+0.059
 Cody+0.058
Neg logit contributions
elope-0.081
bes-0.080
comb-0.079
we-0.077
Ali-0.077
Token were
Token ID547
Feature activation-5.22e-01

Pos logit contributions
 gol+0.085
 Captain+0.080
 traded+0.079
 pride+0.074
 Cody+0.073
Neg logit contributions
elope-0.117
bes-0.116
comb-0.114
we-0.113
Ali-0.112
Token and
Token ID290
Feature activation-3.86e-01

Pos logit contributions
elope+0.029
bes+0.028
comb+0.028
we+0.028
zed+0.026
Neg logit contributions
 gol-0.023
 traded-0.021
 Captain-0.021
 Cody-0.020
 pride-0.019
Token that
Token ID326
Feature activation-4.36e-01

Pos logit contributions
elope+0.021
bes+0.020
we+0.020
comb+0.020
zed+0.019
Neg logit contributions
 gol-0.018
 Captain-0.017
 traded-0.017
 Cody-0.016
 pride-0.015
Token noticed
Token ID6810
Feature activation-8.74e-01

Pos logit contributions
 gol+0.018
 Captain+0.017
 pride+0.016
 traded+0.016
 Cody+0.016
Neg logit contributions
elope-0.025
bes-0.024
comb-0.024
we-0.024
Ali-0.024
Token something
Token ID1223
Feature activation+1.15e+00

Pos logit contributions
we+0.046
elope+0.045
bes+0.045
Ali+0.044
comb+0.044
Neg logit contributions
 gol-0.040
 traded-0.037
 pride-0.036
 Captain-0.036
 Cody-0.034
Token strange
Token ID6283
Feature activation+1.87e+00

Pos logit contributions
 gol+0.050
 Captain+0.047
 traded+0.047
 pride+0.045
 Cody+0.044
Neg logit contributions
elope-0.063
bes-0.063
comb-0.062
we-0.062
Ali-0.061
Token.
Token ID13
Feature activation+1.28e-01

Pos logit contributions
 gol+0.076
 traded+0.074
 Captain+0.073
 pride+0.067
 Cody+0.066
Neg logit contributions
elope-0.109
bes-0.108
Ali-0.105
comb-0.105
we-0.101
Token A
Token ID317
Feature activation+1.29e+00

Pos logit contributions
 gol+0.005
 Captain+0.005
 traded+0.005
 pride+0.005
 Cody+0.004
Neg logit contributions
elope-0.007
bes-0.007
Ali-0.007
zed-0.007
comb-0.007
Token gol
Token ID43791
Feature activation+5.59e+00

Pos logit contributions
 gol+0.060
 traded+0.060
 Captain+0.057
 pride+0.056
 Cody+0.055
Neg logit contributions
elope-0.066
bes-0.063
Ali-0.063
comb-0.063
we-0.061
Tokenfer
Token ID2232
Feature activation-6.92e-02

Pos logit contributions
 gol+0.353
 traded+0.338
 Captain+0.337
 pride+0.321
 Cody+0.319
Neg logit contributions
elope-0.207
bes-0.203
comb-0.198
Ali-0.192
we-0.188
Token was
Token ID373
Feature activation+2.71e-01

Pos logit contributions
elope+0.004
we+0.004
bes+0.004
Ali+0.003
comb+0.003
Neg logit contributions
 gol-0.003
 Captain-0.003
 pride-0.003
 traded-0.003
 Cody-0.003
Token hitting
Token ID9008
Feature activation+4.51e-01

Pos logit contributions
 gol+0.014
 pride+0.013
 traded+0.013
 Captain+0.013
 Cody+0.012
Neg logit contributions
bes-0.012
we-0.012
ze-0.011
elope-0.011
Ali-0.011
Token golf
Token ID13126
Feature activation+4.25e+00

Pos logit contributions
 gol+0.020
 traded+0.019
 Captain+0.017
 Cody+0.017
 pride+0.017
Neg logit contributions
we-0.023
elope-0.023
Ali-0.023
bes-0.022
ze-0.022
Token balls
Token ID11333
Feature activation+2.35e+00

Pos logit contributions
 gol+0.199
 traded+0.188
 Captain+0.187
 pride+0.177
 Cody+0.173
Neg logit contributions
elope-0.226
bes-0.223
comb-0.219
Ali-0.215
we-0.213
Token Tim
Token ID5045
Feature activation+1.32e-01

Pos logit contributions
 gol+0.020
 traded+0.020
 pride+0.018
 Captain+0.018
 Cody+0.017
Neg logit contributions
elope-0.029
comb-0.028
bes-0.027
Ali-0.027
we-0.027
Tokenmy
Token ID1820
Feature activation-2.88e-01

Pos logit contributions
 gol+0.005
 Captain+0.004
 traded+0.004
 Cody+0.004
 pride+0.004
Neg logit contributions
elope-0.009
Ali-0.008
bes-0.008
comb-0.008
we-0.008
Token always
Token ID1464
Feature activation+3.87e-01

Pos logit contributions
elope+0.016
bes+0.015
comb+0.015
zed+0.015
Ali+0.015
Neg logit contributions
 gol-0.013
 Captain-0.013
 traded-0.012
 Cody-0.012
 pride-0.011
Token remembered
Token ID12086
Feature activation-1.01e+00

Pos logit contributions
 gol+0.018
 Captain+0.017
 traded+0.016
 Cody+0.016
 pride+0.015
Neg logit contributions
elope-0.021
comb-0.020
bes-0.020
zed-0.020
Ali-0.020
Token how
Token ID703
Feature activation-1.04e-01

Pos logit contributions
elope+0.056
bes+0.054
we+0.054
comb+0.054
zed+0.053
Neg logit contributions
 gol-0.044
 traded-0.041
 Captain-0.039
 pride-0.037
 Cody-0.036
Token valuable
Token ID8119
Feature activation+5.59e+00

Pos logit contributions
elope+0.006
we+0.006
zed+0.006
Ali+0.005
bes+0.005
Neg logit contributions
 gol-0.004
 traded-0.004
 Captain-0.004
 pride-0.004
 Cody-0.004
Token he
Token ID339
Feature activation+4.25e-01

Pos logit contributions
 gol+0.240
 traded+0.236
 pride+0.218
 Captain+0.216
 Cody+0.205
Neg logit contributions
elope-0.316
bes-0.306
we-0.304
comb-0.298
Ali-0.297
Token was
Token ID373
Feature activation+7.70e-02

Pos logit contributions
 gol+0.020
 Captain+0.018
 traded+0.017
 Cody+0.017
 pride+0.017
Neg logit contributions
elope-0.023
bes-0.023
we-0.023
comb-0.022
zed-0.022
Token,
Token ID11
Feature activation-2.84e-02

Pos logit contributions
 gol+0.004
 Captain+0.003
 traded+0.003
 pride+0.003
 Cody+0.003
Neg logit contributions
elope-0.004
comb-0.004
bes-0.004
we-0.004
zed-0.004
Token even
Token ID772
Feature activation+4.20e-01

Pos logit contributions
elope+0.001
bes+0.001
comb+0.001
we+0.001
Ali+0.001
Neg logit contributions
 gol-0.001
 traded-0.001
 Captain-0.001
 Cody-0.001
 pride-0.001
Token when
Token ID618
Feature activation-7.32e-01

Pos logit contributions
 traded+0.021
 gol+0.020
 pride+0.019
 Cody+0.019
 Captain+0.019
Neg logit contributions
we-0.019
elope-0.018
comb-0.017
isa-0.017
 Pen-0.017
Token Every
Token ID3887
Feature activation+1.02e+00

Pos logit contributions
 gol+0.044
 traded+0.039
 Captain+0.038
 pride+0.035
 Cody+0.034
Neg logit contributions
elope-0.053
we-0.053
Ali-0.052
comb-0.051
bes-0.050
Token day
Token ID1110
Feature activation+1.81e+00

Pos logit contributions
 gol+0.040
 Captain+0.037
 traded+0.037
 pride+0.035
 Cody+0.034
Neg logit contributions
elope-0.062
bes-0.062
comb-0.061
Ali-0.060
we-0.059
Token it
Token ID340
Feature activation+1.90e+00

Pos logit contributions
 gol+0.077
 traded+0.070
 pride+0.068
 Captain+0.067
 Cody+0.061
Neg logit contributions
elope-0.105
bes-0.101
Ali-0.101
comb-0.100
we-0.099
Token would
Token ID561
Feature activation+1.16e+00

Pos logit contributions
 gol+0.087
 Captain+0.081
 traded+0.079
 pride+0.077
 Cody+0.075
Neg logit contributions
elope-0.105
bes-0.102
comb-0.102
Ali-0.099
we-0.099
Token mail
Token ID6920
Feature activation+3.96e+00

Pos logit contributions
 gol+0.051
 traded+0.049
 Captain+0.049
 pride+0.047
 Cody+0.045
Neg logit contributions
elope-0.064
bes-0.064
comb-0.062
we-0.061
Ali-0.061
Token letters
Token ID7475
Feature activation+5.55e+00

Pos logit contributions
 gol+0.197
 traded+0.174
 Captain+0.164
 Cody+0.158
 pride+0.153
Neg logit contributions
elope-0.210
comb-0.202
bes-0.202
we-0.199
Ali-0.190
Token to
Token ID284
Feature activation+1.89e+00

Pos logit contributions
 gol+0.285
 traded+0.258
 Captain+0.253
 pride+0.243
 Cody+0.239
Neg logit contributions
comb-0.279
elope-0.267
bes-0.261
we-0.260
Ali-0.243
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
 gol+0.086
 traded+0.079
 Captain+0.075
 pride+0.071
 Cody+0.071
Neg logit contributions
elope-0.105
bes-0.100
comb-0.100
Ali-0.098
we-0.097
Token people
Token ID661
Feature activation+3.21e+00

Pos logit contributions
 gol+0.087
 traded+0.087
 Captain+0.078
 Cody+0.078
 pride+0.078
Neg logit contributions
elope-0.081
comb-0.076
we-0.074
 cloud-0.072
bes-0.071
Token who
Token ID508
Feature activation+1.15e+00

Pos logit contributions
 gol+0.165
 Captain+0.153
 traded+0.153
 pride+0.148
 Cody+0.146
Neg logit contributions
elope-0.155
we-0.151
comb-0.150
bes-0.148
Ali-0.142
Token lived
Token ID5615
Feature activation+8.41e-01

Pos logit contributions
 gol+0.051
 Captain+0.046
 traded+0.044
 Cody+0.043
 pride+0.043
Neg logit contributions
elope-0.065
comb-0.062
bes-0.061
we-0.060
Ali-0.060
Token pond
Token ID16723
Feature activation-1.94e+00

Pos logit contributions
 gol+0.062
 Captain+0.059
 traded+0.059
 pride+0.056
 Cody+0.055
Neg logit contributions
elope-0.050
bes-0.049
comb-0.048
Ali-0.047
we-0.047
Token?"
Token ID1701
Feature activation+2.11e-01

Pos logit contributions
elope+0.120
bes+0.119
comb+0.117
Ali+0.116
we+0.115
Neg logit contributions
 gol-0.072
 Captain-0.068
 traded-0.068
 pride-0.063
 Cody-0.061
Token
Token ID198
Feature activation+6.17e-01

Pos logit contributions
 gol+0.009
 traded+0.009
 pride+0.008
 Captain+0.008
 Cody+0.008
Neg logit contributions
elope-0.012
bes-0.011
Ali-0.011
we-0.011
comb-0.011
Token
Token ID198
Feature activation+3.34e-01

Pos logit contributions
 gol+0.027
 traded+0.025
 Captain+0.025
 pride+0.024
 Cody+0.023
Neg logit contributions
elope-0.035
bes-0.034
Ali-0.034
we-0.033
zed-0.032
TokenThe
Token ID464
Feature activation+2.14e-01

Pos logit contributions
 gol+0.020
 Captain+0.019
 traded+0.019
 pride+0.019
 Cody+0.018
Neg logit contributions
elope-0.013
bes-0.013
Ali-0.012
comb-0.012
we-0.012
Token gol
Token ID43791
Feature activation+5.54e+00

Pos logit contributions
 online+0.008
 written+0.007
 pride+0.007
 traded+0.006
olded+0.006
Neg logit contributions
ich-0.011
 song-0.010
ggy-0.010
we-0.010
 cloud-0.010
Tokenfer
Token ID2232
Feature activation+5.51e-02

Pos logit contributions
 gol+0.359
 Captain+0.352
 traded+0.349
 pride+0.348
 Cody+0.333
Neg logit contributions
bes-0.182
elope-0.179
we-0.176
comb-0.170
Ali-0.165
Token replied
Token ID8712
Feature activation+4.10e-01

Pos logit contributions
 gol+0.002
 Captain+0.002
 traded+0.002
 pride+0.002
 Cody+0.002
Neg logit contributions
elope-0.003
bes-0.003
comb-0.003
Ali-0.003
we-0.003
Token,
Token ID11
Feature activation-1.85e-02

Pos logit contributions
 gol+0.017
 traded+0.016
 Captain+0.015
 pride+0.015
 Cody+0.014
Neg logit contributions
elope-0.024
bes-0.023
comb-0.023
we-0.023
zed-0.023
Token "
Token ID366
Feature activation-1.09e+00

Pos logit contributions
elope+0.001
bes+0.001
Ali+0.001
comb+0.001
we+0.001
Neg logit contributions
 gol-0.001
 Captain-0.001
 traded-0.001
 Cody-0.001
 pride-0.001
TokenI
Token ID40
Feature activation+1.02e+00

Pos logit contributions
elope+0.053
bes+0.052
comb+0.052
Ali+0.050
we+0.048
Neg logit contributions
 gol-0.057
 traded-0.054
 Captain-0.053
 pride-0.050
 Cody-0.050
Token around
Token ID1088
Feature activation+1.43e-01

Pos logit contributions
bes+0.041
elope+0.041
comb+0.040
we+0.040
Ali+0.039
Neg logit contributions
 gol-0.037
 traded-0.035
 Captain-0.034
 pride-0.034
 Cody-0.033
Token and
Token ID290
Feature activation+4.56e-02

Pos logit contributions
 gol+0.005
 Captain+0.005
 traded+0.004
 pride+0.004
 better+0.004
Neg logit contributions
bes-0.010
elope-0.009
comb-0.009
Ali-0.009
zed-0.009
Token pe
Token ID613
Feature activation+2.12e+00

Pos logit contributions
 gol+0.002
 Captain+0.002
 traded+0.002
 pride+0.002
 Cody+0.002
Neg logit contributions
elope-0.002
bes-0.002
we-0.002
Ali-0.002
comb-0.002
Tokencking
Token ID44377
Feature activation-2.41e+00

Pos logit contributions
 traded+0.119
 gol+0.119
 Captain+0.116
 Cody+0.108
 pride+0.107
Neg logit contributions
elope-0.085
comb-0.085
bes-0.081
Ali-0.078
Pen-0.077
Token each
Token ID1123
Feature activation+3.37e-01

Pos logit contributions
elope+0.132
we+0.127
Ali+0.126
bes+0.126
comb+0.121
Neg logit contributions
 gol-0.106
 traded-0.098
 Captain-0.095
 Cody-0.091
 pride-0.084
Token other
Token ID584
Feature activation+5.33e+00

Pos logit contributions
 gol+0.010
 Captain+0.009
 traded+0.009
 pride+0.008
 chalk+0.008
Neg logit contributions
bes-0.024
elope-0.024
comb-0.024
we-0.023
Ali-0.022
Token.
Token ID13
Feature activation-3.99e-01

Pos logit contributions
 gol+0.213
 Captain+0.204
 traded+0.203
 pride+0.194
 Cody+0.186
Neg logit contributions
elope-0.311
bes-0.309
comb-0.303
Ali-0.298
we-0.296
Token
Token ID198
Feature activation+9.56e-02

Pos logit contributions
elope+0.022
bes+0.021
Ali+0.021
comb+0.020
we+0.020
Neg logit contributions
 gol-0.018
 traded-0.016
 pride-0.016
 Captain-0.016
 Cody-0.015
Token
Token ID198
Feature activation-1.18e-01

Pos logit contributions
 gol+0.003
 Captain+0.003
 traded+0.003
 pride+0.003
 Cody+0.003
Neg logit contributions
elope-0.006
bes-0.006
comb-0.006
Ali-0.006
we-0.006
TokenThe
Token ID464
Feature activation-1.82e-01

Pos logit contributions
elope+0.006
comb+0.006
bes+0.006
we+0.005
Ali+0.005
Neg logit contributions
 gol-0.006
 traded-0.006
 Captain-0.006
 pride-0.005
 Cody-0.005
Token chickens
Token ID25972
Feature activation-1.67e+00

Pos logit contributions
bes+0.010
elope+0.010
comb+0.009
Ali+0.009
we+0.009
Neg logit contributions
 Captain-0.008
 better-0.008
 pride-0.008
 traded-0.008
 gol-0.008
Token frowned
Token ID32198
Feature activation+4.46e-01

Pos logit contributions
elope+0.042
comb+0.041
bes+0.040
Ali+0.039
we+0.039
Neg logit contributions
 gol-0.030
 Captain-0.028
 pride-0.026
 traded-0.026
 Cody-0.025
Token when
Token ID618
Feature activation-5.75e-02

Pos logit contributions
 gol+0.018
 Captain+0.017
 traded+0.017
 pride+0.016
 Cody+0.016
Neg logit contributions
elope-0.026
bes-0.026
comb-0.025
Ali-0.025
we-0.025
Token she
Token ID673
Feature activation+1.26e+00

Pos logit contributions
bes+0.004
elope+0.004
comb+0.004
Ali+0.003
we+0.003
Neg logit contributions
 gol-0.002
 Captain-0.002
 traded-0.002
 pride-0.002
 Cody-0.002
Token noticed
Token ID6810
Feature activation-2.99e-01

Pos logit contributions
 gol+0.051
 Captain+0.048
 traded+0.046
 pride+0.045
 Cody+0.043
Neg logit contributions
elope-0.075
bes-0.074
comb-0.073
Ali-0.072
we-0.071
Token how
Token ID703
Feature activation+4.46e-01

Pos logit contributions
elope+0.016
bes+0.016
we+0.016
comb+0.016
Ali+0.016
Neg logit contributions
 gol-0.014
 traded-0.013
 Captain-0.012
 pride-0.012
 Cody-0.011
Token expensive
Token ID5789
Feature activation+5.32e+00

Pos logit contributions
 gol+0.019
 Captain+0.018
 traded+0.017
 Cody+0.016
 pride+0.016
Neg logit contributions
bes-0.025
elope-0.024
we-0.024
zed-0.024
Ali-0.023
Token some
Token ID617
Feature activation+3.45e-01

Pos logit contributions
 gol+0.258
 traded+0.237
 Captain+0.236
 pride+0.224
 Cody+0.208
Neg logit contributions
bes-0.272
we-0.263
elope-0.262
comb-0.257
 Pen-0.246
Token of
Token ID286
Feature activation+7.42e-01

Pos logit contributions
 gol+0.016
 Captain+0.015
 traded+0.014
 Cody+0.013
 pride+0.013
Neg logit contributions
bes-0.019
elope-0.018
we-0.018
comb-0.018
zed-0.017
Token them
Token ID606
Feature activation+1.64e+00

Pos logit contributions
 gol+0.031
 traded+0.029
 Captain+0.029
 pride+0.026
 Cody+0.026
Neg logit contributions
bes-0.042
elope-0.042
comb-0.040
Ali-0.040
we-0.040
Token were
Token ID547
Feature activation-3.26e-01

Pos logit contributions
 gol+0.080
 Captain+0.075
 traded+0.071
 pride+0.069
 Cody+0.067
Neg logit contributions
bes-0.085
elope-0.085
comb-0.084
we-0.082
zed-0.079
Token.
Token ID13
Feature activation+1.32e-02

Pos logit contributions
bes+0.015
comb+0.015
we+0.014
elope+0.014
zed+0.013
Neg logit contributions
 gol-0.018
 Captain-0.017
 traded-0.016
 pride-0.016
 Cody-0.015
Token them
Token ID606
Feature activation+1.08e+00

Pos logit contributions
elope+0.069
bes+0.069
comb+0.067
we+0.067
Ali+0.066
Neg logit contributions
 gol-0.044
 traded-0.041
 Captain-0.040
 pride-0.038
 Cody-0.037
Token tw
Token ID665
Feature activation+1.03e+00

Pos logit contributions
 gol+0.053
 Captain+0.050
 traded+0.049
 pride+0.047
 Cody+0.047
Neg logit contributions
elope-0.054
bes-0.053
comb-0.052
we-0.052
Ali-0.051
Tokenirl
Token ID1901
Feature activation-1.99e-01

Pos logit contributions
 gol+0.064
 Captain+0.062
 traded+0.062
 pride+0.059
 Cody+0.058
Neg logit contributions
elope-0.038
bes-0.038
comb-0.037
Ali-0.036
we-0.036
Token around
Token ID1088
Feature activation+1.84e-01

Pos logit contributions
bes+0.009
elope+0.009
we+0.009
comb+0.009
Ali+0.009
Neg logit contributions
 gol-0.010
 Captain-0.010
 traded-0.010
 pride-0.009
 Cody-0.009
Token each
Token ID1123
Feature activation+1.66e-01

Pos logit contributions
 Captain+0.006
 gol+0.006
 traded+0.005
 better+0.005
 Cody+0.005
Neg logit contributions
elope-0.012
bes-0.012
Ali-0.012
comb-0.012
zed-0.011
Token other
Token ID584
Feature activation+5.29e+00

Pos logit contributions
 gol+0.004
 Captain+0.004
 traded+0.004
 pride+0.004
 Cody+0.003
Neg logit contributions
bes-0.012
elope-0.012
comb-0.012
we-0.012
Ali-0.012
Token.
Token ID13
Feature activation-3.22e-01

Pos logit contributions
 gol+0.208
 Captain+0.200
 traded+0.199
 pride+0.190
 Cody+0.181
Neg logit contributions
bes-0.305
elope-0.305
Ali-0.301
comb-0.298
zed-0.294
Token Annie
Token ID25860
Feature activation-2.88e+00

Pos logit contributions
elope+0.020
bes+0.020
comb+0.019
Ali+0.019
we+0.019
Neg logit contributions
 gol-0.012
 Captain-0.012
 traded-0.012
 pride-0.011
 Cody-0.011
Token's
Token ID338
Feature activation+1.13e-01

Pos logit contributions
elope+0.159
bes+0.158
comb+0.157
Ali+0.152
we+0.152
Neg logit contributions
 gol-0.125
 traded-0.121
 Captain-0.118
 pride-0.112
 Cody-0.109
Token mother
Token ID2802
Feature activation-8.51e-01

Pos logit contributions
 gol+0.005
 Captain+0.005
 traded+0.005
 online+0.004
 Cody+0.004
Neg logit contributions
bes-0.006
elope-0.006
 chin-0.006
we-0.005
comb-0.005
Token called
Token ID1444
Feature activation+3.34e+00

Pos logit contributions
elope+0.047
Ali+0.045
bes+0.045
we+0.044
comb+0.044
Neg logit contributions
 gol-0.040
 Captain-0.036
 pride-0.035
 traded-0.035
 Cody-0.033
Token accidentally
Token ID14716
Feature activation+2.43e+00

