TOP ACTIVATIONS
MAX = 9.386

to Africa and see more ze br as ."
did not see any baby ze br as .
he was playing make - bel ieve at home , too
was ready for make - bel ieve fun . <|endoftext|> Once
a world of make - bel ieve . She
L ily watched as the ze br as ran as fast
and they played make - bel ieve . Finally , they
that says " Feed the ze br as ". He has
wanted to see the baby ze br as . They were
He would race make - bel ieve cars around the track
watch as the wild sugar scam pered away .
But as they approached the ze br as , Lily got
Lily wanted to see the ze br as the most .
we can 't . The ze br as have their own
pen and looked for the ze br as . They saw
to stay away from the ze br as . The end
John began to make - bel ieve he was a hero
Finally , her make - bel ieve adventures were recorded .
aff es , and fast ze br as . Tim was
. They saw four baby ze br as running and playing

MIN ACTIVATIONS
MIN = -8.057

orange . Lily wore her orange belt every day . It
. He wore his favorite red shirt and blue shorts every
. She wore her favorite red m itten on her hand
my loved wearing his favorite red socks every day . He
. He shows Lily his red train with a yellow bow
my loved wearing his favorite red cap everywhere he went .
. Tim my loved his red shirt and wore it every
. Tim wore his big red coat because it was cold
He loved to wear his red hat everywhere he went .
She loved to wear her orange bath robe after taking a
. She wore her favorite pink boots , which made her
who liked to wear his red cap . He always did
who liked to wear her red dress and her shiny shoes
outside , especially with his red flag . One day ,
loved to play with his red ball outside . One day
loved to wear her favorite pink dress every day . One
loved to play with his red wagon . He would pull
loved to play with his red blocks . Every day ,
my loved to wear his red cap everywhere he went .
swim . She had her red swimming suit ready , her

INTERVAL 5.025 - 9.386
CONTAINS 0.101%

racing each other and making noises . One day
I love seeing all the animals !" Her
He was the best n oder in the world !
. They pretend they are animals or pirates or fair ies
who can spot the most animals on the way ," dad

INTERVAL 0.665 - 5.025
CONTAINS 31.731%

Her mom my left the little girl alone with the box
tree . The tree yelled , " No ! Stop !
to draw on it . She took her cr ay ons
The goat felt sad and didn 't know what
hair again and always felt guilty for what he had done

INTERVAL -3.696 - 0.665
CONTAINS 66.946%

made her so excited ! There was a little puppy outside
and her mom my went outside to play on the lawn
smiled and flew away , happy to help his friend .
and says , " This can be our roof . We
They wished they had not gone in the chamber . They

INTERVAL -8.057 - -3.696
CONTAINS 1.223%

Now , Tim 's room was clean , and
He had a big , red ball . He loved to
gave her a big , juicy apple . Lily took a
. Where is his blue bowl ? He asks
guitar . He had a nice guitar with red and blue
Token to
Token ID284
Feature activation+9.26e-01

Pos logit contributions
ows+0.085
pering+0.084
obb+0.083
arl+0.081
iving+0.079
Neg logit contributions
 penny-0.055
 flavor-0.054
 ornament-0.052
 peanut-0.052
 cube-0.051
Token Africa
Token ID5478
Feature activation+5.11e+00

Pos logit contributions
ows+0.033
pering+0.031
obb+0.031
arl+0.030
iving+0.029
Neg logit contributions
 flavor-0.027
 penny-0.027
 ornament-0.026
 peanut-0.026
 cube-0.025
Token and
Token ID290
Feature activation-2.07e-01

Pos logit contributions
pering+0.190
arl+0.189
obb+0.189
 sons+0.184
ows+0.176
Neg logit contributions
 flavor-0.125
 ornament-0.120
 penny-0.115
 nut-0.109
 peanut-0.109
Token see
Token ID766
Feature activation+6.23e-02

Pos logit contributions
 penny+0.007
 flavor+0.007
 ornament+0.007
 peanut+0.006
 cube+0.006
Neg logit contributions
ows-0.006
pering-0.006
obb-0.006
arl-0.006
iving-0.006
Token more
Token ID517
Feature activation-7.22e-01

Pos logit contributions
ows+0.002
obb+0.002
pering+0.002
arl+0.002
iving+0.002
Neg logit contributions
 flavor-0.002
 ornament-0.002
 penny-0.002
 peanut-0.002
 cube-0.001
Token ze
Token ID41271
Feature activation+9.39e+00

Pos logit contributions
 flavor+0.022
 peanut+0.021
 penny+0.021
 ornament+0.020
 color+0.020
Neg logit contributions
obb-0.026
pering-0.024
ows-0.024
arl-0.024
adders-0.022
Tokenbr
Token ID1671
Feature activation+1.15e+00