Pos logit contributions
elope+0.000
Ali+0.000
comb+0.000
bes+0.000
we+0.000
Neg logit contributions
 gol-0.000
 Captain-0.000
 pride-0.000
 Cody-0.000
 traded-0.000
Token touched
Token ID12615
Feature activation+8.82e-01

Pos logit contributions
 gol+0.115
 Captain+0.108
 traded+0.105
 pride+0.102
 Cody+0.099
Neg logit contributions
bes-0.127
elope-0.127
comb-0.125
Ali-0.123
we-0.122
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
 gol+0.036
 traded+0.033
 Captain+0.033
 pride+0.031
 Cody+0.030
Neg logit contributions
elope-0.053
bes-0.052
comb-0.051
Ali-0.051
we-0.050
Token light
Token ID1657
Feature activation+1.69e+00

Pos logit contributions
 gol+0.084
 traded+0.081
 Captain+0.080
 Cody+0.077
 pride+0.075
Neg logit contributions
elope-0.055
bes-0.055
comb-0.053
we-0.052
Ali-0.052
Tokenbul
Token ID15065
Feature activation+2.24e+00

Pos logit contributions
 gol+0.072
 Captain+0.069
 traded+0.069
 pride+0.065
 Cody+0.062
Neg logit contributions
elope-0.095
bes-0.094
comb-0.091
Ali-0.090
we-0.088
Tokenb
Token ID65
Feature activation+5.25e+00

Pos logit contributions
 gol+0.109
 Captain+0.104
 traded+0.103
 Cody+0.097
 pride+0.096
Neg logit contributions
we-0.120
bes-0.117
elope-0.115
Ali-0.114
comb-0.111
Token and
Token ID290
Feature activation+8.22e-01

Pos logit contributions
 gol+0.268
 Captain+0.260
 traded+0.258
 pride+0.249
 Cody+0.242
Neg logit contributions
elope-0.249
bes-0.244
comb-0.239
Ali-0.232
we-0.227
Token it
Token ID340
Feature activation+8.02e-01

Pos logit contributions
 gol+0.040
 Captain+0.037
 traded+0.036
 pride+0.035
 Cody+0.035
Neg logit contributions
elope-0.042
bes-0.041
comb-0.041
we-0.041
Ali-0.040
Token was
Token ID373
Feature activation+3.04e-02

Pos logit contributions
 gol+0.030
 traded+0.030
 Captain+0.028
 pride+0.027
 better+0.026
Neg logit contributions
elope-0.049
bes-0.048
comb-0.047
Ali-0.046
we-0.045
Token very
Token ID845
Feature activation-5.68e-02

Pos logit contributions
 gol+0.001
 Captain+0.001
 traded+0.001
 pride+0.001
 Cody+0.001
Neg logit contributions
elope-0.002
bes-0.002
comb-0.002
Ali-0.002
we-0.002
Token hot
Token ID3024
Feature activation-1.46e+00

Pos logit contributions
elope+0.003
comb+0.003
bes+0.003
Ali+0.003
 web+0.003
Neg logit contributions
 gol-0.003
 Captain-0.003
 traded-0.003
 Cody-0.003
 pride-0.003
Token her
Token ID607
Feature activation-2.07e-01

Pos logit contributions
 gol+0.032
 Captain+0.030
 traded+0.030
 pride+0.028
 Cody+0.027
Neg logit contributions
elope-0.046
bes-0.046
comb-0.045
Ali-0.044
we-0.044
Token arms
Token ID5101
Feature activation-2.36e-01

Pos logit contributions
we+0.009
comb+0.009
iders+0.009
Ali+0.009
bes+0.009
Neg logit contributions
 pride-0.011
 traded-0.011
 gol-0.010
 Captain-0.010
 chalk-0.010
Token.
Token ID13
Feature activation+3.23e-01

Pos logit contributions
comb+0.012
elope+0.012
bes+0.012
we+0.012
Ali+0.011
Neg logit contributions
 gol-0.011
 Captain-0.011
 traded-0.010
 pride-0.010
 Cody-0.010
Token As
Token ID1081
Feature activation-3.29e-01

Pos logit contributions
 gol+0.017
 traded+0.015
 Captain+0.015
 pride+0.014
vious+0.013
Neg logit contributions
elope-0.016
bes-0.016
 Pen-0.015
Ali-0.015
comb-0.015
Token she
Token ID673
Feature activation+9.81e-01

Pos logit contributions
elope+0.016
Ali+0.015
comb+0.015
bes+0.015
 Pen+0.015
Neg logit contributions
 gol-0.017
 traded-0.016
 Captain-0.015
vious-0.014
 pride-0.014
Token mar
Token ID1667
Feature activation+5.24e+00

Pos logit contributions
 gol+0.040
 traded+0.039
 Captain+0.037
 pride+0.035
 Cody+0.034
Neg logit contributions
elope-0.057
comb-0.057
bes-0.056
Ali-0.054
we-0.054
Tokenached
Token ID2317
Feature activation+1.70e+00

Pos logit contributions
 gol+0.263
 traded+0.255
 Captain+0.248
 pride+0.241
 Cody+0.233
Neg logit contributions
elope-0.257
bes-0.248
comb-0.243
Ali-0.239
we-0.235
Token away
Token ID1497
Feature activation+2.07e+00

Pos logit contributions
 gol+0.068
 Captain+0.064
 traded+0.064
 pride+0.060
 Cody+0.058
Neg logit contributions
elope-0.101
bes-0.100
comb-0.098
Ali-0.097
we-0.096
Token from
Token ID422
Feature activation+1.30e+00

Pos logit contributions
 gol+0.073
 Captain+0.068
 traded+0.068
 pride+0.063
 Cody+0.061
Neg logit contributions
elope-0.133
bes-0.132
comb-0.130
Ali-0.128
we-0.127
Token the
Token ID262
Feature activation+1.43e-01

Pos logit contributions
 gol+0.060
 traded+0.058
 Captain+0.054
 pride+0.051
 Cody+0.050
Neg logit contributions
elope-0.071
bes-0.067
comb-0.067
Ali-0.066
we-0.065
Token garden
Token ID11376
Feature activation-1.48e+00

Pos logit contributions
 gol+0.008
 traded+0.008
 Captain+0.007
 pride+0.007
 better+0.007
Neg logit contributions
bes-0.006
elope-0.006
Ali-0.006
we-0.006
comb-0.006
Token restore
Token ID11169
Feature activation+2.78e-01

Pos logit contributions
 gol+0.032
 traded+0.028
vious+0.028
 Cody+0.027
 Captain+0.027
Neg logit contributions
elope-0.035
comb-0.034
bes-0.032
zed-0.031
we-0.031
Token it
Token ID340
Feature activation+1.37e-01

Pos logit contributions
 gol+0.015
 traded+0.014
vious+0.012
 pride+0.012
 Captain+0.012
Neg logit contributions
elope-0.013
we-0.012
bes-0.012
eds-0.011
comb-0.011
Token back
Token ID736
Feature activation+4.16e-01

Pos logit contributions
 gol+0.007
 Captain+0.007
 traded+0.006
 Cody+0.006
 pride+0.006
Neg logit contributions
elope-0.007
comb-0.007
bes-0.007
we-0.006
zed-0.006
Token to
Token ID284
Feature activation+3.56e-01

Pos logit contributions
 gol+0.018
 Captain+0.017
 traded+0.017
 Cody+0.015
 pride+0.015
Neg logit contributions
elope-0.024
bes-0.023
comb-0.023
we-0.023
Ali-0.022
Token its
Token ID663
Feature activation+1.56e-01

Pos logit contributions
 gol+0.015
 traded+0.014
 Captain+0.013
 pride+0.012
 Cody+0.012
Neg logit contributions
elope-0.021
bes-0.020
comb-0.020
zed-0.020
we-0.020
Token rightful
Token ID43133
Feature activation+5.24e+00

Pos logit contributions
 gol+0.008
 traded+0.007
 Captain+0.007
 Cody+0.007
 pride+0.007
Neg logit contributions
elope-0.008
comb-0.008
bes-0.008
Ali-0.007
we-0.007
Token place
Token ID1295
Feature activation-6.32e-01

Pos logit contributions
 gol+0.220
 traded+0.217
 pride+0.217
 Captain+0.215
 Cody+0.199
Neg logit contributions
bes-0.280
Ali-0.277
we-0.276
comb-0.274
elope-0.265
Token.
Token ID13
Feature activation+7.55e-04

Pos logit contributions
elope+0.032
bes+0.032
comb+0.031
we+0.030
Ali+0.030
Neg logit contributions
 gol-0.031
 Captain-0.029
 traded-0.029
 pride-0.028
 Cody-0.027
Token Although
Token ID4900
Feature activation-8.57e-01

Pos logit contributions
 gol+0.000
 traded+0.000
 Captain+0.000
 pride+0.000
 Cody+0.000
Neg logit contributions
elope-0.000
Ali-0.000
bes-0.000
comb-0.000
zed-0.000
Token Sammy
Token ID44067
Feature activation+4.77e-01

Pos logit contributions
elope+0.049
we+0.047
zed+0.046
comb+0.045
bes+0.045
Neg logit contributions
 gol-0.034
 traded-0.033
 pride-0.030
 Captain-0.029
 online-0.029
Token was
Token ID373
Feature activation+5.71e-01

Pos logit contributions
 gol+0.022
 Captain+0.021
 traded+0.021
 pride+0.020
 Cody+0.019
Neg logit contributions
elope-0.026
bes-0.025
comb-0.025
Ali-0.024
we-0.024
Token he
Token ID339
Feature activation+8.94e-01

Pos logit contributions
elope+0.023
we+0.023
zed+0.023
Ali+0.023
comb+0.022
Neg logit contributions
 gol-0.019
 traded-0.017
 Captain-0.016
 pride-0.016
 Cody-0.015
Token got
Token ID1392
Feature activation+3.82e-02

Pos logit contributions
 gol+0.043
 Captain+0.040
 pride+0.037
 Cody+0.037
 traded+0.035
Neg logit contributions
elope-0.049
bes-0.047
comb-0.046
we-0.046
zed-0.045
Token it
Token ID340
Feature activation-1.24e-02

Pos logit contributions
 gol+0.002
 Captain+0.002
 Cody+0.002
umbo+0.002
 Loyal+0.002
Neg logit contributions
we-0.002
zed-0.002
ze-0.002
elope-0.002
comb-0.001
Token so
Token ID523
Feature activation+1.15e+00

Pos logit contributions
comb+0.001
elope+0.001
bes+0.001
we+0.001
zed+0.001
Neg logit contributions
 gol-0.001
 Captain-0.001
 traded-0.001
 pride-0.001
 Cody-0.001
Token the
Token ID262
Feature activation+2.78e-01

Pos logit contributions
 gol+0.056
 Captain+0.054
 Cody+0.049
 traded+0.048
 pride+0.047
Neg logit contributions
elope-0.057
comb-0.055
bes-0.055
we-0.054
zed-0.054
Token rightful
Token ID43133
Feature activation+5.22e+00

Pos logit contributions
 gol+0.014
 traded+0.014
 Captain+0.013
 pride+0.013
 Cody+0.013
Neg logit contributions
elope-0.013
comb-0.013
we-0.012
bes-0.012
 Pen-0.012
Token owner
Token ID4870
Feature activation+2.14e+00

Pos logit contributions
 gol+0.219
 traded+0.215
 Captain+0.204
 pride+0.204
 Cody+0.191
Neg logit contributions
bes-0.289
Ali-0.282
comb-0.278
we-0.274
elope-0.273
Token could
Token ID714
Feature activation+1.28e+00

Pos logit contributions
 gol+0.101
 Captain+0.094
 Cody+0.088
 traded+0.086
 pride+0.086
Neg logit contributions
elope-0.116
comb-0.112
bes-0.111
we-0.111
zed-0.107
Token find
Token ID1064
Feature activation+1.64e-01

Pos logit contributions
 gol+0.055
 Captain+0.052
 traded+0.051
 pride+0.049
 Cody+0.048
Neg logit contributions
elope-0.072
bes-0.071
comb-0.071
Ali-0.068
we-0.068
Token it
Token ID340
Feature activation-3.07e-01

Pos logit contributions
 gol+0.009
 traded+0.008
 Captain+0.007
 Cody+0.007
 pride+0.007
Neg logit contributions
elope-0.008
we-0.008
zed-0.008
comb-0.007
 Pen-0.007
Token.
Token ID13
Feature activation-1.47e-02

Pos logit contributions
elope+0.015
comb+0.015
bes+0.015
we+0.014
zed+0.014
Neg logit contributions
 gol-0.016
 Captain-0.015
 traded-0.015
 pride-0.014
 Cody-0.014
Token a
Token ID257
Feature activation+1.36e-01

Pos logit contributions
 gol+0.045
 traded+0.042
 Captain+0.042
 pride+0.039
 Cody+0.038
Neg logit contributions
elope-0.062
bes-0.059
comb-0.058
Ali-0.058
 Pen-0.056
Token hairy
Token ID43873
Feature activation-2.88e-01

Pos logit contributions
 gol+0.006
 Captain+0.005
 traded+0.005
 pride+0.005
 Cody+0.005
Neg logit contributions
bes-0.008
elope-0.008
comb-0.008
we-0.008
Ali-0.008
Token palace
Token ID20562
Feature activation-5.72e-01

Pos logit contributions
bes+0.013
elope+0.013
comb+0.013
we+0.013
Ali+0.012
Neg logit contributions
 gol-0.016
 Captain-0.015
 traded-0.015
 Cody-0.014
 pride-0.014
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
Ali+0.040
bes+0.039
Pen+0.038
comb+0.038
elope+0.038
Neg logit contributions
 gol-0.017
 traded-0.016
 Captain-0.016
 online-0.013
 chalk-0.013
Token Everywhere
Token ID48201
Feature activation+2.38e+00

Pos logit contributions
 gol+0.005
 Captain+0.004
 traded+0.004
 pride+0.004
 Cody+0.004
Neg logit contributions
bes-0.010
we-0.010
elope-0.010
comb-0.010
Ali-0.009
Token you
Token ID345
Feature activation+5.22e+00

Pos logit contributions
 gol+0.094
 Captain+0.089
 traded+0.089
 pride+0.083
 Cody+0.081
Neg logit contributions
elope-0.142
bes-0.142
comb-0.139
Ali-0.136
we-0.136
Token looked
Token ID3114
Feature activation+4.41e-01

Pos logit contributions
 gol+0.261
 Captain+0.237
 Cody+0.229
 traded+0.224
 pride+0.222
Neg logit contributions
elope-0.274
comb-0.271
bes-0.262
zed-0.254
Ali-0.254
Token there
Token ID612
Feature activation+3.20e-01

Pos logit contributions
 gol+0.021
 traded+0.019
 Captain+0.018
 pride+0.018
 Cody+0.017
Neg logit contributions
bes-0.024
elope-0.024
we-0.024
zed-0.023
comb-0.023
Token were
Token ID547
Feature activation+9.71e-01

Pos logit contributions
 gol+0.014
 traded+0.013
 Captain+0.013
 pride+0.012
 Cody+0.012
Neg logit contributions
elope-0.018
bes-0.018
comb-0.018
Ali-0.017
we-0.017
Token furry
Token ID40857
Feature activation-1.83e-01

Pos logit contributions
 gol+0.044
 Captain+0.039
 traded+0.037
 pride+0.036
 Cody+0.035
Neg logit contributions
elope-0.054
bes-0.054
we-0.053
comb-0.052
Ali-0.052
Token walls
Token ID7714
Feature activation+6.52e-01

Pos logit contributions
elope+0.009
bes+0.009
comb+0.008
we+0.008
Ali+0.008
Neg logit contributions
 gol-0.009
 traded-0.009
 Captain-0.009
 pride-0.008
 Cody-0.008
Token as
Token ID355
Feature activation+8.33e-01

Pos logit contributions
 gol+0.026
 Captain+0.024
 traded+0.024
 pride+0.023
 Cody+0.022
Neg logit contributions
elope-0.033
bes-0.032
comb-0.032
Ali-0.032
we-0.031
Token he
Token ID339
Feature activation+1.13e+00

Pos logit contributions
 gol+0.038
 traded+0.036
 pride+0.033
 Captain+0.032
vious+0.031
Neg logit contributions
elope-0.046
Ali-0.044
we-0.044
zed-0.044
comb-0.044
Token opened
Token ID4721
Feature activation+6.09e-01

Pos logit contributions
 gol+0.049
 Captain+0.046
 traded+0.044
 pride+0.043
 Cody+0.042
Neg logit contributions
elope-0.065
bes-0.064
comb-0.062
Ali-0.062
we-0.061
Token the
Token ID262
Feature activation+1.32e+00

Pos logit contributions
 gol+0.027
 traded+0.025
 Captain+0.024
 pride+0.022
 Cody+0.022
Neg logit contributions
elope-0.034
bes-0.034
Ali-0.032
comb-0.032
we-0.032
Token ch
Token ID442
Feature activation+1.03e+00

Pos logit contributions
 gol+0.084
 traded+0.081
 Captain+0.078
 Cody+0.076
 Loyal+0.073
Neg logit contributions
elope-0.045
comb-0.044
 web-0.044
bes-0.043
 cloud-0.041
Tokenocol
Token ID4668
Feature activation+5.22e+00

Pos logit contributions
 gol+0.045
 traded+0.043
 Captain+0.043
 pride+0.040
 Cody+0.040
Neg logit contributions
elope-0.056
bes-0.056
comb-0.055
Ali-0.054
we-0.054
Tokenates
Token ID689
Feature activation+8.60e-01

Pos logit contributions
 gol+0.315
 Captain+0.303
 traded+0.303
 pride+0.291
 Cody+0.285
Neg logit contributions
elope-0.202
bes-0.199
comb-0.193
Ali-0.189
we-0.186
Token and
Token ID290
Feature activation+5.21e-01

Pos logit contributions
 gol+0.039
 traded+0.037
 Captain+0.037
 pride+0.035
 Cody+0.034
Neg logit contributions
elope-0.046
bes-0.046
comb-0.046
we-0.044
Ali-0.044
Token started
Token ID2067
Feature activation+2.16e-01

Pos logit contributions
 gol+0.024
 traded+0.021
 Captain+0.021
 pride+0.021
 Cody+0.020
Neg logit contributions
elope-0.028
comb-0.027
bes-0.027
Ali-0.026
we-0.026
Token eating
Token ID6600
Feature activation-1.19e+00

Pos logit contributions
 gol+0.009
 Captain+0.009
 traded+0.009
 pride+0.008
 Cody+0.008
Neg logit contributions
elope-0.012
bes-0.012
comb-0.012
Ali-0.012
we-0.012
Token them
Token ID606
Feature activation+6.16e-01

Pos logit contributions
bes+0.064
elope+0.063
comb+0.063
we+0.061
Ali+0.060
Neg logit contributions
 gol-0.055
 traded-0.051
 Captain-0.048
 pride-0.046
 Cody-0.045
Token was
Token ID373
Feature activation-2.42e-01

Pos logit contributions
elope+0.001
bes+0.001
comb+0.001
Ali+0.001
we+0.001
Neg logit contributions
 gol-0.001
 traded-0.001
 Captain-0.001
 pride-0.001
 Cody-0.001
Token very
Token ID845
Feature activation-3.98e-01

Pos logit contributions
elope+0.012
Ali+0.012
bes+0.012
 Pen+0.012
zed+0.012
Neg logit contributions
 gol-0.011
 traded-0.010
 Captain-0.010
 Cody-0.010
 pride-0.010
Token blue
Token ID4171
Feature activation-4.23e-01

Pos logit contributions
elope+0.018
 Pen+0.017
Ali+0.017
 cloud+0.017
Pen+0.016
Neg logit contributions
 gol-0.020
 traded-0.019
 Cody-0.018
viously-0.018
 Captain-0.018
Token.
Token ID13
Feature activation+3.82e-02

Pos logit contributions
bes+0.028
Ali+0.028
elope+0.027
zed+0.027
comb+0.026
Neg logit contributions
 gol-0.015
 traded-0.014
 Captain-0.013
 Cody-0.012
 chalk-0.012
Token Everywhere
Token ID48201
Feature activation+2.36e+00

Pos logit contributions
 gol+0.002
 traded+0.002
 Captain+0.001
 pride+0.001
 Cody+0.001
Neg logit contributions
elope-0.002
bes-0.002
Ali-0.002
comb-0.002
 Pen-0.002
Token you
Token ID345
Feature activation+5.17e+00

Pos logit contributions
 gol+0.106
 pride+0.098
 Captain+0.096
 traded+0.096
 Cody+0.089
Neg logit contributions
elope-0.130
Ali-0.125
we-0.121
bes-0.120
 Pen-0.119
Token looked
Token ID3114
Feature activation+3.06e-01

Pos logit contributions
 gol+0.238
 Captain+0.221
 Cody+0.215
 traded+0.206
 pride+0.204
Neg logit contributions
elope-0.279
comb-0.270
Ali-0.263
zed-0.260
bes-0.260
Token,
Token ID11
Feature activation+1.98e+00

Pos logit contributions
 gol+0.014
 traded+0.013
 Captain+0.012
 pride+0.012
 Cody+0.011
Neg logit contributions
elope-0.017
bes-0.017
we-0.017
Ali-0.016
zed-0.016
Token it
Token ID340
Feature activation+7.34e-01

Pos logit contributions
 gol+0.096
 traded+0.091
 Captain+0.086
 pride+0.084
 Cody+0.081
Neg logit contributions
elope-0.099
we-0.097
bes-0.096
Ali-0.096
comb-0.094
Token was
Token ID373
Feature activation+9.17e-01

Pos logit contributions
 gol+0.034
 Captain+0.032
 traded+0.031
 pride+0.030
 Cody+0.030
Neg logit contributions
elope-0.040
bes-0.039
we-0.039
Ali-0.038
comb-0.038
Token painted
Token ID13055
Feature activation+1.08e+00

Pos logit contributions
 gol+0.044
 traded+0.039
 Captain+0.038
 Cody+0.037
 pride+0.037
Neg logit contributions
elope-0.048
bes-0.046
we-0.045
Ali-0.045
comb-0.044
Token,
Token ID11
Feature activation+6.95e-01

Pos logit contributions
 gol+0.064
 Captain+0.060
 traded+0.059
 pride+0.057
 Cody+0.055
Neg logit contributions
comb-0.068
elope-0.068
bes-0.068
we-0.066
Ali-0.064
Token cup
Token ID6508
Feature activation-9.96e-02

Pos logit contributions
 gol+0.033
 Captain+0.030
 traded+0.030
 pride+0.029
 Cody+0.028
Neg logit contributions
bes-0.036
elope-0.036
comb-0.035
we-0.034
Ali-0.034
Tokencakes
Token ID37263
Feature activation+5.49e-01

Pos logit contributions
elope+0.006
bes+0.006
comb+0.005
we+0.005
Ali+0.005
Neg logit contributions
 gol-0.004
 Captain-0.004
 traded-0.004
 pride-0.004
 Cody-0.004
Token and
Token ID290
Feature activation+8.49e-01

Pos logit contributions
 gol+0.022
 Captain+0.021
 traded+0.021
 pride+0.019
 Cody+0.019
Neg logit contributions
elope-0.033
bes-0.032
comb-0.032
Ali-0.031
we-0.031
Token ch
Token ID442
Feature activation+9.87e-01

Pos logit contributions
 gol+0.041
 Captain+0.038
 pride+0.035
 traded+0.035
 Cody+0.033
Neg logit contributions
bes-0.044
elope-0.043
we-0.042
comb-0.042
Ali-0.041
Tokenocol
Token ID4668
Feature activation+5.17e+00

Pos logit contributions
 gol+0.043
 Captain+0.043
 traded+0.040
 Cody+0.038
 pride+0.038
Neg logit contributions
bes-0.054
elope-0.053
we-0.052
Ali-0.051
comb-0.051
Tokenates
Token ID689
Feature activation+4.19e-01

Pos logit contributions
 gol+0.320
 Captain+0.308
 traded+0.307
 pride+0.295
 Cody+0.290
Neg logit contributions
elope-0.194
bes-0.192
comb-0.187
we-0.181
Ali-0.181
Token.
Token ID13
Feature activation+2.01e-01

Pos logit contributions
 gol+0.019
 Captain+0.018
 traded+0.018
 pride+0.017
 Cody+0.017
Neg logit contributions
elope-0.022
bes-0.022
comb-0.022
we-0.021
Ali-0.021
Token
Token ID220
Feature activation+3.67e-01

Pos logit contributions
 gol+0.009
 pride+0.008
 traded+0.008
vious+0.008
 Captain+0.008
Neg logit contributions
elope-0.010
bes-0.010
 Pen-0.009
zed-0.009
Ali-0.009
Token
Token ID198
Feature activation+2.36e-01

Pos logit contributions
 gol+0.018
 traded+0.017
 Captain+0.016
 pride+0.016
 Cody+0.015
Neg logit contributions
elope-0.019
bes-0.019
we-0.018
Ali-0.018
comb-0.017
Token
Token ID198
Feature activation-6.40e-02

Pos logit contributions
 gol+0.012
 pride+0.011
 traded+0.011
 Captain+0.011
vious+0.010
Neg logit contributions
elope-0.011
bes-0.011
Ali-0.011
we-0.011
Pen-0.011
Token He
Token ID679
Feature activation+6.34e-01

Pos logit contributions
 gol+0.013
 traded+0.013
 pride+0.012
vious+0.012
 better+0.011
Neg logit contributions
elope-0.014
Ali-0.014
bes-0.014
 Pen-0.013
zed-0.013
Token quickly
Token ID2952
Feature activation+1.41e-01

Pos logit contributions
 gol+0.027
 Captain+0.026
 traded+0.025
 pride+0.024
 Cody+0.024
Neg logit contributions
elope-0.036
bes-0.036
comb-0.035
Ali-0.035
we-0.035
Token hung
Token ID9174
Feature activation+2.10e+00

Pos logit contributions
 gol+0.007
 Captain+0.007
 Cody+0.006
 pride+0.006
 traded+0.006
Neg logit contributions
bes-0.007
comb-0.007
elope-0.007
zed-0.007
Ali-0.007
Token colorful
Token ID20239
Feature activation+3.08e+00

Pos logit contributions
 gol+0.099
 traded+0.091
 Captain+0.085
 pride+0.083
 Cody+0.080
Neg logit contributions
bes-0.113
comb-0.109
we-0.108
elope-0.108
Ali-0.107
Token or
Token ID393
Feature activation+1.76e+00

Pos logit contributions
 gol+0.154
 traded+0.146
 Captain+0.141
 Cody+0.137
 pride+0.133
Neg logit contributions
bes-0.158
we-0.155
comb-0.147
elope-0.146
Ali-0.140
Tokennam
Token ID7402
Feature activation+5.16e+00

Pos logit contributions
 gol+0.096
 traded+0.081
 Captain+0.081
 Loyal+0.076
umbo+0.076
Neg logit contributions
bes-0.082
we-0.081
 chin-0.079
comb-0.077
Ali-0.076
Tokenents
Token ID658
Feature activation+2.00e+00

Pos logit contributions
 gol+0.195
 traded+0.184
 Captain+0.180
 pride+0.173
 Cody+0.166
Neg logit contributions
elope-0.318
bes-0.315
comb-0.309
Ali-0.304
we-0.301
Token and
Token ID290
Feature activation+8.82e-01

Pos logit contributions
 gol+0.086
 Captain+0.080
 traded+0.079
 pride+0.076
 Cody+0.074
Neg logit contributions
comb-0.114
elope-0.113
bes-0.113
we-0.111
Ali-0.109
Token tw
Token ID665
Feature activation+1.22e+00

Pos logit contributions
 gol+0.043
 Captain+0.038
 Cody+0.036
vious+0.035
 traded+0.035
Neg logit contributions
bes-0.045
we-0.044
comb-0.044
elope-0.044
Ali-0.043
Tokenink
Token ID676
Feature activation-1.59e+00

Pos logit contributions
 gol+0.079
 traded+0.076
 Captain+0.076
 pride+0.073
 Cody+0.072
Neg logit contributions
elope-0.043
bes-0.041
comb-0.041
Ali-0.039
we-0.039
Tokenling
Token ID1359
Feature activation-1.68e+00

Pos logit contributions
elope+0.085
bes+0.084
comb+0.083
we+0.081
Ali+0.081
Neg logit contributions
 gol-0.074
 Captain-0.070
 traded-0.069
 pride-0.066
 Cody-0.064
Tokenbled
Token ID9342
Feature activation+1.22e-01

Pos logit contributions
elope+0.004
bes+0.004
comb+0.004
Ali+0.004
we+0.004
Neg logit contributions
 gol-0.005
 Captain-0.004
 traded-0.004
 pride-0.004
 Cody-0.004
Token up
Token ID510
Feature activation+1.03e+00

Pos logit contributions
 gol+0.005
 traded+0.004
 Captain+0.004
 pride+0.004
 Cody+0.004
Neg logit contributions
elope-0.007
bes-0.007
we-0.007
comb-0.007
Ali-0.007
Token all
Token ID477
Feature activation+1.00e+00

Pos logit contributions
 gol+0.037
 Captain+0.035
 traded+0.035
 pride+0.033
 Cody+0.032
Neg logit contributions
elope-0.065
bes-0.065
comb-0.064
Ali-0.063
we-0.062
Token the
Token ID262
Feature activation+1.07e+00

Pos logit contributions
 gol+0.043
 Captain+0.040
 traded+0.039
 Cody+0.036
 pride+0.035
Neg logit contributions
elope-0.058
bes-0.057
Ali-0.056
comb-0.056
we-0.055
Token ch
Token ID442
Feature activation+1.24e+00

Pos logit contributions
 gol+0.047
 Captain+0.042
 traded+0.042
 Cody+0.039
 pride+0.039
Neg logit contributions
elope-0.062
bes-0.062
comb-0.060
Ali-0.060
we-0.059
Tokenocol
Token ID4668
Feature activation+5.15e+00

Pos logit contributions
 gol+0.052
 Captain+0.050
 traded+0.049
 Cody+0.046
 pride+0.044
Neg logit contributions
bes-0.072
elope-0.071
comb-0.069
we-0.068
Ali-0.067
Tokenates
Token ID689
Feature activation+6.56e-01

Pos logit contributions
 gol+0.264
 traded+0.259
 Captain+0.256
 pride+0.251
 Cody+0.238
Neg logit contributions
elope-0.226
bes-0.222
Ali-0.215
comb-0.213
zed-0.208
Token,
Token ID11
Feature activation+8.99e-01

Pos logit contributions
 gol+0.025
 traded+0.024
 Captain+0.024
 pride+0.022
 Cody+0.022
Neg logit contributions
elope-0.040
bes-0.039
Ali-0.039
comb-0.038
we-0.038
Token and
Token ID290
Feature activation+1.95e-01

Pos logit contributions
 gol+0.042
 Captain+0.039
 traded+0.039
 pride+0.037
 Cody+0.036
Neg logit contributions
elope-0.048
bes-0.048
comb-0.047
Ali-0.046
we-0.046
Token she
Token ID673
Feature activation+8.22e-02

Pos logit contributions
 gol+0.008
 Captain+0.008
 traded+0.008
 pride+0.007
 Cody+0.007
Neg logit contributions
elope-0.011
bes-0.011
comb-0.011
we-0.011
Ali-0.011
Token was
Token ID373
Feature activation+1.16e-02

Pos logit contributions
 traded+0.003
 gol+0.003
 Captain+0.003
 pride+0.003
 Cody+0.003
Neg logit contributions
bes-0.005
elope-0.005
comb-0.005
we-0.005
Ali-0.005
Token full
Token ID1336
Feature activation-1.37e+00

Pos logit contributions
elope+0.007
bes+0.006
Ali+0.006
comb+0.006
zed+0.006
Neg logit contributions
 gol-0.006
 traded-0.005
 pride-0.005
 Captain-0.005
 Cody-0.005
Token of
Token ID286
Feature activation-7.83e-01

Pos logit contributions
elope+0.088
comb+0.087
bes+0.087
we+0.085
Ali+0.085
Neg logit contributions
 gol-0.047
 traded-0.043
 Captain-0.043
 pride-0.039
 Cody-0.039
Token life
Token ID1204
Feature activation-5.91e-01

Pos logit contributions
 Pen+0.030
elope+0.030
 cloud+0.029
 web+0.028
we+0.028
Neg logit contributions
 gol-0.044
 traded-0.043
 Cody-0.038
 Captain-0.037
 Jared-0.037
Token.
Token ID13
Feature activation-4.37e-02

Pos logit contributions
elope+0.030
bes+0.030
comb+0.029
we+0.029
Ali+0.028
Neg logit contributions
 gol-0.029
 traded-0.027
 Captain-0.027
 pride-0.026
 Cody-0.025
Token Everywhere
Token ID48201
Feature activation+2.35e+00

Pos logit contributions
elope+0.003
bes+0.003
comb+0.003
Ali+0.003
we+0.003
Neg logit contributions
 gol-0.002
 Captain-0.002
 traded-0.002
 pride-0.001
 Cody-0.001
Token you
Token ID345
Feature activation+5.14e+00

Pos logit contributions
 gol+0.102
 traded+0.095
 Captain+0.095
 pride+0.090
 Cody+0.086
Neg logit contributions
elope-0.136
bes-0.129
Ali-0.129
comb-0.128
we-0.126
Token looked
Token ID3114
Feature activation+3.12e-01

Pos logit contributions
 gol+0.249
 Captain+0.228
 Cody+0.222
 traded+0.219
 pride+0.217
Neg logit contributions
elope-0.273
comb-0.264
bes-0.253
Ali-0.249
isa-0.247
Token there
Token ID612
Feature activation+3.06e-01

Pos logit contributions
 gol+0.014
 traded+0.013
 Captain+0.013
 pride+0.012
 Cody+0.012
Neg logit contributions
elope-0.017
we-0.017
bes-0.017
zed-0.016
comb-0.016
Token were
Token ID547
Feature activation+6.80e-01

Pos logit contributions
 gol+0.013
 Captain+0.013
 traded+0.013
 pride+0.012
 Cody+0.012
Neg logit contributions
elope-0.017
bes-0.017
comb-0.017
Ali-0.016
we-0.016
Token crazy
Token ID7165
Feature activation+2.50e-01

Pos logit contributions
 gol+0.032
 traded+0.028
 Captain+0.028
 pride+0.027
 Cody+0.026
Neg logit contributions
elope-0.037
we-0.035
bes-0.035
comb-0.034
Ali-0.034
Token creatures
Token ID8109
Feature activation+5.73e-01

Pos logit contributions
 gol+0.012
 traded+0.012
 Captain+0.011
 pride+0.011
 Cody+0.011
Neg logit contributions
elope-0.012
bes-0.012
we-0.012
comb-0.011
Ali-0.011
Token "
Token ID366
Feature activation-3.38e-01

Pos logit contributions
 gol+0.003
 Captain+0.003
 traded+0.003
 pride+0.002
 Cody+0.002
Neg logit contributions
elope-0.005
bes-0.005
comb-0.005
we-0.004
Ali-0.004
TokenAnd
Token ID1870
Feature activation+2.67e-01

Pos logit contributions
elope+0.018
bes+0.018
comb+0.018
zed+0.017
Ali+0.017
Neg logit contributions
 gol-0.016
 traded-0.015
 Captain-0.014
 pride-0.013
 Cody-0.013
Token it
Token ID340
Feature activation-4.82e-01

Pos logit contributions
 gol+0.014
 traded+0.013
 Captain+0.012
 pride+0.012
 Cody+0.012
Neg logit contributions
elope-0.013
comb-0.012
bes-0.012
we-0.012
Ali-0.012
Token is
Token ID318
Feature activation-1.20e+00

Pos logit contributions
bes+0.026
comb+0.026
elope+0.026
Ali+0.025
we+0.025
Neg logit contributions
 gol-0.020
 traded-0.020
 Captain-0.020
 pride-0.019
 better-0.019
Token our
Token ID674
Feature activation-5.65e-01

Pos logit contributions
elope+0.068
comb+0.063
bes+0.062
 web+0.062
 Pen+0.061
Neg logit contributions
 gol-0.056
 traded-0.052
 Cody-0.047
 pride-0.045
 Captain-0.045
Token cloud
Token ID6279
Feature activation-6.16e+00

Pos logit contributions
bes+0.034
elope+0.033
comb+0.033
we+0.033
Ali+0.032
Neg logit contributions
 gol-0.022
 Captain-0.021
 pride-0.021
 traded-0.020
 Cody-0.019
Token.
Token ID13
Feature activation-6.55e-01

Pos logit contributions
bes+0.355
Ali+0.350
elope+0.345
zed+0.341
comb+0.334
Neg logit contributions
 gol-0.238
 traded-0.237
 Captain-0.234
 better-0.226
 pride-0.221
Token Let
Token ID3914
Feature activation-1.19e+00

Pos logit contributions
elope+0.037
bes+0.036
comb+0.036
Ali+0.035
we+0.035
Neg logit contributions
 gol-0.028
 traded-0.027
 Captain-0.026
 pride-0.025
 Cody-0.024
Token's
Token ID338
Feature activation+2.77e-01

Pos logit contributions
bes+0.069
elope+0.068
comb+0.068
Ali+0.066
we+0.065
Neg logit contributions
 gol-0.049
 traded-0.048
 Captain-0.048
 pride-0.045
 Cody-0.044
Token give
Token ID1577
Feature activation+7.91e-02

Pos logit contributions
 gol+0.012
 Captain+0.012
 traded+0.012
 Cody+0.011
 pride+0.011
Neg logit contributions
elope-0.015
comb-0.015
bes-0.015
Ali-0.015
we-0.014
Token it
Token ID340
Feature activation-7.69e-01

Pos logit contributions
 gol+0.004
 traded+0.003
 Captain+0.003
 pride+0.003
 Cody+0.003
Neg logit contributions
elope-0.004
bes-0.004
we-0.004
comb-0.004
Ali-0.004
Token city
Token ID1748
Feature activation-1.34e-01

Pos logit contributions
 traded+0.026
 gol+0.026
 Cody+0.025
 Captain+0.025
 pride+0.024
Neg logit contributions
elope-0.020
 cloud-0.020
comb-0.019
we-0.019
Ali-0.019
Token.
Token ID13
Feature activation-3.36e-01

Pos logit contributions
elope+0.007
bes+0.006
we+0.006
comb+0.006
Ali+0.006
Neg logit contributions
 gol-0.007
 Captain-0.006
 traded-0.006
 pride-0.006
 Cody-0.006
Token
Token ID220
Feature activation-1.94e-01

Pos logit contributions
comb+0.021
bes+0.021
we+0.021
ivering+0.020
ze+0.019
Neg logit contributions
 Captain-0.012
 traded-0.011
 pride-0.010
 gol-0.010
 Loyal-0.010
Token
Token ID198
Feature activation+3.14e-01

Pos logit contributions
bes+0.012
elope+0.012
comb+0.012
we+0.012
Ali+0.012
Neg logit contributions
 gol-0.007
 Captain-0.007
 traded-0.006
 pride-0.006
 Cody-0.006
Token
Token ID198
Feature activation+4.86e-02

Pos logit contributions
 Captain+0.005
 gol+0.003
 traded+0.003
 better+0.003
 pride+0.003
Neg logit contributions
comb-0.026
bes-0.025
 chin-0.025
 gag-0.024
ze-0.024
TokenAli
Token ID37893
Feature activation-6.06e+00

Pos logit contributions
 Captain+0.002
 gol+0.002
 traded+0.002
Ready+0.002
 Loyal+0.002
Neg logit contributions
comb-0.002
bes-0.002
 chin-0.002
 gag-0.002
ivering-0.002
Token said
Token ID531
Feature activation+1.42e+00

Pos logit contributions
elope+0.337
bes+0.320
we+0.312
comb+0.309
Ali+0.308
Neg logit contributions
 gol-0.272
 Captain-0.258
 pride-0.254
 traded-0.245
 Cody-0.238
Token,
Token ID11
Feature activation-1.24e-02

Pos logit contributions
 gol+0.065
 Captain+0.061
 traded+0.061
 pride+0.061
 Cody+0.056
Neg logit contributions
comb-0.070
zed-0.070
elope-0.069
Ali-0.068
 Pen-0.068
Token
Token ID6184
Feature activation-3.66e-01

Pos logit contributions
elope+0.001
bes+0.001
comb+0.001
Ali+0.001
we+0.001
Neg logit contributions
 gol-0.001
 traded-0.001
 Captain-0.001
 pride-0.001
 Cody-0.001
Token
Token ID95
Feature activation-3.01e-01

Pos logit contributions
elope+0.018
bes+0.018
comb+0.018
we+0.018
Ali+0.017
Neg logit contributions
 gol-0.018
 Captain-0.017
 traded-0.017
 Cody-0.016
 pride-0.016
Token
Token ID26391
Feature activation-5.00e-01

Pos logit contributions
elope+0.015
bes+0.015
comb+0.015
we+0.014
Ali+0.014
Neg logit contributions
 gol-0.015
 Captain-0.014
 traded-0.014
 pride-0.013
 Cody-0.013
Tokenlets
Token ID5289
Feature activation+1.68e-01

Pos logit contributions
 gol+0.182
 Captain+0.176
 traded+0.171
 Cody+0.164
 pride+0.164
Neg logit contributions
bes-0.138
elope-0.137
comb-0.134
we-0.130
Ali-0.129
Token.
Token ID13
Feature activation+1.40e-02

Pos logit contributions
 gol+0.008
 Captain+0.008
 traded+0.007
 Cody+0.007
 pride+0.007
Neg logit contributions
comb-0.009
bes-0.009
we-0.009
elope-0.009
Ali-0.008
Token
Token ID220
Feature activation-2.50e-02

Pos logit contributions
 gol+0.001
 traded+0.001
 pride+0.001
 better+0.001
 Captain+0.001
Neg logit contributions
elope-0.001
Ali-0.001
bes-0.001
 Pen-0.001
Pen-0.001
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
elope+0.001
bes+0.001
Ali+0.001
we+0.001
comb+0.001
Neg logit contributions
 gol-0.001
 traded-0.001
 Captain-0.001
 pride-0.001
vious-0.001
Token
Token ID198
Feature activation-8.99e-02

Pos logit contributions
 gol+0.007
 traded+0.007
 Captain+0.006
 pride+0.006
 Cody+0.006
Neg logit contributions
elope-0.009
Ali-0.009
bes-0.009
we-0.009
comb-0.008
TokenAli
Token ID37893
Feature activation-5.86e+00

Pos logit contributions
elope+0.004
bes+0.004
Ali+0.004
comb+0.004
we+0.004
Neg logit contributions
 gol-0.005
 traded-0.005
 Captain-0.005
 pride-0.005
 Cody-0.005
Token was
Token ID373
Feature activation-2.47e-02

Pos logit contributions
elope+0.321
bes+0.314
comb+0.307
Ali+0.303
we+0.302
Neg logit contributions
 gol-0.267
 Captain-0.253
 traded-0.246
 pride-0.236
 Cody-0.232
Token so
Token ID523
Feature activation+4.04e-01

Pos logit contributions
elope+0.001
bes+0.001
zed+0.001
comb+0.001
Ali+0.001
Neg logit contributions
 gol-0.001
 Captain-0.001
 traded-0.001
 Cody-0.001
 pride-0.001
Token excited
Token ID6568
Feature activation-1.39e+00

Pos logit contributions
 gol+0.020
 Captain+0.018
 traded+0.018
 Loyal+0.017
 Cody+0.017
Neg logit contributions
zed-0.019
elope-0.019
bes-0.018
Ali-0.018
 Pen-0.018
Token,
Token ID11
Feature activation+6.31e-01

Pos logit contributions
elope+0.076
bes+0.075
comb+0.073
we+0.073
Ali+0.072
Neg logit contributions
 gol-0.062
 traded-0.059
 Captain-0.058
 pride-0.056
 Cody-0.053
Token he
Token ID339
Feature activation+1.58e-01

Pos logit contributions
 gol+0.020
 Captain+0.019
 traded+0.019
 pride+0.017
 Cody+0.017
Neg logit contributions
elope-0.042
bes-0.042
comb-0.041
Ali-0.041
we-0.041
Token thought
Token ID1807
Feature activation+9.45e-01

Pos logit contributions
 gol+0.008
 Captain+0.007
 traded+0.007
 Cody+0.007
 pride+0.006
Neg logit contributions
elope-0.009
Ali-0.008
zed-0.008
bes-0.008
isa-0.008
Token it
Token ID340
Feature activation+8.46e-01

Pos logit contributions
 gol+0.039
 traded+0.036
 Captain+0.036
 pride+0.034
 Cody+0.033
Neg logit contributions
elope-0.055
bes-0.054
comb-0.054
we-0.053
Ali-0.053
Token was
Token ID373
Feature activation+3.46e-01

Pos logit contributions
 gol+0.043
 Captain+0.040
 traded+0.040
 pride+0.039
 Cody+0.038
Neg logit contributions
elope-0.042
bes-0.041
comb-0.040
Ali-0.040
we-0.040
Token the
Token ID262
Feature activation-8.20e-01

Pos logit contributions
 gol+0.015
 traded+0.014
 pride+0.013
 Captain+0.013
 Cody+0.012
Neg logit contributions
elope-0.020
comb-0.019
bes-0.019
we-0.019
Ali-0.018
Token best
Token ID1266
Feature activation-4.41e-02

Pos logit contributions
elope+0.049
comb+0.048
Ali+0.047
we+0.046
bes+0.046
Neg logit contributions
 gol-0.032
 traded-0.032
 Captain-0.029
 Cody-0.028
 pride-0.027
Token cloud
Token ID6279
Feature activation-5.85e+00

Pos logit contributions
bes+0.003
elope+0.002
Ali+0.002
Pen+0.002
comb+0.002
Neg logit contributions
 gol-0.002
 Captain-0.002
 pride-0.002
 traded-0.002
 better-0.002
Token ever
Token ID1683
Feature activation-1.80e+00