Pos logit contributions
pering+0.411
 sons+0.404
 realize+0.397
obb+0.397
icia+0.387
Neg logit contributions
 flavor-0.131
 nut-0.128
 penny-0.127
 peanut-0.126
 ornament-0.122
Tokenas
Token ID292
Feature activation+4.04e+00

Pos logit contributions
pering+0.013
obb+0.012
ows+0.011
 announcements+0.009
arl+0.009
Neg logit contributions
 flavor-0.058
 penny-0.057
 ornament-0.056
 cube-0.056
 peanut-0.056
Token."
Token ID526
Feature activation-1.21e-01

Pos logit contributions
obb+0.159
ows+0.140
pering+0.140
arl+0.138
rig+0.138
Neg logit contributions
 ornament-0.101
 penny-0.099
 cube-0.096
 flavor-0.092
c-0.090
Token
Token ID198
Feature activation-8.50e-02

Pos logit contributions
 penny+0.003
 flavor+0.003
 ornament+0.003
 cube+0.003
 peanut+0.003
Neg logit contributions
ows-0.004
pering-0.004
obb-0.004
arl-0.004
iving-0.004
Token
Token ID198
Feature activation-2.43e-01

Pos logit contributions
 flavor+0.002
 penny+0.002
 ornament+0.002
 peanut+0.002
 cube+0.001
Neg logit contributions
ows-0.004
pering-0.004
obb-0.004
iving-0.003
oms-0.003
Token did
Token ID750
Feature activation-4.47e-01

Pos logit contributions
pering+0.060
ows+0.059
arl+0.058
obb+0.056
iving+0.056
Neg logit contributions
 flavor-0.043
 penny-0.043
 peanut-0.041
 cube-0.040
 ornament-0.040
Token not
Token ID407
Feature activation+9.73e-01

Pos logit contributions
 flavor+0.010
 penny+0.010
 cube+0.009
 peanut+0.009
 ornament+0.009
Neg logit contributions
arl-0.018
pering-0.017
ows-0.017
iving-0.017
obb-0.017
Token see
Token ID766
Feature activation+9.16e-01

Pos logit contributions
ows+0.025
pering+0.025
obb+0.024
arl+0.023
oms+0.022
Neg logit contributions
 flavor-0.036
 penny-0.036
 peanut-0.035
 ornament-0.034
 cube-0.034
Token any
Token ID597
Feature activation+1.48e+00

Pos logit contributions
ows+0.034
pering+0.033
arl+0.033
iving+0.033
obb+0.032
Neg logit contributions
 penny-0.024
 flavor-0.024
 peanut-0.023
 ornament-0.023
 cube-0.022
Token baby
Token ID5156
Feature activation+3.37e-01

Pos logit contributions
ows+0.048
pering+0.047
obb+0.046
arl+0.045
iving+0.043
Neg logit contributions
 flavor-0.044
 penny-0.044
 ornament-0.043
 peanut-0.042
 cube-0.042
Token ze
Token ID41271
Feature activation+9.03e+00

Pos logit contributions
arl+0.010
obb+0.010
ows+0.009
pering+0.009
uits+0.009
Neg logit contributions
 penny-0.012
 flavor-0.011
 ornament-0.011
 peanut-0.011
 cube-0.011
Tokenbr
Token ID1671
Feature activation+4.71e-01

Pos logit contributions
 sons+0.396
pering+0.393
ows+0.375
 realize+0.373
arl+0.373
Neg logit contributions
 nut-0.126
 flavor-0.125
 penny-0.123
on-0.121
 peanut-0.121
Tokenas
Token ID292
Feature activation+4.01e+00

Pos logit contributions
pering+0.004
ows+0.004
obb+0.004
arl+0.003
iving+0.003
Neg logit contributions
 flavor-0.025
 penny-0.025
 ornament-0.024
 cube-0.024
 peanut-0.024
Token.
Token ID13
Feature activation+6.16e-02

Pos logit contributions
obb+0.164
ows+0.149
 announcements+0.146
rig+0.146
arl+0.146
Neg logit contributions
 penny-0.092
 cube-0.089
 ornament-0.088
 flavor-0.081
 peanut-0.081
Token
Token ID198
Feature activation-4.83e-01

Pos logit contributions
pering+0.002
ows+0.002
obb+0.002
iving+0.002
arl+0.002
Neg logit contributions
 flavor-0.002
 peanut-0.001
 penny-0.001
 cube-0.001
 ornament-0.001
Token
Token ID198
Feature activation-5.59e-01