Pos logit contributions
elope+0.318
bes+0.314
comb+0.310
we+0.303
Ali+0.303
Neg logit contributions
 gol-0.263
 Captain-0.249
 traded-0.248
 pride-0.236
 Cody-0.230
Token.
Token ID13
Feature activation-9.84e-03

Pos logit contributions
elope+0.076
we+0.072
comb+0.070
bes+0.069
zed+0.065
Neg logit contributions
 gol-0.107
 Captain-0.101
 traded-0.101
 pride-0.098
 Cody-0.096
Token And
Token ID843
Feature activation+7.58e-01

Pos logit contributions
bes+0.001
elope+0.001
comb+0.001
we+0.001
Ali+0.001
Neg logit contributions
 gol-0.000
 Captain-0.000
 traded-0.000
 pride-0.000
 Cody-0.000
Token Bob
Token ID5811
Feature activation-1.69e+00

Pos logit contributions
 gol+0.034
 traded+0.032
 Captain+0.030
 pride+0.029
 Cody+0.029
Neg logit contributions
elope-0.043
comb-0.040
bes-0.040
Ali-0.040
we-0.039
Token never
Token ID1239
Feature activation-1.26e-01

Pos logit contributions
elope+0.095
bes+0.093
comb+0.092
Ali+0.090
we+0.090
Neg logit contributions
 gol-0.074
 Captain-0.069
 traded-0.069
 pride-0.065
 Cody-0.064
Token
Token ID198
Feature activation+5.17e-01

Pos logit contributions
elope+0.001
bes+0.001
comb+0.001
Ali+0.001
we+0.001
Neg logit contributions
 gol-0.001
 Captain-0.001
 traded-0.001
 pride-0.001
 Cody-0.001
Token
Token ID198
Feature activation+2.00e-01

Pos logit contributions
 Captain+0.006
 better+0.005
 Cody+0.005
 pride+0.005
 traded+0.005
Neg logit contributions
comb-0.044
bes-0.042
 chin-0.040
ze-0.040
 throats-0.040
TokenOne
Token ID3198
Feature activation-4.79e-01

Pos logit contributions
old+0.006
 better+0.005
 chalk+0.005
 written+0.005
 fun+0.005
Neg logit contributions
comb-0.013
bes-0.012
 chin-0.011
 throats-0.011
flake-0.011
Token day
Token ID1110
Feature activation-8.92e-01

Pos logit contributions
bes+0.031
elope+0.030
comb+0.030
we+0.029
Ali+0.029
Neg logit contributions
 gol-0.017
 Captain-0.016
 traded-0.016
 pride-0.015
 Cody-0.014
Token,
Token ID11
Feature activation-2.43e-01

Pos logit contributions
bes+0.080
comb+0.075
eds+0.075
we+0.074
elope+0.074
Neg logit contributions
 Captain-0.004
 Johnny-0.004
 chalk-0.003
 Jack-0.002
 better-0.002
Token Ali
Token ID12104
Feature activation-5.84e+00

Pos logit contributions
bes+0.016
lor+0.015
eds+0.015
ivering+0.015
comb+0.014
Neg logit contributions
 Johnny-0.007
 Captain-0.007
 online-0.007
 chalk-0.007
 Jack-0.007
Token received
Token ID2722
Feature activation+5.28e-01

Pos logit contributions
elope+0.335
bes+0.313
comb+0.310
we+0.307
Ali+0.305
Neg logit contributions
 gol-0.265
 Captain-0.241
 pride-0.236
 traded-0.231
 Cody-0.222
Token a
Token ID257
Feature activation-1.18e-01

Pos logit contributions
 gol+0.021
 traded+0.019
 Captain+0.019
 pride+0.017
 Cody+0.017
Neg logit contributions
elope-0.032
bes-0.031
Ali-0.031
comb-0.031
we-0.031
Token letter
Token ID3850
Feature activation+1.00e+00

Pos logit contributions
comb+0.005
elope+0.005
 web+0.005
 cloud+0.005
 song+0.005
Neg logit contributions
 gol-0.006
 traded-0.006
 Captain-0.005
 Cody-0.005
 pride-0.005
Token in
Token ID287
Feature activation-3.46e-01

Pos logit contributions
 gol+0.040
 Captain+0.037
 traded+0.037
 pride+0.035
 Cody+0.034
Neg logit contributions
elope-0.060
bes-0.059
comb-0.059
we-0.058
Ali-0.058
Token the
Token ID262
Feature activation+1.54e-01

Pos logit contributions
comb+0.025
bes+0.025
we+0.025
elope+0.025
iders+0.024
Neg logit contributions
 Captain-0.009
 pride-0.009
 gol-0.008
 Cody-0.008
 traded-0.008
Token were
Token ID547
Feature activation-9.05e-01

Pos logit contributions
comb+0.055
elope+0.054
bes+0.052
Ali+0.052
 cloud+0.049
Neg logit contributions
 gol-0.048
 Captain-0.046
 Cody-0.043
 Loyal-0.040
 pride-0.039
Token happy
Token ID3772
Feature activation-1.23e+00

Pos logit contributions
elope+0.054
bes+0.054
comb+0.052
Ali+0.051
we+0.050
Neg logit contributions
 gol-0.037
 Captain-0.034
 traded-0.033
 Cody-0.031
 pride-0.029
Token with
Token ID351
Feature activation-1.12e+00

Pos logit contributions
elope+0.071
bes+0.070
comb+0.069
Ali+0.068
we+0.066
Neg logit contributions
 gol-0.054
 Captain-0.051
 traded-0.050
 pride-0.048
 Cody-0.046
Token their
Token ID511
Feature activation-1.72e+00

Pos logit contributions
elope+0.066
bes+0.065
comb+0.064
Ali+0.063
we+0.062
Neg logit contributions
 gol-0.047
 traded-0.044
 Captain-0.043
 Cody-0.040
 pride-0.040
Token new
Token ID649
Feature activation+1.63e+00

Pos logit contributions
elope+0.107
bes+0.107
comb+0.106
we+0.103
Ali+0.103
Neg logit contributions
 gol-0.064
 pride-0.059
 Captain-0.059
 traded-0.058
 chalk-0.052
Token cloud
Token ID6279
Feature activation-5.81e+00

Pos logit contributions
 gol+0.071
 pride+0.069
 Captain+0.066
 chalk+0.066
 traded+0.062
Neg logit contributions
comb-0.091
bes-0.089
elope-0.089
zed-0.088
Ali-0.086
Token.
Token ID13
Feature activation-8.38e-01

Pos logit contributions
Ali+0.346
bes+0.344
elope+0.339
comb+0.333
zed+0.330
Neg logit contributions
 gol-0.217
 traded-0.214
 Captain-0.209
 pride-0.199
 better-0.188
Token They
Token ID1119
Feature activation-1.02e+00

Pos logit contributions
elope+0.042
bes+0.040
Ali+0.038
comb+0.037
 Pen+0.037
Neg logit contributions
 gol-0.042
 traded-0.041
 Captain-0.038
 pride-0.037
 Cody-0.036
Token pretended
Token ID36766
Feature activation-1.36e+00

Pos logit contributions
comb+0.052
elope+0.051
bes+0.050
Ali+0.048
 cloud+0.047
Neg logit contributions
 gol-0.047
 Captain-0.046
 Cody-0.042
 Loyal-0.038
 pride-0.038
Token it
Token ID340
Feature activation+7.40e-01

Pos logit contributions
elope+0.086
bes+0.085
comb+0.084
Ali+0.082
we+0.082
Neg logit contributions
 gol-0.050
 Captain-0.046
 traded-0.046
 pride-0.043
 Cody-0.042
Token was
Token ID373
Feature activation+3.28e-01

Pos logit contributions
 traded+0.026
 better+0.024
 Captain+0.023
 gol+0.023
 fixed+0.023
Neg logit contributions
elope-0.046
comb-0.045
bes-0.045
Ali-0.044
Pen-0.044
Token realized
Token ID6939
Feature activation+9.14e-01

Pos logit contributions
bes+0.074
elope+0.070
Ali+0.069
isa+0.068
Pen+0.068
Neg logit contributions
 traded-0.032
 better-0.030
 gol-0.029
 Captain-0.026
 chalk-0.026
Token it
Token ID340
Feature activation-5.58e-01

Pos logit contributions
 gol+0.038
 traded+0.036
 Captain+0.035
 pride+0.034
 Cody+0.032
Neg logit contributions
elope-0.053
bes-0.052
comb-0.051
we-0.051
Ali-0.051
Token wasn
Token ID2492
Feature activation+8.25e-01

Pos logit contributions
bes+0.030
elope+0.030
comb+0.029
Ali+0.029
we+0.028
Neg logit contributions
 gol-0.025
 traded-0.024
 Captain-0.024
 pride-0.022
 Cody-0.022
Token't
Token ID470
Feature activation-1.62e+00

Pos logit contributions
 gol+0.041
 Captain+0.040
 traded+0.039
 pride+0.038
 better+0.037
Neg logit contributions
elope-0.041
bes-0.041
comb-0.038
we-0.038
isa-0.037
Token a
Token ID257
Feature activation-6.01e-01

Pos logit contributions
elope+0.094
comb+0.092
bes+0.091
Ali+0.089
we+0.088
Neg logit contributions
 gol-0.067
 traded-0.064
 Captain-0.063
 pride-0.059
 Cody-0.058
Token cloud
Token ID6279
Feature activation-5.80e+00

Pos logit contributions
bes+0.031
we+0.029
elope+0.029
comb+0.028
Ali+0.028
Neg logit contributions
 gol-0.031
 Captain-0.030
 traded-0.028
 better-0.028
 pride-0.027
Token at
Token ID379
Feature activation-7.65e-01

Pos logit contributions
bes+0.341
elope+0.336
Ali+0.326
comb+0.321
we+0.318
Neg logit contributions
 gol-0.243
 Captain-0.229
 traded-0.228
 pride-0.209
 Cody-0.206
Token all
Token ID477
Feature activation-4.24e-01

Pos logit contributions
elope+0.050
bes+0.050
comb+0.049
Ali+0.048
we+0.048
Neg logit contributions
 gol-0.026
 Captain-0.025
 traded-0.025
 pride-0.023
 Cody-0.022
Token.
Token ID13
Feature activation-7.27e-02

Pos logit contributions
elope+0.022
bes+0.022
comb+0.022
Ali+0.021
we+0.021
Neg logit contributions
 gol-0.020
 traded-0.019
 Captain-0.019
 pride-0.018
 Cody-0.018
Token It
Token ID632
Feature activation+4.55e-01

Pos logit contributions
elope+0.005
bes+0.005
comb+0.005
Ali+0.005
we+0.005
Neg logit contributions
 gol-0.003
 Captain-0.002
 traded-0.002
 pride-0.002
 Cody-0.002
Token was
Token ID373
Feature activation+6.61e-01

Pos logit contributions
 gol+0.017
 traded+0.017
 Captain+0.017
 pride+0.016
 better+0.015
Neg logit contributions
bes-0.027
comb-0.027
elope-0.027
we-0.026
Ali-0.026
Token inside
Token ID2641
Feature activation+1.58e+00

Pos logit contributions
elope+0.008
comb+0.008
bes+0.008
zed+0.008
we+0.007
Neg logit contributions
 gol-0.007
 traded-0.006
 Captain-0.006
 pride-0.005
 Cody-0.005
Token,
Token ID11
Feature activation+3.35e-01

Pos logit contributions
 gol+0.078
 traded+0.074
 Captain+0.072
 pride+0.069
 Cody+0.067
Neg logit contributions
elope-0.080
bes-0.078
comb-0.077
we-0.076
Ali-0.075
Tokenâ
Token ID22940
Feature activation-9.00e-01

Pos logit contributions
 gol+0.015
 traded+0.014
 Captain+0.014
 pride+0.013
 Cody+0.013
Neg logit contributions
elope-0.018
bes-0.018
comb-0.018
Ali-0.017
we-0.017
Token
Token ID26391
Feature activation-1.44e-01

Pos logit contributions
bes+0.050
elope+0.049
comb+0.049
we+0.049
Ali+0.048
Neg logit contributions
 gol-0.039
 traded-0.036
 Captain-0.036
 pride-0.033
 Cody-0.033
Token said
Token ID531
Feature activation+9.91e-01

Pos logit contributions
Pen+0.006
comb+0.006
Ali+0.006
isa+0.006
 web+0.006
Neg logit contributions
 gol-0.007
 Captain-0.007
 traded-0.007
 Cody-0.007
 Loyal-0.006
Token Ali
Token ID12104
Feature activation-5.80e+00

Pos logit contributions
 gol+0.040
 traded+0.038
 Captain+0.037
 pride+0.035
 Cody+0.034
Neg logit contributions
elope-0.059
bes-0.058
comb-0.057
Ali-0.056
we-0.056
Tokenâ
Token ID22940
Feature activation-9.22e-01

Pos logit contributions
elope+0.330
bes+0.327
comb+0.321
Ali+0.316
we+0.315
Neg logit contributions
 gol-0.245
 Captain-0.232
 traded-0.232
 pride-0.218
 Cody-0.213
Token
Token ID26391
Feature activation-2.51e-01

Pos logit contributions
bes+0.049
elope+0.049
comb+0.049
we+0.047
Ali+0.047
Neg logit contributions
 gol-0.042
 traded-0.040
 Captain-0.039
 pride-0.038
 Cody-0.037
Token
Token ID8151
Feature activation-3.25e+00

Pos logit contributions
Pen+0.009
 web+0.009
isa+0.008
comb+0.008
elope+0.008
Neg logit contributions
 traded-0.014
 Captain-0.014
 gol-0.014
 Cody-0.014
 written-0.013
Tokens
Token ID82
Feature activation-1.01e+00

Pos logit contributions
elope+0.157
bes+0.157
comb+0.153
Ali+0.149
we+0.148
Neg logit contributions
 gol-0.165
 traded-0.157
 Captain-0.157
 pride-0.149
 Cody-0.147
Token mom
Token ID1995
Feature activation-8.58e-01

Pos logit contributions
elope+0.066
bes+0.066
comb+0.064
we+0.064
Ali+0.064
Neg logit contributions
 gol-0.033
 Captain-0.031
 traded-0.031
 pride-0.029
 Cody-0.028
Token
Token ID198
Feature activation+8.12e-01

Pos logit contributions
 pride+0.000
 Johnny+0.000
 Captain+0.000
 Jack+0.000
 chalk+0.000
Neg logit contributions
bes-0.002
we-0.002
comb-0.002
ich-0.002
ivering-0.001
Token
Token ID198
Feature activation+4.64e-01

Pos logit contributions
 Captain+0.008
 Johnny+0.006
 better+0.006
 traded+0.005
 gol+0.005
Neg logit contributions
comb-0.071
bes-0.069
 chin-0.066
ze-0.066
 throats-0.065
TokenOne
Token ID3198
Feature activation-3.80e-01

Pos logit contributions
 chalk+0.017
 fun+0.017
 better+0.017
 online+0.016
old+0.016
Neg logit contributions
bes-0.025
comb-0.025
 chin-0.023
 throats-0.022
 tongue-0.022
Token day
Token ID1110
Feature activation-7.86e-01

Pos logit contributions
bes+0.026
elope+0.025
comb+0.024
we+0.024
Ali+0.024
Neg logit contributions
 gol-0.013
 Captain-0.012
 traded-0.012
 pride-0.011
 Cody-0.010
Token,
Token ID11
Feature activation-8.80e-02

Pos logit contributions
bes+0.073
we+0.067
comb+0.067
lor+0.067
elope+0.067
Neg logit contributions
 Captain-0.003
 Johnny-0.002
 chalk-0.002
 Jack-0.000
 better-0.000
Token Ali
Token ID12104
Feature activation-5.79e+00

Pos logit contributions
bes+0.005
lor+0.005
eds+0.005
ivering+0.005
comb+0.005
Neg logit contributions
 Captain-0.003
 Johnny-0.003
 online-0.003
 Jack-0.003
 chalk-0.003
Token and
Token ID290
Feature activation+1.62e-01

Pos logit contributions
elope+0.345
bes+0.342
comb+0.336
Ali+0.331
we+0.329
Neg logit contributions
 gol-0.231
 Captain-0.218
 traded-0.217
 pride-0.204
 Cody-0.199
Token her
Token ID607
Feature activation-1.26e+00

Pos logit contributions
 Captain+0.004
 traded+0.003
 gol+0.003
 pride+0.003
 better+0.003
Neg logit contributions
bes-0.013
comb-0.012
we-0.012
elope-0.012
eds-0.011
Token mum
Token ID25682
Feature activation-1.09e+00

Pos logit contributions
elope+0.056
bes+0.055
comb+0.054
Ali+0.053
we+0.053
Neg logit contributions
 gol-0.070
 traded-0.067
 Captain-0.066
 pride-0.063
 Cody-0.062
Token went
Token ID1816
Feature activation+6.60e-01

Pos logit contributions
elope+0.052
comb+0.050
we+0.048
 cloud+0.047
isa+0.046
Neg logit contributions
 gol-0.055
 Captain-0.052
 pride-0.048
 Cody-0.047
 richer-0.043
Token to
Token ID284
Feature activation-2.72e-01

Pos logit contributions
 gol+0.032
 Captain+0.028
 pride+0.028
 traded+0.028
 Cody+0.027
Neg logit contributions
bes-0.034
elope-0.034
we-0.033
comb-0.032
Ali-0.032
Token said
Token ID531
Feature activation+1.33e+00

Pos logit contributions
 gol+0.009
 Captain+0.008
 traded+0.008
 pride+0.007
 Cody+0.007
Neg logit contributions
elope-0.014
comb-0.014
bes-0.014
Ali-0.014
zed-0.013
Token it
Token ID340
Feature activation-2.88e-01

Pos logit contributions
 gol+0.058
 traded+0.054
 Captain+0.053
 pride+0.050
 Cody+0.048
Neg logit contributions
comb-0.074
elope-0.074
bes-0.073
we-0.072
zed-0.071
Token wasn
Token ID2492
Feature activation+7.44e-01

Pos logit contributions
elope+0.015
bes+0.015
comb+0.015
Ali+0.014
we+0.014
Neg logit contributions
 gol-0.013
 traded-0.013
 Captain-0.013
 pride-0.012
 Cody-0.012
Token't
Token ID470
Feature activation-1.81e+00

Pos logit contributions
 gol+0.048
 traded+0.046
 Captain+0.045
 pride+0.044
 Cody+0.043
Neg logit contributions
elope-0.026
comb-0.026
Ali-0.025
bes-0.025
Pen-0.024
Token a
Token ID257
Feature activation-7.94e-01

Pos logit contributions
elope+0.099
comb+0.096
 Pen+0.091
 web+0.090
Ali+0.089
Neg logit contributions
 gol-0.085
 traded-0.077
 Captain-0.073
 pride-0.068
 Cody-0.068
Token cloud
Token ID6279
Feature activation-5.75e+00

Pos logit contributions
elope+0.042
comb+0.041
bes+0.040
Ali+0.039
 web+0.039
Neg logit contributions
 gol-0.036
 traded-0.035
 Captain-0.034
 pride-0.033
 Cody-0.033
Token.
Token ID13
Feature activation+4.12e-02

Pos logit contributions
bes+0.350
elope+0.347
Ali+0.337
comb+0.335
we+0.331
Neg logit contributions
 gol-0.223
 Captain-0.210
 traded-0.209
 pride-0.192
 Cody-0.188
Token She
Token ID1375
Feature activation+6.66e-02

Pos logit contributions
 gol+0.002
 traded+0.002
 Captain+0.002
 pride+0.002
 Cody+0.002
Neg logit contributions
elope-0.002
Ali-0.002
bes-0.002
 Pen-0.002
comb-0.002
Token went
Token ID1816
Feature activation+1.03e+00

Pos logit contributions
 gol+0.003
 Captain+0.002
 traded+0.002
 Cody+0.002
 pride+0.002
Neg logit contributions
elope-0.004
bes-0.004
comb-0.004
Ali-0.004
we-0.004
Token to
Token ID284
Feature activation-2.75e-02

Pos logit contributions
 gol+0.050
 traded+0.045
 pride+0.042
 Captain+0.041
 Cody+0.040
Neg logit contributions
bes-0.054
elope-0.053
we-0.052
Ali-0.052
comb-0.051
Token the
Token ID262
Feature activation+7.93e-01

Pos logit contributions
elope+0.001
Ali+0.001
 Pen+0.001
comb+0.001
bes+0.001
Neg logit contributions
 gol-0.001
 traded-0.001
 Captain-0.001
 pride-0.001
vious-0.001
Token "
Token ID366
Feature activation-1.17e+00

Pos logit contributions
bes+0.010
elope+0.010
comb+0.009
Ali+0.009
we+0.009
Neg logit contributions
 gol-0.008
 Captain-0.008
 traded-0.007
 pride-0.007
 Cody-0.007
TokenHi
Token ID17250
Feature activation+2.25e-02

Pos logit contributions
bes+0.090
comb+0.088
elope+0.087
zed+0.086
Ali+0.085
Neg logit contributions
 gol-0.029
 traded-0.026
 Captain-0.025
 Cody-0.021
 pride-0.020
Token,
Token ID11
Feature activation-3.96e-01

Pos logit contributions
 Captain+0.001
 gol+0.001
 traded+0.000
 better+0.000
 Cody+0.000
Neg logit contributions
bes-0.002
we-0.002
zed-0.002
elope-0.002
comb-0.002
Token I
Token ID314
Feature activation+5.47e-01

Pos logit contributions
bes+0.025
elope+0.024
we+0.023
comb+0.023
Ali+0.023
Neg logit contributions
 gol-0.016
 Captain-0.016
 traded-0.014
 pride-0.014
 Cody-0.014
Token'm
Token ID1101
Feature activation-1.22e+00

Pos logit contributions
 gol+0.030
 Captain+0.029
 Cody+0.028
 traded+0.028
 pride+0.027
Neg logit contributions
elope-0.024
comb-0.023
bes-0.022
Ali-0.022
ze-0.022
Token Bee
Token ID24719
Feature activation-5.75e+00

Pos logit contributions
elope+0.068
 Pen+0.065
comb+0.063
Ali+0.063
bes+0.063
Neg logit contributions
 gol-0.054
 traded-0.051
 pride-0.045
 Captain-0.045
 Cody-0.043
Token.
Token ID13
Feature activation-2.50e-01

Pos logit contributions
bes+0.389
zed+0.376
Ali+0.361
comb+0.354
we+0.353
Neg logit contributions
 gol-0.184
 Captain-0.184
 better-0.172
 traded-0.167
 Cody-0.152
Token Do
Token ID2141
Feature activation+1.22e+00

Pos logit contributions
elope+0.014
bes+0.014
comb+0.014
Ali+0.014
we+0.013
Neg logit contributions
 gol-0.011
 traded-0.010
 Captain-0.010
 pride-0.010
 Cody-0.009
Token you
Token ID345
Feature activation+2.34e+00

Pos logit contributions
 gol+0.044
 traded+0.043
 Captain+0.042
 pride+0.040
 Cody+0.038
Neg logit contributions
elope-0.076
bes-0.076
comb-0.076
we-0.073
Ali-0.073
Token want
Token ID765
Feature activation-2.95e-01

Pos logit contributions
 gol+0.104
 Captain+0.096
 Cody+0.092
 Trevor+0.088
 Loyal+0.083
Neg logit contributions
elope-0.122
ze-0.122
comb-0.120
 web-0.120
bes-0.117
Token to
Token ID284
Feature activation-2.36e-01

Pos logit contributions
elope+0.017
bes+0.017
comb+0.017
we+0.017
Ali+0.016
Neg logit contributions
 gol-0.012
 traded-0.011
 Captain-0.011
 Cody-0.010
 pride-0.010
Token bird
Token ID6512
Feature activation-6.13e-01

Pos logit contributions
 traded+0.084
 gol+0.084
 Captain+0.083
 Cody+0.079
 pride+0.077
Neg logit contributions
elope-0.060
comb-0.058
bes-0.058
Ali-0.054
we-0.054
Token began
Token ID2540
Feature activation+4.32e-01

Pos logit contributions
bes+0.034
elope+0.033
comb+0.033
Ali+0.032
we+0.032
Neg logit contributions
 gol-0.027
 traded-0.026
 Captain-0.026
 pride-0.024
 Cody-0.023
Token to
Token ID284
Feature activation-5.75e-01

Pos logit contributions
 gol+0.013
 Captain+0.012
 traded+0.012
 pride+0.012
 Cody+0.011
Neg logit contributions
bes-0.030
elope-0.029
comb-0.029
Ali-0.029
we-0.028
Token tell
Token ID1560
Feature activation-1.22e+00

Pos logit contributions
bes+0.028
elope+0.027
we+0.027
comb+0.026
Ali+0.026
Neg logit contributions
 gol-0.029
 Captain-0.028
 traded-0.028
 pride-0.027
 Cody-0.026
Token Pen
Token ID7507
Feature activation-5.25e+00

Pos logit contributions
bes+0.088
we+0.082
comb+0.081
iders+0.079
eds+0.079
Neg logit contributions
 better-0.036
 pride-0.036
 Captain-0.034
 Cody-0.029
 traded-0.028
Tokenelope
Token ID47329
Feature activation-5.69e+00

Pos logit contributions
bes+0.153
iders+0.140
we+0.116
 mat+0.113
zed+0.113
Neg logit contributions
 better-0.351
 Captain-0.322
 written-0.313
 pride-0.311
 Cody-0.301
Token it
Token ID340
Feature activation-7.38e-01

Pos logit contributions
bes+0.367
elope+0.360
comb+0.355
we+0.354
Ali+0.354
Neg logit contributions
 gol-0.186
 Captain-0.184
 traded-0.183
 pride-0.176
 Cody-0.164
Token's
Token ID338
Feature activation-1.09e+00

Pos logit contributions
bes+0.042
elope+0.041
comb+0.040
Ali+0.040
we+0.040
Neg logit contributions
 gol-0.030
 Captain-0.030
 traded-0.030
 pride-0.028
 Cody-0.027
Token story
Token ID1621
Feature activation-1.56e+00

Pos logit contributions
elope+0.060
bes+0.059
comb+0.059
Ali+0.056
we+0.056
Neg logit contributions
 gol-0.050
 traded-0.047
 Captain-0.047
 Cody-0.043
 pride-0.043
Token.
Token ID13
Feature activation+3.72e-01

Pos logit contributions
elope+0.093
bes+0.093
Ali+0.090
comb+0.090
we+0.090
Neg logit contributions
 gol-0.059
 Captain-0.057
 traded-0.057
 pride-0.053
 Cody-0.051
Token
Token ID220
Feature activation+2.97e-03

Pos logit contributions
 Captain+0.007
 better+0.007
 pride+0.007
 Cody+0.006
 traded+0.005
Neg logit contributions
we-0.029
bes-0.028
eds-0.028
iders-0.028
comb-0.027
Token there
Token ID612
Feature activation-4.63e-02

Pos logit contributions
 gol+0.028
 traded+0.027
 Captain+0.026
 pride+0.025
 Cody+0.024
Neg logit contributions
elope-0.045
bes-0.045
comb-0.044
Ali-0.044
we-0.043
Token were
Token ID547
Feature activation+3.32e-02

Pos logit contributions
bes+0.003
comb+0.003
elope+0.003
we+0.003
Ali+0.003
Neg logit contributions
 gol-0.002
 traded-0.002
 Captain-0.002
 Cody-0.002
 pride-0.002
Token two
Token ID734
Feature activation+2.50e-01

Pos logit contributions
 gol+0.001
 Captain+0.001
 traded+0.001
 Cody+0.001
 pride+0.001
Neg logit contributions
elope-0.002
Ali-0.002
we-0.002
Pen-0.002
 Pen-0.002
Token friends
Token ID2460
Feature activation+1.37e+00

Pos logit contributions
 gol+0.008
 traded+0.008
 Captain+0.008
 pride+0.008
 Cody+0.007
Neg logit contributions
bes-0.016
comb-0.016
elope-0.016
Ali-0.016
we-0.016
Token,
Token ID11
Feature activation-2.80e-02

Pos logit contributions
 Captain+0.043
 gol+0.043
 traded+0.042
 pride+0.038
 Cody+0.036
Neg logit contributions
comb-0.095
bes-0.095
Ali-0.090
elope-0.089
zed-0.089
Token Ali
Token ID12104
Feature activation-5.65e+00

Pos logit contributions
elope+0.002
Ali+0.002
bes+0.002
comb+0.002
 Pen+0.002
Neg logit contributions
 gol-0.001
 traded-0.001
 Captain-0.001
 pride-0.001
 Cody-0.001
Token and
Token ID290
Feature activation+1.12e-01

Pos logit contributions
comb+0.400
bes+0.400
Ali+0.386
iders+0.384
we+0.381
Neg logit contributions
 Captain-0.144
 traded-0.140
 gol-0.138
 pride-0.122
 Cody-0.116
Token Pat
Token ID3208
Feature activation-2.26e+00

Pos logit contributions
 gol+0.004
 Captain+0.004
 traded+0.004
 pride+0.003
 Cody+0.003
Neg logit contributions
elope-0.007
bes-0.007
comb-0.007
Ali-0.007
we-0.007
Token.
Token ID13
Feature activation+3.54e-01

Pos logit contributions
elope+0.118
bes+0.112
Ali+0.110
comb+0.109
we+0.109
Neg logit contributions
 gol-0.112
 Captain-0.105
 traded-0.104
 pride-0.100
 Cody-0.098
Token They
Token ID1119
Feature activation+2.42e-02

Pos logit contributions
 Captain+0.008
 traded+0.007
 chalk+0.007
 Jack+0.007
 pride+0.006
Neg logit contributions
we-0.026
ivering-0.026
bes-0.026
ich-0.025
comb-0.025
Token were
Token ID547
Feature activation-2.92e-01

Pos logit contributions
 gol+0.001
 Captain+0.001
 Cody+0.001
 richer+0.001
 pride+0.001
Neg logit contributions
elope-0.001
 cloud-0.001
comb-0.001
Ali-0.001
bes-0.001
Token all
Token ID477
Feature activation+9.66e-01

Pos logit contributions
elope+0.078
bes+0.078
comb+0.076
we+0.075
Ali+0.074
Neg logit contributions
 gol-0.055
 traded-0.052
 Captain-0.051
 pride-0.048
 Cody-0.047
Token day
Token ID1110
Feature activation+9.68e-01

Pos logit contributions
 gol+0.037
 traded+0.035
 Captain+0.035
 Cody+0.032
 pride+0.032
Neg logit contributions
elope-0.059
bes-0.057
Ali-0.057
we-0.056
comb-0.055
Token with
Token ID351
Feature activation-4.47e-01

Pos logit contributions
 gol+0.044
 Captain+0.042
 traded+0.042
 pride+0.039
 Cody+0.038
Neg logit contributions
elope-0.052
bes-0.052
comb-0.051
Ali-0.050
we-0.050
Token his
Token ID465
Feature activation-1.12e+00

Pos logit contributions
elope+0.029
bes+0.028
comb+0.028
Ali+0.028
we+0.027
Neg logit contributions
 gol-0.016
 traded-0.015
 Captain-0.015
 pride-0.014
 Cody-0.013
Token new
Token ID649
Feature activation+1.96e+00

Pos logit contributions
comb+0.073
bes+0.073
elope+0.072
we+0.071
zed+0.071
Neg logit contributions
 pride-0.036
 gol-0.036
 Captain-0.036
 chalk-0.033
 traded-0.032
Token cloud
Token ID6279
Feature activation-5.63e+00

Pos logit contributions
 gol+0.080
 pride+0.080
 Captain+0.078
 chalk+0.076
 better+0.071
Neg logit contributions
bes-0.111
comb-0.110
we-0.108
zed-0.107
elope-0.106
Token close
Token ID1969
Feature activation-6.02e-02

Pos logit contributions
bes+0.321
elope+0.319
Ali+0.312
comb+0.310
we+0.305
Neg logit contributions
 gol-0.232
 traded-0.224
 Captain-0.221
 pride-0.210
 Cody-0.199
Token to
Token ID284
Feature activation+8.44e-01

Pos logit contributions
elope+0.003
comb+0.003
bes+0.003
Ali+0.003
we+0.003
Neg logit contributions
 gol-0.003
 Captain-0.003
 traded-0.003
 pride-0.003
 Cody-0.003
Token him
Token ID683
Feature activation+1.24e+00

Pos logit contributions
 gol+0.031
 Captain+0.031
 traded+0.029
 pride+0.029
 Cody+0.027
Neg logit contributions
bes-0.053
elope-0.052
comb-0.051
we-0.051
Ali-0.050
Token.
Token ID13
Feature activation-4.56e-02

Pos logit contributions
 gol+0.057
 Captain+0.054
 traded+0.054
 pride+0.051
 Cody+0.050
Neg logit contributions
elope-0.066
bes-0.066
comb-0.065
Ali-0.064
we-0.063
Token He
Token ID679
Feature activation+5.04e-01

Pos logit contributions
bes+0.003
elope+0.003
comb+0.003
we+0.003
Ali+0.003
Neg logit contributions
 gol-0.002
 Captain-0.002
 traded-0.002
 pride-0.001
 Cody-0.001
Token harmless
Token ID23585
Feature activation-1.05e-01

Pos logit contributions
elope+0.036
bes+0.035
comb+0.035
Ali+0.034
we+0.034
Neg logit contributions
 gol-0.029
 traded-0.028
 Captain-0.028
 pride-0.026
 Cody-0.025
Token day
Token ID1110
Feature activation-8.84e-01

Pos logit contributions
bes+0.005
elope+0.005
Ali+0.005
we+0.005
comb+0.005
Neg logit contributions
 gol-0.005
 Captain-0.005
 traded-0.005
 pride-0.005
 Cody-0.005
Token with
Token ID351
Feature activation-1.48e+00

Pos logit contributions
elope+0.050
bes+0.049
comb+0.048
Ali+0.048
we+0.047
Neg logit contributions
 gol-0.038
 traded-0.036
 Captain-0.036
 pride-0.034
 Cody-0.033
Token not
Token ID407
Feature activation-1.45e+00

Pos logit contributions
elope+0.085
bes+0.085
Ali+0.083
we+0.082
comb+0.081
Neg logit contributions
 gol-0.062
 Captain-0.057
 traded-0.056
 Cody-0.051
 pride-0.049
Token a
Token ID257
Feature activation-5.48e-01

Pos logit contributions
elope+0.076
bes+0.075
comb+0.074
we+0.073
Ali+0.072
Neg logit contributions
 gol-0.069
 Captain-0.065
 traded-0.065
 pride-0.061
 Cody-0.060
Token cloud
Token ID6279
Feature activation-5.60e+00

Pos logit contributions
elope+0.026
bes+0.026
comb+0.025
Ali+0.025
we+0.024
Neg logit contributions
 gol-0.029
 Captain-0.027
 traded-0.027
 pride-0.026
 Cody-0.025
Token in
Token ID287
Feature activation-5.40e-01

Pos logit contributions
bes+0.339
elope+0.336
Ali+0.328
comb+0.319
we+0.315
Neg logit contributions
 gol-0.218
 traded-0.207
 Captain-0.206
 pride-0.185
 Cody-0.184
Token the
Token ID262
Feature activation-1.23e-01

Pos logit contributions
comb+0.039
elope+0.038
bes+0.038
we+0.037
iders+0.036
Neg logit contributions
 pride-0.014
 Captain-0.013
 chalk-0.013
 gol-0.013
 Cody-0.012
Token sky
Token ID6766
Feature activation-2.33e-01

Pos logit contributions
elope+0.007
bes+0.007
comb+0.006
Ali+0.006
we+0.006
Neg logit contributions
 gol-0.006
 Captain-0.005
 traded-0.005
 pride-0.005
 Cody-0.005
Token.
Token ID13
Feature activation-3.58e-01

Pos logit contributions
elope+0.014
bes+0.014
Ali+0.014
comb+0.014
zed+0.013
Neg logit contributions
 gol-0.008
 traded-0.008
 Captain-0.008
 pride-0.007
 better-0.007
Token
Token ID220
Feature activation-2.54e-01

Pos logit contributions
elope+0.020
bes+0.020
comb+0.019
we+0.019
Ali+0.019
Neg logit contributions
 gol-0.016
 traded-0.014
 Captain-0.014
 pride-0.013
 Cody-0.013
Token do
Token ID466
Feature activation-3.32e-03

Pos logit contributions
 Captain+0.022
 gol+0.022
 traded+0.021
 Cody+0.021
 pride+0.021
Neg logit contributions
comb-0.015
Ali-0.014
elope-0.014
 chin-0.014
bes-0.014
Token?"
Token ID1701
Feature activation+7.56e-02

Pos logit contributions
we+0.000
bes+0.000
comb+0.000
zed+0.000
ze+0.000
Neg logit contributions
 gol-0.000
 pride-0.000
 Captain-0.000
 traded-0.000
 Cody-0.000
Token
Token ID220
Feature activation+1.14e-01

Pos logit contributions
 Captain+0.003
 gol+0.003
 traded+0.003
 pride+0.003
 Cody+0.003
Neg logit contributions
comb-0.004
bes-0.004
elope-0.004
we-0.004
Ali-0.004
Token
Token ID198
Feature activation+5.40e-01

Pos logit contributions
 gol+0.004
 Captain+0.004
 traded+0.004
 pride+0.004
 Cody+0.003
Neg logit contributions
elope-0.007
bes-0.007
comb-0.007
Ali-0.007
we-0.007
Token
Token ID198
Feature activation+2.71e-01

Pos logit contributions
 Captain+0.014
 gol+0.011
 traded+0.011
 pride+0.011
 Cody+0.010
Neg logit contributions
comb-0.041
bes-0.039
 chin-0.037
elope-0.037
 web-0.037
TokenAli
Token ID37893
Feature activation-5.55e+00

Pos logit contributions
 Captain+0.013
 gol+0.013
 traded+0.012
 pride+0.012
 Cody+0.011
Neg logit contributions
comb-0.013
bes-0.013
 chin-0.012
 gag-0.012
elope-0.012
Token had
Token ID550
Feature activation+1.04e+00

Pos logit contributions
elope+0.374
bes+0.369
comb+0.364
Ali+0.359
we+0.357
Neg logit contributions
 gol-0.179
 Captain-0.165
 traded-0.163
 pride-0.152
 Cody-0.147
Token an
Token ID281
Feature activation+3.84e-01

Pos logit contributions
 gol+0.042
 Captain+0.040
 traded+0.037
 pride+0.036
 Cody+0.035
Neg logit contributions
elope-0.058
bes-0.058
Ali-0.057
comb-0.057
zed-0.056
Token idea
Token ID2126
Feature activation+1.58e+00

Pos logit contributions
 gol+0.016
 Captain+0.015
 traded+0.015
 Cody+0.014
 pride+0.013
Neg logit contributions
elope-0.022
bes-0.022
comb-0.021
zed-0.021
Ali-0.020
Token.
Token ID13
Feature activation+2.81e-01

Pos logit contributions
 gol+0.074
 traded+0.071
 Captain+0.071
 pride+0.067
 Cody+0.065
Neg logit contributions
elope-0.083
bes-0.082
comb-0.081
Ali-0.079
we-0.079
Token She
Token ID1375
Feature activation+2.23e-01

Pos logit contributions
 gol+0.009
 Captain+0.009
 traded+0.008
 pride+0.008
 Cody+0.008
Neg logit contributions
bes-0.019
elope-0.019
comb-0.019
we-0.018
Ali-0.018
Token done
Token ID1760
Feature activation-4.14e-01

Pos logit contributions
 gol+0.015
 Captain+0.014
 traded+0.014
 pride+0.013
 Cody+0.013
Neg logit contributions
elope-0.025
bes-0.025
comb-0.025
Ali-0.024
we-0.024
Token something
Token ID1223
Feature activation+3.88e-01

Pos logit contributions
elope+0.025
bes+0.025
comb+0.025
we+0.024
Ali+0.024
Neg logit contributions
 gol-0.016
 traded-0.015
 Captain-0.014
 pride-0.013
 Cody-0.013
Token good
Token ID922
Feature activation+5.57e-01

Pos logit contributions
 gol+0.015
 traded+0.014
 Captain+0.013
 pride+0.012
 Cody+0.012
Neg logit contributions
elope-0.024
comb-0.023
bes-0.023
we-0.023
zed-0.023
Token for
Token ID329
Feature activation+4.12e-01

Pos logit contributions
 gol+0.027
 traded+0.025
 Captain+0.025
 pride+0.024
 Cody+0.023
Neg logit contributions
comb-0.029
elope-0.028
we-0.028
bes-0.027
zed-0.026
Token his
Token ID465
Feature activation-1.61e+00

Pos logit contributions
 gol+0.011
 Captain+0.011
 traded+0.011
 pride+0.010
 Cody+0.010
Neg logit contributions
elope-0.029
bes-0.029
comb-0.029
Ali-0.029
we-0.028
Token hive
Token ID35881
Feature activation-5.55e+00

Pos logit contributions
bes+0.097
Ali+0.095
we+0.093
elope+0.092
comb+0.090
Neg logit contributions
 pride-0.060
 gol-0.059
 Captain-0.058
 traded-0.056
 better-0.055
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
elope+0.309
bes+0.308
Ali+0.302
comb+0.298
we+0.296
Neg logit contributions
 gol-0.235
 Captain-0.225
 traded-0.224
 pride-0.213
 Cody-0.205
Token<|endoftext|>
Token ID50256
Feature activation-4.35e-01

Pos logit contributions
elope+0.010
bes+0.010
comb+0.010
Ali+0.010
we+0.010
Neg logit contributions
 gol-0.006
 traded-0.006
 Captain-0.006
 pride-0.005
 Cody-0.005
TokenOnce
Token ID7454
Feature activation-7.88e-01

Pos logit contributions
elope+0.026
bes+0.026
comb+0.025
Ali+0.025
we+0.025
Neg logit contributions
 gol-0.017
 traded-0.016
 Captain-0.016
 pride-0.015
 Cody-0.014
Token upon
Token ID2402
Feature activation-3.26e-01

Pos logit contributions
elope+0.049
Ali+0.047
bes+0.047
comb+0.046
we+0.045
Neg logit contributions
 gol-0.030
 traded-0.028
 Captain-0.028
 pride-0.026
 Cody-0.025
Token a
Token ID257
Feature activation+1.12e+00

Pos logit contributions
elope+0.025
bes+0.025
comb+0.025
we+0.025
Ali+0.024
Neg logit contributions
 traded-0.006
 gol-0.006
 Captain-0.006
 pride-0.005
 better-0.005
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
elope+0.007
bes+0.007
comb+0.007
Ali+0.007
we+0.007
Neg logit contributions
 gol-0.003
 Captain-0.003
 traded-0.003
 pride-0.003
 Cody-0.003
Token
Token ID198
Feature activation-8.55e-02

Pos logit contributions
 gol+0.005
 Captain+0.005
 traded+0.005
 pride+0.004
 Cody+0.004
Neg logit contributions
elope-0.009
bes-0.009
comb-0.009
we-0.009
Ali-0.009
Token"
Token ID1
Feature activation-1.35e+00

Pos logit contributions
elope+0.004
bes+0.004
comb+0.004
Ali+0.004
we+0.004
Neg logit contributions
 gol-0.005
 Captain-0.004
 traded-0.004
 pride-0.004
 Cody-0.004
TokenHello
Token ID15496
Feature activation+3.35e-01

Pos logit contributions
bes+0.094
zed+0.093
elope+0.090
comb+0.090
eds+0.088
Neg logit contributions
 gol-0.041
 Captain-0.037
 traded-0.036
 chalk-0.032
 Cody-0.032
Token,
Token ID11
Feature activation-4.84e-01

Pos logit contributions
 gol+0.012
 Captain+0.011
 traded+0.011
 pride+0.011
 Cody+0.010
Neg logit contributions
elope-0.021
bes-0.021
comb-0.021
Ali-0.020
we-0.020
Token cloud
Token ID6279
Feature activation-5.53e+00

Pos logit contributions
elope+0.025
Ali+0.024
comb+0.024
bes+0.024
we+0.023
Neg logit contributions
 gol-0.023
 traded-0.022
 Captain-0.021
 pride-0.020
 Cody-0.020
Token!"
Token ID2474
Feature activation-5.80e-01

Pos logit contributions
bes+0.339
zed+0.327
Ali+0.319
comb+0.314
elope+0.310
Neg logit contributions
 gol-0.217
 Captain-0.199
 traded-0.191
 better-0.183
 chalk-0.167
Token Ellie
Token ID44801
Feature activation+1.07e+00

Pos logit contributions
elope+0.037
bes+0.036
Ali+0.034
comb+0.034
we+0.033
Neg logit contributions
 gol-0.023
 traded-0.019
 Captain-0.019
 pride-0.019
 Cody-0.019
Token said
Token ID531
Feature activation+2.41e+00

Pos logit contributions
 gol+0.032
 Captain+0.030
 traded+0.029
 pride+0.028
 Cody+0.026
Neg logit contributions
elope-0.076
bes-0.074
comb-0.073
Ali-0.072
we-0.071
Token.
Token ID13
Feature activation+2.70e-01

Pos logit contributions
 gol+0.095
 Captain+0.091
 traded+0.091
 pride+0.085
 Cody+0.083
Neg logit contributions
bes-0.144
elope-0.144
comb-0.140
Ali-0.140
we-0.138
Token
Token ID220
Feature activation+1.82e-01

Pos logit contributions
 gol+0.010
 Captain+0.010
 traded+0.010
 pride+0.009
 Cody+0.009
Neg logit contributions
elope-0.016
comb-0.016
bes-0.016
we-0.015
Ali-0.015
Token hive
Token ID35881
Feature activation-5.12e+00

Pos logit contributions
elope+0.038
bes+0.038
comb+0.037
Ali+0.037
we+0.037
Neg logit contributions
 gol-0.023
 traded-0.022
 Captain-0.022
 pride-0.021
 Cody-0.019
Token was
Token ID373
Feature activation-7.50e-01

Pos logit contributions
elope+0.291
bes+0.289
Ali+0.283
comb+0.281
we+0.278
Neg logit contributions
 gol-0.210
 traded-0.204
 Captain-0.200
 pride-0.192
 Cody-0.182
Token the
Token ID262
Feature activation-1.25e+00

Pos logit contributions
elope+0.042
bes+0.042
comb+0.042
Ali+0.040
we+0.040
Neg logit contributions
 gol-0.033
 Captain-0.030
 traded-0.029
 Cody-0.028
 pride-0.027
Token most
Token ID749
Feature activation+9.49e-02

Pos logit contributions
elope+0.076
comb+0.076
bes+0.073
we+0.072
Ali+0.071
Neg logit contributions
 gol-0.048
 traded-0.046
 Captain-0.045
 Cody-0.042
 pride-0.040
Token independent
Token ID4795
Feature activation-6.19e-01

Pos logit contributions
 traded+0.004
 gol+0.004
 Captain+0.004
 Cody+0.004
 Loyal+0.004
Neg logit contributions
we-0.005
elope-0.005
comb-0.005
bes-0.005
 web-0.005
Token hive
Token ID35881
Feature activation-5.53e+00

Pos logit contributions
bes+0.032
elope+0.032
Ali+0.031
we+0.031
comb+0.031
Neg logit contributions
 gol-0.029
 Captain-0.028
 traded-0.028
 pride-0.026
 Cody-0.026
Token in
Token ID287
Feature activation-8.65e-01

Pos logit contributions
elope+0.317
bes+0.315
comb+0.309
Ali+0.305
we+0.302
Neg logit contributions
 gol-0.230
 Captain-0.218
 traded-0.218
 pride-0.204
 Cody-0.199
Token town
Token ID3240
Feature activation-6.94e-01

Pos logit contributions
elope+0.055
bes+0.055
comb+0.055
we+0.053
Ali+0.053
Neg logit contributions
 gol-0.031
 Captain-0.029
 traded-0.029
 pride-0.027
 Cody-0.026
Token.
Token ID13
Feature activation+1.06e-01

Pos logit contributions
elope+0.036
bes+0.035
comb+0.034
we+0.034
Ali+0.033
Neg logit contributions
 gol-0.034
 Captain-0.032
 traded-0.032
 pride-0.030
 Cody-0.030
Token Everyone
Token ID11075
Feature activation+2.35e+00

Pos logit contributions
 gol+0.004
 Captain+0.004
 traded+0.003
 pride+0.003
 Cody+0.003
Neg logit contributions
bes-0.007
elope-0.007
comb-0.007
we-0.007
Ali-0.006
Token was
Token ID373
Feature activation+1.39e-01

Pos logit contributions
 gol+0.110
 Captain+0.104
 traded+0.103
 pride+0.098
 Cody+0.097
Neg logit contributions
elope-0.125
bes-0.122
we-0.119
comb-0.119
Ali-0.119
Token.
Token ID13
Feature activation-3.03e-01

Pos logit contributions
bes+0.012
elope+0.012
Ali+0.012
comb+0.012
we+0.011
Neg logit contributions
 gol-0.005
 Captain-0.005
 traded-0.005
 pride-0.005
 better-0.005
Token The
Token ID383
Feature activation+9.75e-02

Pos logit contributions
elope+0.017
bes+0.016
comb+0.016
Ali+0.016
zed+0.016
Neg logit contributions
 gol-0.013
 traded-0.012
 Captain-0.012
 pride-0.012
 Cody-0.011
Token yacht
Token ID43207
Feature activation+4.15e-01

Pos logit contributions
 gol+0.004
 Captain+0.004
 traded+0.004
 pride+0.004
 Cody+0.003
Neg logit contributions
elope-0.006
bes-0.006
comb-0.006
Ali-0.006
we-0.006
Token remembered
Token ID12086
Feature activation-1.48e+00

Pos logit contributions
 gol+0.018
 Captain+0.017
 traded+0.017
 pride+0.016
 Cody+0.016
Neg logit contributions
elope-0.023
bes-0.023
comb-0.022
Ali-0.022
we-0.022
Token the
Token ID262
Feature activation-7.31e-01

Pos logit contributions
elope+0.090
bes+0.090
comb+0.088
Ali+0.087
we+0.086
Neg logit contributions
 gol-0.058
 Captain-0.055
 traded-0.054
 pride-0.051
 Cody-0.049
Token cloud
Token ID6279
Feature activation-5.53e+00

Pos logit contributions
elope+0.039
bes+0.039
comb+0.038
Ali+0.037
we+0.037
Neg logit contributions
 gol-0.033
 traded-0.031
 Captain-0.031
 pride-0.029
 Cody-0.029
Token and
Token ID290
Feature activation-1.31e-01

Pos logit contributions
bes+0.331
elope+0.329
comb+0.321
Ali+0.320
we+0.315
Neg logit contributions
 gol-0.214
 traded-0.206
 Captain-0.205
 pride-0.192
 Cody-0.184
Token thought
Token ID1807
Feature activation-9.41e-02

Pos logit contributions
elope+0.008
bes+0.008
comb+0.008
Ali+0.007
we+0.007
Neg logit contributions
 gol-0.005
 Captain-0.005
 traded-0.005
 pride-0.005
 Cody-0.005
Token,
Token ID11
Feature activation+2.74e-01

Pos logit contributions
elope+0.006
bes+0.006
comb+0.006
Ali+0.006
we+0.006
Neg logit contributions
 gol-0.003
 Captain-0.003
 traded-0.003
 pride-0.003
 Cody-0.003
Token "
Token ID366
Feature activation-8.02e-01

Pos logit contributions
 Captain+0.011
 gol+0.010
 traded+0.010
 better+0.009
 Cody+0.009
Neg logit contributions
elope-0.017
bes-0.017
comb-0.016
Ali-0.016
we-0.015
TokenOh
Token ID5812
Feature activation-5.16e-01

Pos logit contributions
bes+0.043
elope+0.041
comb+0.041
zed+0.040
Ali+0.039
Neg logit contributions
 gol-0.038
 traded-0.036
 Captain-0.035
 pride-0.033
 Cody-0.032
Token But
Token ID887
Feature activation+2.08e-02

Pos logit contributions
bes+0.004
elope+0.004
Ali+0.004
zed+0.004
 Pen+0.004
Neg logit contributions
 gol-0.003
 Captain-0.003
 pride-0.003
 traded-0.003
 better-0.003
Token then
Token ID788
Feature activation+1.21e+00

Pos logit contributions
 gol+0.001
 pride+0.001
 traded+0.001
 Captain+0.001
vious+0.001
Neg logit contributions
elope-0.001
comb-0.001
zed-0.001
bes-0.001
Ali-0.001
Token she
Token ID673
Feature activation-5.64e-03

Pos logit contributions
 gol+0.059
 pride+0.053
 traded+0.051
 Captain+0.051
vious+0.049
Neg logit contributions
elope-0.061
Ali-0.060
comb-0.058
zed-0.058
ggy-0.057
Token saw
Token ID2497
Feature activation-1.39e-01

Pos logit contributions
elope+0.000
comb+0.000
Ali+0.000
bes+0.000
we+0.000
Neg logit contributions
 gol-0.000
 Captain-0.000
 pride-0.000
 Cody-0.000
 traded-0.000
Token how
Token ID703
Feature activation+2.59e-01

Pos logit contributions
elope+0.007
bes+0.007
we+0.007
Ali+0.007
zed+0.007
Neg logit contributions
 gol-0.007
 traded-0.006
 pride-0.006
 Captain-0.005
 Cody-0.005
Token expensive
Token ID5789
Feature activation+5.08e+00

Pos logit contributions
 gol+0.011
 Captain+0.011
 traded+0.010
 pride+0.010
 Cody+0.010
Neg logit contributions
elope-0.014
zed-0.014
Ali-0.014
we-0.014
bes-0.014
Token the
Token ID262
Feature activation+1.48e+00

Pos logit contributions
 gol+0.221
 traded+0.211
 Captain+0.201
 pride+0.198
 Cody+0.182
Neg logit contributions
we-0.273
elope-0.273
bes-0.271
comb-0.269
Ali-0.264
Token things
Token ID1243
Feature activation+2.51e+00

Pos logit contributions
 gol+0.074
 traded+0.074
 Captain+0.069
 Loyal+0.068
 Cody+0.068
Neg logit contributions
bes-0.064
 cloud-0.063
we-0.063
elope-0.063
comb-0.061
Token were
Token ID547
Feature activation-5.49e-01

Pos logit contributions
 gol+0.110
 Captain+0.103
 traded+0.100
 pride+0.096
 Cody+0.094
Neg logit contributions
bes-0.139
elope-0.139
comb-0.138
we-0.136
Ali-0.133
Token and
Token ID290
Feature activation-3.91e-01

Pos logit contributions
comb+0.026
bes+0.026
elope+0.026
we+0.026
zed+0.025
Neg logit contributions
 gol-0.028
 Captain-0.026
 traded-0.025
 pride-0.025
 Cody-0.024
Token decided
Token ID3066
Feature activation+6.10e-01

Pos logit contributions
elope+0.022
bes+0.022
comb+0.021
we+0.021
Ali+0.021
Neg logit contributions
 gol-0.017
 Captain-0.016
 traded-0.015
 pride-0.015
 Cody-0.014
Token board
Token ID3096
Feature activation-4.51e-01

Pos logit contributions
elope+0.013
bes+0.012
comb+0.012
Ali+0.012
we+0.012
Neg logit contributions
 gol-0.009
 traded-0.008
 Captain-0.008
 pride-0.008
 Cody-0.008
Token and
Token ID290
Feature activation+4.21e-01

Pos logit contributions
elope+0.026
bes+0.026
comb+0.025
Ali+0.025
we+0.025
Neg logit contributions
 gol-0.019
 Captain-0.018
 traded-0.018
 pride-0.017
 Cody-0.016
Token quickly
Token ID2952
Feature activation+8.97e-02

Pos logit contributions
 gol+0.021
 Captain+0.020
 pride+0.019
 traded+0.019
 Cody+0.019
Neg logit contributions
elope-0.020
Ali-0.020
bes-0.020
comb-0.019
zed-0.019
Token noticed
Token ID6810
Feature activation-9.18e-01

Pos logit contributions
 gol+0.004
 Captain+0.004
 pride+0.004
 traded+0.004
 Cody+0.004
Neg logit contributions
bes-0.005
elope-0.005
zed-0.005
comb-0.005
Ali-0.004
Token something
Token ID1223
Feature activation+1.15e+00

Pos logit contributions
elope+0.048
we+0.048
bes+0.047
comb+0.046
Ali+0.046
Neg logit contributions
 gol-0.042
 traded-0.040
 Captain-0.038
 pride-0.037
 Cody-0.036
Token expensive
Token ID5789
Feature activation+4.29e+00

Pos logit contributions
 gol+0.051
 traded+0.047
 Captain+0.046
 pride+0.045
 Cody+0.043
Neg logit contributions
elope-0.064
we-0.063
bes-0.063
comb-0.063
Ali-0.060
Token shining
Token ID22751
Feature activation+1.56e+00

Pos logit contributions
 gol+0.217
 Captain+0.206
 traded+0.202
 pride+0.200
 Cody+0.188
Neg logit contributions
comb-0.209
bes-0.208
elope-0.205
we-0.205
zed-0.189
Token and
Token ID290
Feature activation+3.79e-01

Pos logit contributions
 gol+0.075
 traded+0.071
 Captain+0.071
 pride+0.070
 Cody+0.066
Neg logit contributions
comb-0.080
elope-0.077
we-0.076
bes-0.074
 cloud-0.071
Token gl
Token ID1278
Feature activation+1.50e+00

Pos logit contributions
 gol+0.018
 traded+0.016
 Captain+0.016
 pride+0.015
 Cody+0.015
Neg logit contributions
elope-0.020
bes-0.020
we-0.020
comb-0.019
Ali-0.019
Tokenint
Token ID600
Feature activation-4.59e-01

Pos logit contributions
 gol+0.102
 Captain+0.098
 traded+0.097
 pride+0.095
 Cody+0.093
Neg logit contributions
bes-0.048
comb-0.048
elope-0.048
we-0.047
zed-0.044
Tokening
Token ID278
Feature activation-2.40e-01

Pos logit contributions
elope+0.023
comb+0.022
bes+0.022
we+0.022
Ali+0.022
Neg logit contributions
 gol-0.023
 Captain-0.022
 traded-0.022
 pride-0.021
 Cody-0.020
Token,
Token ID11
Feature activation-1.99e-01

Pos logit contributions
 gol+0.065
 traded+0.062
 pride+0.060
 Captain+0.059
 Cody+0.056
Neg logit contributions
zed-0.063
comb-0.063
we-0.062
elope-0.062
 Pen-0.061
Token "
Token ID366
Feature activation-1.07e+00

Pos logit contributions
elope+0.010
bes+0.010
comb+0.010
Ali+0.010
we+0.010
Neg logit contributions
 gol-0.009
 Captain-0.009
 traded-0.009
 pride-0.008
 Cody-0.008
TokenLet
Token ID5756
Feature activation-5.91e-01

Pos logit contributions
elope+0.046
we+0.045
Ali+0.044
bes+0.044
comb+0.043
Neg logit contributions
 gol-0.061
 Captain-0.060
 traded-0.059
 pride-0.057
 Cody-0.055
Token me
Token ID502
Feature activation+2.29e+00

Pos logit contributions
elope+0.030
bes+0.029
comb+0.029
Ali+0.029
we+0.028
Neg logit contributions
 gol-0.029
 Captain-0.028
 traded-0.028
 pride-0.026
 Cody-0.026
Token help
Token ID1037
Feature activation-1.91e-01

Pos logit contributions
 gol+0.113
 Cody+0.102
 Captain+0.102
 traded+0.101
 pride+0.098
Neg logit contributions
comb-0.109
elope-0.108
Ali-0.103
ze-0.103
 chin-0.103
Token you
Token ID345
Feature activation+3.53e+00

Pos logit contributions
elope+0.013
bes+0.013
comb+0.013
zed+0.012
Ali+0.012
Neg logit contributions
 Captain-0.006
 gol-0.006
 traded-0.005
 Cody-0.005
 pride-0.005
Token,"
Token ID553
Feature activation+9.78e-01

Pos logit contributions
 gol+0.170
 Captain+0.161
 traded+0.161
 pride+0.153
 Cody+0.150
Neg logit contributions
elope-0.181
bes-0.180
comb-0.177
Ali-0.172
we-0.172
Token and
Token ID290
Feature activation+1.03e+00

Pos logit contributions
 Captain+0.032
 traded+0.030
 better+0.030
 pride+0.029
 gol+0.027
Neg logit contributions
bes-0.064
comb-0.063
ich-0.062
eds-0.061
elope-0.061
Token squ
Token ID2809
Feature activation+1.51e+00

Pos logit contributions
 gol+0.041
 traded+0.037
 Captain+0.037
 pride+0.036
 Cody+0.035
Neg logit contributions
elope-0.060
bes-0.059
Ali-0.058
we-0.057
zed-0.057
Tokenatted
Token ID16898
Feature activation+1.20e-01

Pos logit contributions
 Captain+0.083
 gol+0.079
 Cody+0.074
 Loyal+0.071
 pride+0.070
Neg logit contributions
bes-0.064
elope-0.064
zed-0.063
we-0.061
isa-0.060
Token down
Token ID866
Feature activation+9.35e-01

Pos logit contributions
 Captain+0.003
 better+0.003
 pride+0.003
 traded+0.003
 gol+0.003
Neg logit contributions
bes-0.009
comb-0.008
elope-0.008
ich-0.008
we-0.008
Token pull
Token ID2834
Feature activation-1.87e-01

Pos logit contributions
comb+0.024
we+0.024
elope+0.024
bes+0.024
Ali+0.023
Neg logit contributions
 gol-0.022
 traded-0.022
 Captain-0.021
 pride-0.020
 Cody-0.019
Token the
Token ID262
Feature activation+8.87e-01

Pos logit contributions
elope+0.011
bes+0.011
Ali+0.010
we+0.010
comb+0.010
Neg logit contributions
 gol-0.008
 traded-0.007
 Captain-0.007
 pride-0.007
 Cody-0.007
Token doll
Token ID3654
Feature activation+3.24e-01

Pos logit contributions
 gol+0.060
 Captain+0.058
 traded+0.056
 Cody+0.055
 pride+0.053
Neg logit contributions
bes-0.031
 web-0.027
elope-0.027
we-0.027
comb-0.026
Token from
Token ID422
Feature activation+1.02e+00

Pos logit contributions
 gol+0.011
 traded+0.010
 Captain+0.010
 pride+0.009
 better+0.009
Neg logit contributions
elope-0.021
bes-0.021
Ali-0.020
we-0.020
comb-0.020
Token each
Token ID1123
Feature activation-1.34e+00

Pos logit contributions
 gol+0.038
 Captain+0.036
 traded+0.035
 pride+0.033
 Cody+0.032
Neg logit contributions
elope-0.064
bes-0.064
comb-0.063
Ali-0.062
we-0.062
Token other
Token ID584
Feature activation+3.50e+00

Pos logit contributions
elope+0.092
bes+0.092
comb+0.090
Ali+0.089
we+0.089
Neg logit contributions
 gol-0.041
 Captain-0.038
 traded-0.037
 pride-0.034
 Cody-0.033
Token.
Token ID13
Feature activation-3.54e-02

Pos logit contributions
 gol+0.145
 traded+0.139
 Captain+0.137
 pride+0.132
 Cody+0.125
Neg logit contributions
elope-0.200
bes-0.199
comb-0.196
Ali-0.194
we-0.192
Token The
Token ID383
Feature activation+4.57e-01

Pos logit contributions
bes+0.002
elope+0.002
comb+0.002
we+0.002
Ali+0.002
Neg logit contributions
 gol-0.001
 Captain-0.001
 traded-0.001
 pride-0.001
 Cody-0.001
Token doll
Token ID3654
Feature activation+1.72e-01

Pos logit contributions
 gol+0.031
 Captain+0.030
 Cody+0.028
 traded+0.028
 pride+0.027
Neg logit contributions
bes-0.016
 web-0.013
elope-0.013
 mat-0.013
Ali-0.013
Token makes
Token ID1838
Feature activation-1.16e+00

Pos logit contributions
 gol+0.007
 traded+0.007
 Captain+0.007
 pride+0.007
 Cody+0.006
Neg logit contributions
elope-0.009
bes-0.009
comb-0.009
we-0.009
Ali-0.009
Token a
Token ID257
Feature activation+2.95e-01

Pos logit contributions
elope+0.070
bes+0.070
Ali+0.069
we+0.068
comb+0.068
Neg logit contributions
 gol-0.045
 Captain-0.041
 traded-0.041
 Cody-0.038
 pride-0.037
Token give
Token ID1577
Feature activation+4.36e-02

Pos logit contributions
elope+0.065
bes+0.065
comb+0.064
Ali+0.062
we+0.061
Neg logit contributions
 gol-0.047
 Captain-0.044
 traded-0.044
 pride-0.041
 Cody-0.040
Token you
Token ID345
Feature activation+2.04e+00

Pos logit contributions
 gol+0.002
 traded+0.002
 Captain+0.002
 pride+0.002
 Cody+0.002
Neg logit contributions
elope-0.002
we-0.002
bes-0.002
zed-0.002
comb-0.002
Token this
Token ID428
Feature activation-4.24e-01

Pos logit contributions
 gol+0.075
 Captain+0.069
 traded+0.069
 pride+0.064
 Cody+0.062
Neg logit contributions
elope-0.128
bes-0.127
comb-0.125
Ali-0.123
we-0.122
Token sausage
Token ID31889
Feature activation-1.09e+00

Pos logit contributions
elope+0.022
bes+0.022
Ali+0.021
comb+0.021
we+0.021
Neg logit contributions
 gol-0.020
 traded-0.020
 Captain-0.020
 pride-0.019
 Cody-0.018
Token if
Token ID611
Feature activation-4.31e-01

Pos logit contributions
elope+0.053
bes+0.052
comb+0.051
Ali+0.050
we+0.050
Neg logit contributions
 gol-0.055
 Captain-0.053
 traded-0.052
 pride-0.050
 Cody-0.049
Token you
Token ID345
Feature activation+3.65e+00

Pos logit contributions
elope+0.025
bes+0.024
comb+0.024
Ali+0.024
we+0.023
Neg logit contributions
 gol-0.018
 Captain-0.017
 traded-0.017
 pride-0.016
 Cody-0.016
Token slap
Token ID23905
Feature activation+5.59e-01

Pos logit contributions
 gol+0.168
 Captain+0.158
 Cody+0.145
 pride+0.144
 traded+0.140
Neg logit contributions
comb-0.195
elope-0.185
bes-0.182
ze-0.175
 chin-0.175
Token me
Token ID502
Feature activation+2.48e+00

Pos logit contributions
 gol+0.023
 Captain+0.022
 traded+0.022
 pride+0.021
 Cody+0.020
Neg logit contributions
elope-0.032
bes-0.032
comb-0.031
Ali-0.031
we-0.031
Token on
Token ID319
Feature activation-2.20e-01

Pos logit contributions
 gol+0.112
 Captain+0.109
 traded+0.108
 pride+0.100
 better+0.100
Neg logit contributions
elope-0.131
Ali-0.129
bes-0.128
comb-0.125
we-0.124
Token the
Token ID262
Feature activation+4.23e-01

Pos logit contributions
elope+0.015
comb+0.015
we+0.014
Ali+0.014
bes+0.014
Neg logit contributions
 Captain-0.007
 gol-0.007
 Cody-0.006
 traded-0.006
 better-0.006
Token back
Token ID736
Feature activation+6.46e-01

Pos logit contributions
 gol+0.020
 traded+0.020
 Captain+0.020
 better+0.020
 Cody+0.019
Neg logit contributions
elope-0.022
Ali-0.022
bes-0.021
we-0.021
comb-0.020
Token.
Token ID13
Feature activation+9.04e-02

Pos logit contributions
elope+0.057
Ali+0.056
bes+0.055
comb+0.055
we+0.054
Neg logit contributions
 gol-0.039
 traded-0.038
 Captain-0.037
 pride-0.036
 Cody-0.034
Token
Token ID198
Feature activation+3.15e-01

Pos logit contributions
 gol+0.004
 traded+0.004
 pride+0.004
 Captain+0.004
 Cody+0.004
Neg logit contributions
elope-0.005
bes-0.005
Ali-0.005
we-0.004
comb-0.004
Token
Token ID198
Feature activation+8.29e-02

Pos logit contributions
 gol+0.013
 traded+0.012
 Captain+0.012
 pride+0.011
 Cody+0.011
Neg logit contributions
elope-0.019
bes-0.018
Ali-0.018
comb-0.018
we-0.018
TokenShe
Token ID3347
Feature activation+9.65e-02

Pos logit contributions
 gol+0.005
 Captain+0.005
 traded+0.005
 pride+0.005
 Cody+0.004
Neg logit contributions
bes-0.003
elope-0.003
Ali-0.003
we-0.003
comb-0.003
Token sees
Token ID7224
Feature activation-6.01e-02

Pos logit contributions
 gol+0.005
 Captain+0.005
 traded+0.005
 Cody+0.005
 pride+0.004
Neg logit contributions
Ali-0.005
bes-0.005
elope-0.004
 web-0.004
 Pen-0.004
Token the
Token ID262
Feature activation+7.89e-01

Pos logit contributions
bes+0.003
Ali+0.003
elope+0.003
we+0.003
 cloud+0.003
Neg logit contributions
 gol-0.003
 traded-0.003
 Captain-0.002
 Cody-0.002
 pride-0.002
Token tower
Token ID10580
Feature activation-1.50e+00

Pos logit contributions
 gol+0.039
 Captain+0.037
 traded+0.036
 pride+0.036
 Cody+0.034
Neg logit contributions
elope-0.041
bes-0.040
comb-0.038
we-0.037
Ali-0.037
Token.
Token ID13
Feature activation-7.83e-02

Pos logit contributions
elope+0.097
bes+0.095
Ali+0.092
comb+0.092
Pen+0.090
Neg logit contributions
 traded-0.049
 gol-0.048
 better-0.047
 Captain-0.046
 pride-0.044
Token It
Token ID632
Feature activation+3.48e-01

Pos logit contributions
elope+0.004
bes+0.004
Ali+0.004
comb+0.004
 Pen+0.004
Neg logit contributions
 gol-0.004
 traded-0.003
 pride-0.003
 Captain-0.003
 Cody-0.003
Token is
Token ID318
Feature activation-6.19e-01

Pos logit contributions
 gol+0.017
 Captain+0.017
 traded+0.017
 pride+0.016
 Cody+0.015
Neg logit contributions
elope-0.017
bes-0.017
comb-0.017
Ali-0.016
we-0.016
Token very
Token ID845
Feature activation+4.78e-03

Pos logit contributions
comb+0.032
elope+0.032
bes+0.032
Ali+0.031
we+0.030
Neg logit contributions
 gol-0.030
 traded-0.028
 Captain-0.028
 Cody-0.026
 pride-0.026
Token the
Token ID262
Feature activation+1.74e-01

Pos logit contributions
elope+0.021
bes+0.021
comb+0.021
Ali+0.021
we+0.021
Neg logit contributions
 gol-0.016
 traded-0.015
 Captain-0.015
 pride-0.014
 Cody-0.013
Token coffee
Token ID6891
Feature activation+1.84e-01

Pos logit contributions
 gol+0.009
 Captain+0.008
 traded+0.008
 pride+0.008
 Cody+0.008
Neg logit contributions
elope-0.009
comb-0.008
bes-0.008
Ali-0.008
we-0.008
Token.
Token ID13
Feature activation-9.51e-02

Pos logit contributions
 gol+0.008
 Captain+0.008
 traded+0.008
 pride+0.007
 Cody+0.007
Neg logit contributions
elope-0.010
bes-0.010
Ali-0.010
comb-0.010
we-0.010
Token He
Token ID679
Feature activation+6.42e-01

Pos logit contributions
bes+0.005
elope+0.005
zed+0.005
 chin+0.005
Ali+0.005
Neg logit contributions
 gol-0.004
 Captain-0.004
 pride-0.004
 traded-0.004
 Cody-0.004
Token sees
Token ID7224
Feature activation+7.24e-02

Pos logit contributions
 gol+0.034
 Captain+0.030
 pride+0.029
 Cody+0.029
 traded+0.029
Neg logit contributions
elope-0.032
Ali-0.032
bes-0.031
we-0.030
comb-0.029
Token a
Token ID257
Feature activation+9.23e-01

Pos logit contributions
 gol+0.003
 traded+0.003
 Captain+0.003
 pride+0.003
 Cody+0.003
Neg logit contributions
bes-0.004
we-0.004
Ali-0.004
elope-0.004
ze-0.004
Token bottle
Token ID9294
Feature activation+4.87e-02

Pos logit contributions
 gol+0.045
 Captain+0.043
 traded+0.043
 pride+0.041
 Cody+0.040
Neg logit contributions
elope-0.047
bes-0.046
comb-0.045
Ali-0.044
we-0.044
Token of
Token ID286
Feature activation+1.13e+00

Pos logit contributions
 gol+0.002
 Captain+0.002
 traded+0.002
 pride+0.002
 Cody+0.001
Neg logit contributions
elope-0.003
bes-0.003
comb-0.003
we-0.003
Ali-0.003
Token k
Token ID479
Feature activation+1.07e+00

Pos logit contributions
 gol+0.061
 traded+0.058
 Captain+0.057
 Cody+0.054
 pride+0.053
Neg logit contributions
bes-0.052
elope-0.048
we-0.048
Ali-0.047
comb-0.046
Tokenetchup
Token ID47132
Feature activation+1.38e+00

Pos logit contributions
 gol+0.051
 traded+0.047
 Captain+0.044
 pride+0.043
 chalk+0.042
Neg logit contributions
elope-0.059
zed-0.058
comb-0.056
bes-0.055
Ali-0.055
Token in
Token ID287
Feature activation+5.25e-01

Pos logit contributions
 gol+0.055
 traded+0.052
 Captain+0.052
 pride+0.048
 Cody+0.047
Neg logit contributions
elope-0.083
bes-0.082
comb-0.080
Ali-0.080
we-0.078
Token go
Token ID467
Feature activation+9.79e-02

Pos logit contributions
 gol+0.019
 traded+0.018
 Captain+0.017
 pride+0.017
 Cody+0.016
Neg logit contributions
elope-0.022
comb-0.021
bes-0.021
Ali-0.020
zed-0.020
Token home
Token ID1363
Feature activation+2.22e+00

Pos logit contributions
 gol+0.005
 traded+0.004
 pride+0.004
 Captain+0.004
 Cody+0.004
Neg logit contributions
elope-0.005
bes-0.005
comb-0.005
we-0.005
eds-0.005
Token."
Token ID526
Feature activation+4.15e-02

Pos logit contributions
 gol+0.092
 Captain+0.089
 traded+0.087
 pride+0.083
 Cody+0.082
Neg logit contributions
elope-0.126
bes-0.125
Ali-0.123
comb-0.122
we-0.121
Token Emma
Token ID18966
Feature activation+1.91e-01

Pos logit contributions
 gol+0.002
 traded+0.002
 pride+0.002
 Captain+0.002
 online+0.001
Neg logit contributions
elope-0.002
bes-0.002
Ali-0.002
 Pen-0.002
comb-0.002
Token knew
Token ID2993
Feature activation+1.54e+00

Pos logit contributions
 gol+0.007
 Captain+0.007
 traded+0.007
 pride+0.006
 Cody+0.006
Neg logit contributions
elope-0.012
bes-0.011
comb-0.011
Ali-0.011
we-0.011
Token that
Token ID326
Feature activation+2.66e-01

Pos logit contributions
 gol+0.072
 traded+0.068
 Captain+0.065
 pride+0.063
 Cody+0.059
Neg logit contributions
elope-0.084
comb-0.082
bes-0.081
Ali-0.080
zed-0.080
Token it
Token ID340
Feature activation+7.09e-01

Pos logit contributions
 gol+0.009
 Captain+0.009
 traded+0.009
 pride+0.008
 Cody+0.008
Neg logit contributions
bes-0.017
elope-0.017
comb-0.017
Ali-0.016
we-0.016
Token was
Token ID373
Feature activation+1.47e-01

Pos logit contributions
 gol+0.031
 traded+0.030
 Captain+0.030
 pride+0.028
 Cody+0.027
Neg logit contributions
bes-0.039
elope-0.038
comb-0.038
Ali-0.037
we-0.037
Token time
Token ID640
Feature activation+1.35e-01

Pos logit contributions
 gol+0.007
 traded+0.006
 Captain+0.006
 Cody+0.006
 pride+0.006
Neg logit contributions
elope-0.008
comb-0.008
zed-0.008
bes-0.008
 Pen-0.007
Token to
Token ID284
Feature activation+3.52e-01

Pos logit contributions
 gol+0.006
 Captain+0.005
 traded+0.005
 pride+0.005
 Cody+0.005
Neg logit contributions
elope-0.008
comb-0.007
bes-0.007
we-0.007
zed-0.007
Token wait
Token ID4043
Feature activation-8.59e-01

Pos logit contributions
 gol+0.016
 traded+0.015
 Captain+0.015
 pride+0.014
 Cody+0.013
Neg logit contributions
elope-0.019
comb-0.019
bes-0.018
Ali-0.018
zed-0.018
Token of
Token ID286
Feature activation-8.40e-01

Pos logit contributions
 gol+0.045
 traded+0.043
 Captain+0.042
 pride+0.039
 Cody+0.039
Neg logit contributions
elope-0.068
bes-0.068
comb-0.067
we-0.067
Ali-0.066
Token its
Token ID663
Feature activation-6.77e-01

Pos logit contributions
elope+0.041
bes+0.041
comb+0.041
Ali+0.040
we+0.039
Neg logit contributions
 gol-0.042
 Captain-0.041
 traded-0.040
 pride-0.039
 Cody-0.037
Token hard
Token ID1327
Feature activation-6.27e-02

Pos logit contributions
elope+0.044
bes+0.044
comb+0.043
Ali+0.043
we+0.043
Neg logit contributions
 gol-0.023
 Captain-0.021
 traded-0.021
 pride-0.020
 Cody-0.019
Token work
Token ID670
Feature activation+1.60e+00

Pos logit contributions
elope+0.005
bes+0.005
comb+0.005
Ali+0.005
we+0.005
Neg logit contributions
 gol-0.002
 Captain-0.001
 traded-0.001
 pride-0.001
 Cody-0.001
Token.
Token ID13
Feature activation-3.37e-01

Pos logit contributions
 gol+0.070
 Captain+0.066
 traded+0.066
 pride+0.063
 Cody+0.061
Neg logit contributions
elope-0.088
bes-0.087
comb-0.086
Ali-0.084
we-0.084
Token From
Token ID3574
Feature activation+1.10e+00

Pos logit contributions
elope+0.020
bes+0.020
Ali+0.019
comb+0.019
zed+0.019
Neg logit contributions
 gol-0.014
 traded-0.013
 Captain-0.012
 pride-0.011
 Cody-0.011
Token then
Token ID788
Feature activation+4.53e-01

Pos logit contributions
 gol+0.059
 traded+0.057
 Captain+0.054
 pride+0.053
 Cody+0.051
Neg logit contributions
elope-0.051
bes-0.046
we-0.046
Ali-0.045
comb-0.045
Token on
Token ID319
Feature activation-1.17e+00

Pos logit contributions
 gol+0.018
 Captain+0.017
 traded+0.017
 pride+0.016
 Cody+0.016
Neg logit contributions
elope-0.027
bes-0.027
comb-0.026
Ali-0.026
we-0.026
Token,
Token ID11
Feature activation+3.22e-02

Pos logit contributions
bes+0.078
elope+0.077
comb+0.076
we+0.075
Ali+0.075
Neg logit contributions
 gol-0.038
 Captain-0.036
 traded-0.035
 pride-0.033
 Cody-0.032
Token it
Token ID340
Feature activation-4.98e-01

Pos logit contributions
 gol+0.001
 traded+0.001
 Captain+0.001
 pride+0.001
 Cody+0.001
Neg logit contributions
elope-0.002
bes-0.002
comb-0.002
Ali-0.002
we-0.002
Token kept
Token ID4030
Feature activation-3.45e-01

Pos logit contributions
elope+0.029
bes+0.029
comb+0.028
Ali+0.028
we+0.027
Neg logit contributions
 gol-0.021
 Captain-0.020
 traded-0.020
 pride-0.018
 Cody-0.018
Token She
Token ID1375
Feature activation-8.78e-02

Pos logit contributions
 gol+0.003
 traded+0.002
 Captain+0.002
 better+0.002
 richer+0.002
Neg logit contributions
elope-0.002
bes-0.002
Ali-0.002
zed-0.002
 lap-0.002
Token was
Token ID373
Feature activation+1.17e-01

Pos logit contributions
elope+0.005
bes+0.004
comb+0.004
Ali+0.004
zed+0.004
Neg logit contributions
 gol-0.004
 Captain-0.004
 traded-0.004
 Cody-0.004
 pride-0.004
Token so
Token ID523
Feature activation+1.17e-01

Pos logit contributions
 gol+0.005
 traded+0.005
 Captain+0.005
 Cody+0.004
 pride+0.004
Neg logit contributions
elope-0.007
comb-0.007
bes-0.007
Ali-0.007
zed-0.006
Token excited
Token ID6568
Feature activation-1.63e+00

Pos logit contributions
 gol+0.005
 Captain+0.005
 traded+0.005
 Cody+0.004
 Loyal+0.004
Neg logit contributions
elope-0.006
comb-0.006
bes-0.006
zed-0.006
Ali-0.006
Token when
Token ID618
Feature activation-2.53e-01

Pos logit contributions
elope+0.089
bes+0.088
comb+0.087
we+0.087
Ali+0.084
Neg logit contributions
 gol-0.073
 traded-0.069
 Captain-0.069
 pride-0.065
 Cody-0.063
Token she
Token ID673
Feature activation+1.05e+00

Pos logit contributions
elope+0.013
we+0.013
Ali+0.012
comb+0.012
zed+0.012
Neg logit contributions
 gol-0.012
 traded-0.012
 Captain-0.011
 pride-0.010
vious-0.010
Token found
Token ID1043
Feature activation+1.23e+00

Pos logit contributions
 gol+0.049
 Captain+0.044
 pride+0.043
 traded+0.041
 Cody+0.041
Neg logit contributions
elope-0.058
comb-0.056
zed-0.055
Ali-0.055
bes-0.055
Token it
Token ID340
Feature activation+2.49e-01

Pos logit contributions
 gol+0.068
 traded+0.063
 Captain+0.054
 Cody+0.052
vious+0.051
Neg logit contributions
elope-0.060
comb-0.057
Ali-0.056
 Pen-0.056
zed-0.055
Token.
Token ID13
Feature activation+1.44e-01

Pos logit contributions
 gol+0.013
 Captain+0.012
 traded+0.012
 pride+0.011
 Cody+0.011
Neg logit contributions
elope-0.012
bes-0.012
comb-0.012
we-0.012
Ali-0.012
Token
Token ID220
Feature activation-1.32e-01

Pos logit contributions
 gol+0.008
 traded+0.008
 Captain+0.007
 better+0.007
 richer+0.007
Neg logit contributions
elope-0.005
bes-0.005
zed-0.005
Ali-0.005
 lap-0.005
Token
Token ID198
Feature activation+2.86e-01

Pos logit contributions
elope+0.007
bes+0.007
Ali+0.007
we+0.006
comb+0.006
Neg logit contributions
 gol-0.007
 traded-0.006
 Captain-0.006
 pride-0.006
 Cody-0.005
Token.
Token ID13
Feature activation+4.94e-01

Pos logit contributions
 gol+0.033
 traded+0.032
 Captain+0.031
 pride+0.030
 Cody+0.029
Neg logit contributions
elope-0.041
bes-0.041
comb-0.040
Ali-0.040
we-0.039
Token "
Token ID366
Feature activation-3.47e-01

Pos logit contributions
 gol+0.023
 traded+0.022
 Captain+0.022
 pride+0.021
 Cody+0.020
Neg logit contributions
elope-0.026
bes-0.026
we-0.024
Ali-0.024
comb-0.024
TokenYes
Token ID5297
Feature activation+5.34e-01

Pos logit contributions
elope+0.018
bes+0.017
comb+0.017
Ali+0.016
zed+0.016
Neg logit contributions
 gol-0.017
 Captain-0.016
 traded-0.016
 pride-0.015
 Cody-0.015
Token,
Token ID11
Feature activation+1.13e+00

Pos logit contributions
 gol+0.017
 Captain+0.017
 traded+0.016
 pride+0.015
 Cody+0.015
Neg logit contributions
bes-0.036
elope-0.036
comb-0.035
Ali-0.034
we-0.034
Token it
Token ID340
Feature activation+2.47e-01

Pos logit contributions
 gol+0.054
 traded+0.051
 Captain+0.050
 pride+0.048
 Cody+0.047
Neg logit contributions
elope-0.058
comb-0.057
bes-0.057
Ali-0.056
we-0.056
Token is
Token ID318
Feature activation-5.76e-01

Pos logit contributions
 traded+0.010
 Captain+0.010
 gol+0.010
 better+0.009
 pride+0.009
Neg logit contributions
bes-0.014
comb-0.014
elope-0.014
we-0.013
Ali-0.013
Token,"
Token ID553
Feature activation+9.53e-01

Pos logit contributions
elope+0.027
bes+0.026
comb+0.026
we+0.024
Ali+0.024
Neg logit contributions
 gol-0.032
 traded-0.030
 Captain-0.029
 Cody-0.028
 pride-0.028
Token said
Token ID531
Feature activation+2.27e+00

Pos logit contributions
 gol+0.024
 traded+0.022
 Captain+0.022
 pride+0.020
 Cody+0.019
Neg logit contributions
elope-0.070
bes-0.070
comb-0.069
Ali-0.068
we-0.068
Token her
Token ID607
Feature activation-8.65e-01

Pos logit contributions
 gol+0.098
 Captain+0.092
 traded+0.092
 pride+0.087
 Cody+0.084
Neg logit contributions
elope-0.129
bes-0.127
comb-0.125
Ali-0.123
we-0.122
Token mom
Token ID1995
Feature activation-1.59e-01

Pos logit contributions
elope+0.047
bes+0.047
comb+0.046
we+0.046
zed+0.045
Neg logit contributions
 gol-0.039
 pride-0.037
 traded-0.037
 Captain-0.037
 better-0.034
Token.
Token ID13
Feature activation+3.73e-01

Pos logit contributions
elope+0.009
bes+0.009
comb+0.008
Ali+0.008
we+0.008
Neg logit contributions
 gol-0.007
 traded-0.007
 Captain-0.007
 pride-0.006
 Cody-0.006
Token named
Token ID3706
Feature activation+1.93e+00

Pos logit contributions
 gol+0.003
 traded+0.003
 Captain+0.003
 chalk+0.003
 pride+0.002
Neg logit contributions
bes-0.011
comb-0.011
Ali-0.011
zed-0.011
elope-0.011
Token Lily
Token ID20037
Feature activation+5.08e-01

Pos logit contributions
 gol+0.059
 Captain+0.053
 traded+0.052
 pride+0.048
 Cody+0.046
Neg logit contributions
elope-0.137
bes-0.135
comb-0.134
Ali-0.131
we-0.131
Token.
Token ID13
Feature activation+2.00e-01

Pos logit contributions
 gol+0.018
 traded+0.018
 Captain+0.016
 pride+0.016
 better+0.015
Neg logit contributions
bes-0.032
comb-0.032
Ali-0.031
elope-0.031
zed-0.031
Token Lily
Token ID20037
Feature activation+6.23e-01

Pos logit contributions
 gol+0.009
 Captain+0.008
 traded+0.008
 pride+0.008
 Cody+0.008
Neg logit contributions
elope-0.011
bes-0.011
comb-0.011
Ali-0.011
we-0.010
Token loved
Token ID6151
Feature activation+1.69e-02

Pos logit contributions
 traded+0.020
 gol+0.020
 Captain+0.019
 pride+0.018
 Cody+0.017
Neg logit contributions
comb-0.040
bes-0.040
elope-0.040
Ali-0.039
we-0.039
Token to
Token ID284
Feature activation-3.73e-01

Pos logit contributions
 gol+0.001
 traded+0.001
 Captain+0.001
 pride+0.000
 Cody+0.000
Neg logit contributions
elope-0.001
bes-0.001
comb-0.001
Ali-0.001
we-0.001
Token play
Token ID711
Feature activation+7.83e-01

Pos logit contributions
elope+0.024
bes+0.023
we+0.023
comb+0.023
Ali+0.023
Neg logit contributions
 gol-0.013
 traded-0.013
 Captain-0.013
 pride-0.012
 Cody-0.011
Token outside
Token ID2354
Feature activation-3.94e-02

Pos logit contributions
 gol+0.026
 traded+0.025
 Captain+0.025
 chalk+0.021
 online+0.021
Neg logit contributions
elope-0.054
comb-0.051
Ali-0.050
isa-0.050
bes-0.049
Token and
Token ID290
Feature activation+4.84e-01

Pos logit contributions
elope+0.003
bes+0.003
comb+0.003
Ali+0.003
zed+0.003
Neg logit contributions
 better-0.001
 traded-0.001
 gol-0.001
 online-0.001
 chalk-0.001
Token get
Token ID651
Feature activation-8.92e-02

Pos logit contributions
 gol+0.021
 traded+0.020
 Captain+0.020
 pride+0.019
 Cody+0.019
Neg logit contributions
elope-0.027
bes-0.027
comb-0.026
Ali-0.026
we-0.026
Token dirty
Token ID11841
Feature activation+4.71e-01

Pos logit contributions
we+0.004
Pen+0.003
 Pen+0.003
 gag+0.003
bes+0.003
Neg logit contributions
 gol-0.005
 Captain-0.005
 Cody-0.004
 traded-0.004
 Loyal-0.004
Token to
Token ID284
Feature activation-6.17e-01

Pos logit contributions
 gol+0.028
 Captain+0.025
 traded+0.024
 Cody+0.024
 pride+0.023
Neg logit contributions
elope-0.029
we-0.029
bes-0.028
Ali-0.028
 Pen-0.028
Token go
Token ID467
Feature activation-3.07e-01

Pos logit contributions
elope+0.034
bes+0.034
comb+0.033
Ali+0.032
we+0.032
Neg logit contributions
 gol-0.027
 Captain-0.026
 traded-0.026
 pride-0.024
 Cody-0.024
Token back
Token ID736
Feature activation-1.66e-01

Pos logit contributions
elope+0.015
we+0.015
eds+0.015
bes+0.014
comb+0.014
Neg logit contributions
 gol-0.015
 Captain-0.013
 pride-0.013
 Cody-0.013
 traded-0.013
Token to
Token ID284
Feature activation-2.52e-01

Pos logit contributions
elope+0.009
bes+0.009
we+0.009
comb+0.009
Ali+0.009
Neg logit contributions
 gol-0.008
 traded-0.007
 Captain-0.007
 pride-0.007
 Cody-0.006
Token their
Token ID511
Feature activation-9.35e-01

Pos logit contributions
bes+0.017
elope+0.017
comb+0.017
Ali+0.016
we+0.016
Neg logit contributions
 gol-0.008
 Captain-0.008
 traded-0.008
 pride-0.007
 Cody-0.007
Token bus
Token ID1323
Feature activation-5.76e-01

Pos logit contributions
elope+0.050
bes+0.050
comb+0.050
Ali+0.049
we+0.048
Neg logit contributions
 gol-0.043
 traded-0.041
 Captain-0.041
 pride-0.039
 Cody-0.037
Token.
Token ID13
Feature activation-6.32e-01

Pos logit contributions
elope+0.029
bes+0.029
comb+0.028
we+0.027
Ali+0.027
Neg logit contributions
 gol-0.028
 Captain-0.027
 traded-0.026
 pride-0.026
 Cody-0.025
Token
Token ID198
Feature activation-2.98e-01

Pos logit contributions
elope+0.035
bes+0.034
Ali+0.033
we+0.033
comb+0.032
Neg logit contributions
 gol-0.028
 traded-0.027
 Captain-0.026
 pride-0.025
 Cody-0.024
Token
Token ID198
Feature activation-4.74e-01

Pos logit contributions
elope+0.017
bes+0.017
Ali+0.017
comb+0.016
we+0.016
Neg logit contributions
 gol-0.013
 traded-0.012
 Captain-0.012
 pride-0.011
 Cody-0.011
TokenThey
Token ID2990
Feature activation-9.45e-01

Pos logit contributions
elope+0.019
bes+0.019
Ali+0.018
we+0.018
comb+0.017
Neg logit contributions
 gol-0.029
 traded-0.028
 Captain-0.028
 pride-0.027
 Cody-0.026
Token got
Token ID1392
Feature activation+1.19e-01

Pos logit contributions
elope+0.046
comb+0.044
Ali+0.044
bes+0.044
zed+0.043
Neg logit contributions
 gol-0.047
 Captain-0.044
 pride-0.040
 traded-0.040
 Cody-0.040
Token leaves
Token ID5667
Feature activation+1.20e+00

Pos logit contributions
 gol+0.040
 Cody+0.038
 Captain+0.037
 pride+0.036
 traded+0.035
Neg logit contributions
comb-0.036
elope-0.036
bes-0.035
 web-0.034
we-0.033
Token for
Token ID329
Feature activation+4.91e-01

Pos logit contributions
 gol+0.058
 Captain+0.055
 traded+0.054
 pride+0.053
 Cody+0.052
Neg logit contributions
comb-0.061
elope-0.060
bes-0.060
we-0.058
Ali-0.057
Token the
Token ID262
Feature activation-7.44e-01

Pos logit contributions
 gol+0.018
 traded+0.017
 Captain+0.016
 pride+0.016
 Cody+0.015
Neg logit contributions
bes-0.031
elope-0.030
comb-0.029
we-0.029
Ali-0.029
Token nest
Token ID16343
Feature activation-2.98e+00

Pos logit contributions
bes+0.034
elope+0.034
Ali+0.032
we+0.032
comb+0.031
Neg logit contributions
 gol-0.040
 traded-0.038
 Captain-0.038
 pride-0.037
 better-0.036
Token.
Token ID13
Feature activation+1.30e-01

Pos logit contributions
elope+0.159
bes+0.158
comb+0.155
Ali+0.152
we+0.151
Neg logit contributions
 gol-0.136
 Captain-0.129
 traded-0.129
 pride-0.122
 Cody-0.119
Token They
Token ID1119
Feature activation-3.92e-01

Pos logit contributions
 gol+0.007
 pride+0.006
 Cody+0.006
 written+0.006
 Captain+0.006
Neg logit contributions
elope-0.006
bes-0.006
we-0.005
zed-0.005
comb-0.005
Token all
Token ID477
Feature activation+2.35e-01

Pos logit contributions
comb+0.023
elope+0.023
bes+0.021
Ali+0.021
zed+0.021
Neg logit contributions
 gol-0.016
 Captain-0.015
 Cody-0.014
 pride-0.013
 traded-0.013
Token worked
Token ID3111
Feature activation+2.95e-01

Pos logit contributions
 gol+0.009
 Captain+0.009
 Cody+0.008
 pride+0.007
 traded+0.007
Neg logit contributions
elope-0.015
comb-0.014
bes-0.014
Ali-0.014
zed-0.014
Token together
Token ID1978
Feature activation-7.40e-01

Pos logit contributions
 gol+0.013
 traded+0.012
 Captain+0.012
 pride+0.011
 Cody+0.011
Neg logit contributions
bes-0.017
elope-0.016
we-0.016
comb-0.015
zed-0.015
Token and
Token ID290
Feature activation+4.02e-02

Pos logit contributions
elope+0.046
bes+0.046
comb+0.045
Ali+0.045
we+0.045
Neg logit contributions
 gol-0.027
 Captain-0.025
 traded-0.025
 pride-0.024
 Cody-0.023
Token soon
Token ID2582
Feature activation-1.33e+00

Pos logit contributions
 gol+0.002
 pride+0.002
vious+0.001
 Captain+0.001
 Cody+0.001
Neg logit contributions
elope-0.002
comb-0.002
zed-0.002
bes-0.002
we-0.002
Token dust
Token ID8977
Feature activation-6.37e-02

Pos logit contributions
 gol+0.015
 traded+0.014
 Captain+0.014
 Cody+0.013
 pride+0.013
Neg logit contributions
elope-0.016
bes-0.016
comb-0.016
we-0.015
Ali-0.015
Token and
Token ID290
Feature activation+4.18e-01

Pos logit contributions
elope+0.004
bes+0.004
comb+0.004
Ali+0.003
we+0.003
Neg logit contributions
 gol-0.003
 Captain-0.003
 traded-0.003
 pride-0.002
 Cody-0.002
Token its
Token ID663
Feature activation+1.37e-01

Pos logit contributions
 gol+0.020
 traded+0.018
 Captain+0.017
 Cody+0.017
 pride+0.016
Neg logit contributions
elope-0.022
bes-0.021
we-0.020
comb-0.020
zed-0.020
Token mysterious
Token ID11428
Feature activation+1.15e+00

Pos logit contributions
 gol+0.007
 Captain+0.007
 traded+0.007
 pride+0.006
 Cody+0.006
Neg logit contributions
elope-0.007
bes-0.007
comb-0.006
Ali-0.006
we-0.006
Token beauty
Token ID8737
Feature activation+1.57e+00

Pos logit contributions
 gol+0.059
 Captain+0.056
 traded+0.056
 pride+0.053
 Cody+0.052
Neg logit contributions
elope-0.055
bes-0.055
comb-0.054
Ali-0.053
we-0.052
Token.
Token ID13
Feature activation-6.14e-02

Pos logit contributions
 gol+0.070
 Captain+0.066
 traded+0.066
 pride+0.063
 Cody+0.061
Neg logit contributions
elope-0.086
bes-0.085
comb-0.084
we-0.082
Ali-0.082
Token<|endoftext|>
Token ID50256
Feature activation-4.95e-01

Pos logit contributions
elope+0.003
bes+0.003
zed+0.003
Ali+0.003
 Pen+0.003
Neg logit contributions
 gol-0.003
 traded-0.003
 Captain-0.003
 pride-0.003
vious-0.003
TokenOnce
Token ID7454
Feature activation-8.98e-01

Pos logit contributions
elope+0.028
bes+0.027
Ali+0.027
we+0.027
comb+0.026
Neg logit contributions
 gol-0.022
 traded-0.020
 Captain-0.020
 pride-0.020
 Cody-0.018
Token upon
Token ID2402
Feature activation-4.01e-01

Pos logit contributions
elope+0.049
Ali+0.048
zed+0.046
comb+0.046
 Pen+0.045
Neg logit contributions
 gol-0.040
 traded-0.037
 Captain-0.037
 pride-0.035
 Cody-0.032
Token a
Token ID257
Feature activation+1.07e+00

Pos logit contributions
elope+0.029
bes+0.028
comb+0.028
we+0.028
Ali+0.028
Neg logit contributions
 gol-0.011
 traded-0.010
 Captain-0.010
 pride-0.009
 Cody-0.009
Token time
Token ID640
Feature activation+8.15e-01

Pos logit contributions
 gol+0.019
 traded+0.018
 pride+0.015
 Captain+0.015
 better+0.015
Neg logit contributions
we-0.087
bes-0.084
comb-0.083
eds-0.080
ich-0.080
Token every
Token ID790
Feature activation-1.51e+00

Pos logit contributions
 gol+0.046
 traded+0.043
 pride+0.041
 Captain+0.040
vious+0.038
Neg logit contributions
elope-0.057
comb-0.054
Ali-0.053
bes-0.053
zed-0.052
Token day
Token ID1110
Feature activation+3.37e-01

Pos logit contributions
bes+0.111
we+0.108
comb+0.104
elope+0.104
Ali+0.103
Neg logit contributions
 gol-0.041
 Captain-0.039
 traded-0.038
 better-0.034
 pride-0.034
Token,
Token ID11
Feature activation+5.73e-01

Pos logit contributions
 gol+0.014
 pride+0.013
 traded+0.013
 Captain+0.012
 online+0.011
Neg logit contributions
elope-0.018
Ali-0.018
we-0.018
zed-0.018
bes-0.017
Token Tommy
Token ID19919
Feature activation+1.20e+00

Pos logit contributions
 gol+0.023
 traded+0.022
 pride+0.021
 Captain+0.020
vious+0.018
Neg logit contributions
elope-0.032
Ali-0.032
bes-0.032
 Pen-0.031
comb-0.031
Token and
Token ID290
Feature activation+6.13e-01

Pos logit contributions
 gol+0.057
 pride+0.055
 Captain+0.053
 Cody+0.049
 traded+0.049
Neg logit contributions
elope-0.064
bes-0.061
comb-0.060
Ali-0.059
isa-0.058
Token Larry
Token ID13633
Feature activation-3.46e+00

Pos logit contributions
 Captain+0.029
 gol+0.027
 pride+0.026
 traded+0.026
 Cody+0.025
Neg logit contributions
bes-0.035
comb-0.032
we-0.032
ze-0.030
elope-0.030
Token filled
Token ID5901
Feature activation-8.44e-01

Pos logit contributions
elope+0.172
comb+0.162
isa+0.153
Ali+0.151
bes+0.147
Neg logit contributions
 gol-0.187
 Captain-0.174
 Cody-0.163
 pride-0.158
 Loyal-0.151
Token the
Token ID262
Feature activation+1.44e+00

Pos logit contributions
elope+0.052
bes+0.052
comb+0.050
we+0.050
Ali+0.050
Neg logit contributions
 gol-0.032
 traded-0.029
 Captain-0.029
 pride-0.027
 Cody-0.026
Token big
Token ID1263
Feature activation+5.60e-01

Pos logit contributions
 gol+0.083
 Captain+0.080
 traded+0.080
 pride+0.077
 Cody+0.075
Neg logit contributions
elope-0.060
bes-0.059
comb-0.057
Ali-0.056
we-0.056
Token place
Token ID1295
Feature activation+4.73e-02

Pos logit contributions
 gol+0.031
 Captain+0.030
 traded+0.029
 pride+0.028
 Cody+0.028
Neg logit contributions
elope-0.025
bes-0.025
comb-0.024
Ali-0.023
we-0.023
Token with
Token ID351
Feature activation-2.54e-01

Pos logit contributions
 gol+0.002
 Captain+0.002
 traded+0.002
 pride+0.002
 Cody+0.002
Neg logit contributions
elope-0.002
bes-0.002
comb-0.002
Ali-0.002
we-0.002
Token stayed
Token ID9658
Feature activation-9.95e-01

Pos logit contributions
 gol+0.039
 Captain+0.036
 traded+0.035
 pride+0.034
 Cody+0.034
Neg logit contributions
elope-0.051
bes-0.049
comb-0.049
we-0.048
Ali-0.048
Token and
Token ID290
Feature activation+8.55e-02

Pos logit contributions
elope+0.056
bes+0.055
comb+0.054
we+0.053
Ali+0.053
Neg logit contributions
 gol-0.043
 traded-0.040
 Captain-0.040
 pride-0.037
 Cody-0.037
Token watched
Token ID7342
Feature activation-1.79e+00

Pos logit contributions
 gol+0.004
 Captain+0.004
 traded+0.004
 pride+0.003
 Cody+0.003
Neg logit contributions
elope-0.005
comb-0.004
Ali-0.004
bes-0.004
we-0.004
Token for
Token ID329
Feature activation+3.54e-01

Pos logit contributions
elope+0.100
we+0.098
bes+0.098
comb+0.097
zed+0.097
Neg logit contributions
 gol-0.076
 traded-0.072
 Captain-0.067
 pride-0.065
 Cody-0.064
Token a
Token ID257
Feature activation-6.42e-01

Pos logit contributions
 gol+0.013
 traded+0.013
 Captain+0.012
 Cody+0.011
 pride+0.011
Neg logit contributions
elope-0.022
bes-0.022
comb-0.021
Ali-0.021
we-0.021
Token while
Token ID981
Feature activation-3.07e+00

Pos logit contributions
elope+0.032
bes+0.031
comb+0.031
Ali+0.030
we+0.030
Neg logit contributions
 gol-0.032
 traded-0.031
 Captain-0.030
 pride-0.029
 Cody-0.028
Token until
Token ID1566
Feature activation-9.00e-01

Pos logit contributions
elope+0.162
comb+0.155
we+0.155
bes+0.154
Ali+0.152
Neg logit contributions
 gol-0.144
 traded-0.139
 Captain-0.131
 pride-0.128
 Cody-0.126
Token he
Token ID339
Feature activation+9.77e-01

Pos logit contributions
zed+0.044
elope+0.043
comb+0.041
Ali+0.039
 Pen+0.039
Neg logit contributions
 gol-0.044
 traded-0.040
 pride-0.038
umbo-0.038
vious-0.037
Token got
Token ID1392
Feature activation-1.36e-01

Pos logit contributions
 gol+0.043
 Captain+0.039
 traded+0.039
 pride+0.038
 Cody+0.037
Neg logit contributions
elope-0.055
comb-0.053
Ali-0.053
bes-0.052
we-0.052
Token tired
Token ID10032
Feature activation-6.92e-01

Pos logit contributions
elope+0.006
 breath+0.006
 Pen+0.006
comb+0.006
eds+0.005
Neg logit contributions
 gol-0.007
 Captain-0.006
 Loyal-0.006
 traded-0.006
umbo-0.005
Token.
Token ID13
Feature activation-2.01e-01

Pos logit contributions
elope+0.034
comb+0.034
bes+0.033
we+0.033
Ali+0.032
Neg logit contributions
 gol-0.034
 traded-0.033
 Captain-0.032
 pride-0.031
 Cody-0.030
Token holding
Token ID4769
Feature activation-7.83e-01

Pos logit contributions
 gol+0.009
 Captain+0.009
 traded+0.009
 pride+0.008
 Cody+0.008
Neg logit contributions
elope-0.015
bes-0.015
comb-0.015
Ali-0.014
we-0.014
Token his
Token ID465
Feature activation-8.44e-01

Pos logit contributions
elope+0.048
bes+0.048
Ali+0.047
we+0.046
comb+0.046
Neg logit contributions
 gol-0.030
 traded-0.028
 Captain-0.027
 Cody-0.025
 pride-0.025
Token mom
Token ID1995
Feature activation-6.08e-01

Pos logit contributions
elope+0.043
bes+0.043
comb+0.042
Ali+0.042
we+0.041
Neg logit contributions
 gol-0.041
 Captain-0.039
 traded-0.039
 pride-0.037
 Cody-0.036
Tokenâ
Token ID22940
Feature activation-9.16e-01

Pos logit contributions
bes+0.042
comb+0.042
elope+0.042
Ali+0.041
we+0.040
Neg logit contributions
 traded-0.017
 gol-0.017
 Captain-0.016
 pride-0.015
 better-0.015
Token
Token ID26391
Feature activation+1.39e-01

Pos logit contributions
bes+0.046
elope+0.046
comb+0.045
Ali+0.044
we+0.044
Neg logit contributions
 gol-0.045
 traded-0.043
 Captain-0.042
 pride-0.040
 Cody-0.039
Token
Token ID8151
Feature activation-3.45e+00

Pos logit contributions
 traded+0.006
 Johnny+0.006
 gol+0.006
 fixed+0.006
 Cody+0.006
Neg logit contributions
comb-0.007
Pen-0.007
 thorn-0.006
 gag-0.006
 web-0.006
Tokens
Token ID82
Feature activation-3.73e-01

Pos logit contributions
bes+0.191
elope+0.190
comb+0.186
Ali+0.183
we+0.181
Neg logit contributions
 gol-0.151
 traded-0.144
 Captain-0.143
 pride-0.135
 Cody-0.133
Token hand
Token ID1021
Feature activation-2.65e+00

Pos logit contributions
elope+0.018
comb+0.017
Ali+0.017
we+0.017
bes+0.017
Neg logit contributions
 gol-0.019
 pride-0.019
 Captain-0.019
 traded-0.018
 Cody-0.017
Token tight
Token ID5381
Feature activation+9.40e-01

Pos logit contributions
elope+0.155
bes+0.154
comb+0.151
Ali+0.150
we+0.148
Neg logit contributions
 gol-0.107
 traded-0.103
 Captain-0.102
 pride-0.096
 Cody-0.093
Token and
Token ID290
Feature activation+5.78e-01

Pos logit contributions
 gol+0.038
 traded+0.037
 Captain+0.036
 pride+0.034
 Cody+0.034
Neg logit contributions
elope-0.054
bes-0.053
Ali-0.053
comb-0.053
we-0.052
Token shaking
Token ID17275
Feature activation-3.30e-01

Pos logit contributions
 gol+0.022
 traded+0.022
 Captain+0.021
 pride+0.020
 Cody+0.020
Neg logit contributions
elope-0.035
bes-0.034
comb-0.034
we-0.033
Ali-0.033
Token lady
Token ID10846
Feature activation+2.93e-01

Pos logit contributions
 gol+0.140
 traded+0.137
 Captain+0.136
 pride+0.132
 Cody+0.126
Neg logit contributions
elope-0.136
bes-0.133
comb-0.132
Ali-0.128
we-0.126
Token saw
Token ID2497
Feature activation-1.71e-01

Pos logit contributions
 gol+0.015
 pride+0.014
 Captain+0.013
 Cody+0.013
 traded+0.013
Neg logit contributions
elope-0.016
we-0.015
Ali-0.014
isa-0.014
comb-0.014
Token him
Token ID683
Feature activation+5.78e-01

Pos logit contributions
elope+0.011
Ali+0.010
we+0.010
bes+0.010
zed+0.010
Neg logit contributions
 gol-0.007
 traded-0.006
 pride-0.006
 Captain-0.005
 Cody-0.005
Token sne
Token ID10505
Feature activation-9.41e-01

Pos logit contributions
 gol+0.021
 traded+0.021
 Captain+0.020
 better+0.019
 Cody+0.018
Neg logit contributions
bes-0.035
Ali-0.035
elope-0.035
comb-0.034
we-0.034
Tokene
Token ID68
Feature activation-1.45e+00

Pos logit contributions
comb+0.036
elope+0.035
bes+0.034
we+0.033
Ali+0.033
Neg logit contributions
 gol-0.057
 traded-0.056
 pride-0.055
 Captain-0.054
vious-0.051
Tokenze
Token ID2736
Feature activation-3.25e+00

Pos logit contributions
elope+0.041
Ali+0.039
comb+0.038
Pen+0.034
isa+0.032
Neg logit contributions
 traded-0.098
 Captain-0.098
 gol-0.095
 better-0.092
 fixed-0.091
Token and
Token ID290
Feature activation+2.45e-01

Pos logit contributions
elope+0.223
bes+0.216
Ali+0.215
comb+0.210
Pen+0.208
Neg logit contributions
 Captain-0.095
 traded-0.094
 gol-0.093
 better-0.089
 written-0.083
Token said
Token ID531
Feature activation+7.53e-01

Pos logit contributions
 gol+0.008
 traded+0.007
 Captain+0.007
 pride+0.007
 Cody+0.006
Neg logit contributions
elope-0.017
bes-0.016
comb-0.016
Ali-0.016
we-0.016
Token,
Token ID11
Feature activation-4.73e-01

Pos logit contributions
 gol+0.026
 Captain+0.025
 traded+0.025
 pride+0.023
 Cody+0.022
Neg logit contributions
elope-0.048
bes-0.048
comb-0.047
Ali-0.047
we-0.046
Token "
Token ID366
Feature activation-1.12e+00

Pos logit contributions
elope+0.026
bes+0.026
comb+0.025
Ali+0.025
we+0.024
Neg logit contributions
 gol-0.021
 Captain-0.020
 traded-0.020
 Cody-0.019
 pride-0.019
TokenB
Token ID33
Feature activation-9.62e-01

Pos logit contributions
bes+0.065
comb+0.063
elope+0.062
zed+0.059
 web+0.058
Neg logit contributions
 gol-0.049
 Captain-0.047
 traded-0.045
 Cody-0.043
 pride-0.043
Token kitten
Token ID42143
Feature activation-1.67e+00

Pos logit contributions
elope+0.018
bes+0.018
comb+0.018
Ali+0.017
we+0.017
Neg logit contributions
 gol-0.031
 Captain-0.029
 traded-0.029
 pride-0.028
 Cody-0.028
Token home
Token ID1363
Feature activation+1.76e+00

Pos logit contributions
elope+0.104
bes+0.103
comb+0.101
Ali+0.099
we+0.099
Neg logit contributions
 gol-0.062
 Captain-0.058
 traded-0.058
 pride-0.054
 Cody-0.053
Token."
Token ID526
Feature activation-2.62e-01

Pos logit contributions
 gol+0.076
 Captain+0.073
 traded+0.073
 pride+0.069
 Cody+0.067
Neg logit contributions
elope-0.097
bes-0.096
Ali-0.095
comb-0.094
we-0.092
Token
Token ID198
Feature activation+4.85e-01

Pos logit contributions
bes+0.018
comb+0.018
we+0.017
elope+0.017
zed+0.017
Neg logit contributions
 Captain-0.007
 gol-0.007
 traded-0.007
 pride-0.007
 better-0.006
Token
Token ID198
Feature activation+1.75e-01

Pos logit contributions
 Captain+0.007
 better+0.007
 traded+0.007
 pride+0.007
 gol+0.006
Neg logit contributions
comb-0.038
bes-0.038
 chin-0.037
we-0.037
elope-0.036
TokenM
Token ID44
Feature activation-4.21e+00

Pos logit contributions
 better+0.007
 traded+0.007
 decide+0.007
 gol+0.006
 pride+0.006
Neg logit contributions
bes-0.009
 chin-0.009
ich-0.009
comb-0.008
elope-0.008
Tokenia
Token ID544
Feature activation-1.65e+00

Pos logit contributions
bes+0.147
elope+0.141
we+0.136
comb+0.134
Ali+0.131
Neg logit contributions
 gol-0.269
 traded-0.257
 Captain-0.254
 pride-0.250
 Cody-0.237
Token and
Token ID290
Feature activation+5.26e-01

Pos logit contributions
elope+0.095
bes+0.094
comb+0.093
we+0.091
Ali+0.091
Neg logit contributions
 gol-0.068
 traded-0.066
 Captain-0.065
 pride-0.061
 Cody-0.059
Token her
Token ID607
Feature activation-6.22e-01

Pos logit contributions
 traded+0.009
 pride+0.007
 Captain+0.007
 gol+0.006
 chalk+0.006
Neg logit contributions
we-0.044
bes-0.044
lor-0.043
iders-0.042
comb-0.041
Token mom
Token ID1995
Feature activation-2.40e-01

Pos logit contributions
comb+0.037
bes+0.036
elope+0.036
Ali+0.036
zed+0.036
Neg logit contributions
 gol-0.025
 pride-0.025
 traded-0.025
 Captain-0.023
 Cody-0.022
Token took
Token ID1718
Feature activation-1.18e-01

Pos logit contributions
elope+0.014
comb+0.014
bes+0.014
Ali+0.014
we+0.014
Neg logit contributions
 gol-0.010
 Captain-0.009
 traded-0.008
 pride-0.008
 Cody-0.008