Pos logit contributions
 flavor+0.008
 penny+0.007
 peanut+0.007
 cube+0.007
 ornament+0.007
Neg logit contributions
obb-0.022
pering-0.022
ows-0.022
iving-0.022
arl-0.021
Token he
Token ID339
Feature activation+2.70e+00

Pos logit contributions
ows+0.213
arl+0.202
obb+0.196
pering+0.191
adders+0.186
Neg logit contributions
 penny-0.099
 flavor-0.099
 cube-0.091
 peanut-0.091
 ornament-0.089
Token was
Token ID373
Feature activation-9.80e-02

Pos logit contributions
ows+0.124
arl+0.124
pering+0.122
obb+0.117
adders+0.117
Neg logit contributions
 flavor-0.049
 penny-0.049
 peanut-0.045
 cube-0.042
 ornament-0.042
Token playing
Token ID2712
Feature activation+2.00e+00

Pos logit contributions
 penny+0.002
 flavor+0.002
 ornament+0.002
 peanut+0.002
 cube+0.002
Neg logit contributions
ows-0.004
arl-0.004
pering-0.003
obb-0.003
oms-0.003
Token make
Token ID787
Feature activation+6.78e-01

Pos logit contributions
arl+0.090
ows+0.088
pering+0.088
obb+0.086
oms+0.085
Neg logit contributions
 ornament-0.037
 flavor-0.036
 penny-0.036
 cube-0.035
 peanut-0.031
Token-
Token ID12
Feature activation+1.05e+00

Pos logit contributions
arl+0.029
pering+0.028
obb+0.028
ows+0.026
oms+0.026
Neg logit contributions
 flavor-0.017
 ornament-0.015
 penny-0.015
 peanut-0.015
 cube-0.015
Tokenbel
Token ID6667
Feature activation+8.90e+00

Pos logit contributions
pering+0.021
ows+0.021
obb+0.020
arl+0.019
iving+0.018
Neg logit contributions
 flavor-0.044
 penny-0.044
 ornament-0.044
 cube-0.043
 peanut-0.043
Tokenieve
Token ID12311
Feature activation+8.99e-01

Pos logit contributions
pering+0.174
ows+0.167
arl+0.165
iving+0.145
obb+0.143
Neg logit contributions
 ornament-0.388
 flavor-0.382
 penny-0.379
 cube-0.365
 pencil-0.349
Token at
Token ID379
Feature activation+1.12e+00

Pos logit contributions
arl+0.036
pering+0.035
obb+0.035
ows+0.033
ighters+0.032
Neg logit contributions
 flavor-0.023
 penny-0.023
 ornament-0.023
 cube-0.022
 pencil-0.020
Token home
Token ID1363
Feature activation-1.09e+00

Pos logit contributions
pering+0.031
ows+0.030
obb+0.029
oms+0.028
arl+0.028
Neg logit contributions
 penny-0.036
 flavor-0.036
 peanut-0.035
 ornament-0.035
 cube-0.034
Token,
Token ID11
Feature activation+5.93e-01

Pos logit contributions
 flavor+0.027
 penny+0.025
 cube+0.025
 ornament+0.025
 color+0.023
Neg logit contributions
arl-0.045
obb-0.044
pering-0.042
oms-0.041
ighters-0.040
Token too
Token ID1165
Feature activation+1.78e-01

Pos logit contributions
ows+0.021
obb+0.021
arl+0.021
pering+0.020
oms+0.019
Neg logit contributions
 penny-0.017
 flavor-0.017
 ornament-0.016
 peanut-0.016
 cube-0.016
Token was
Token ID373
Feature activation+6.03e-02

Pos logit contributions
arl+0.004
pering+0.004
obb+0.004
ows+0.004
adders+0.004
Neg logit contributions
 flavor-0.002
 penny-0.002
 peanut-0.002
 ornament-0.002
 cube-0.002
Token ready
Token ID3492
Feature activation+9.18e-01

Pos logit contributions
ows+0.002
arl+0.002
pering+0.002
obb+0.002
iving+0.002
Neg logit contributions
 penny-0.002
 flavor-0.002
 ornament-0.002
 peanut-0.002
 cube-0.002
Token for
Token ID329
Feature activation+1.44e+00

Pos logit contributions
obb+0.042
pering+0.041
ows+0.041
ighters+0.041
arl+0.040
Neg logit contributions
 flavor-0.016
 penny-0.015
 cube-0.014
 peanut-0.013
 ornament-0.013
Token make
Token ID787
Feature activation+6.93e-01

Pos logit contributions
ows+0.058
arl+0.056
obb+0.054
iving+0.054
pering+0.054
Neg logit contributions
 flavor-0.035
 penny-0.033
 peanut-0.032
 ornament-0.032
 cube-0.031
Token-
Token ID12
Feature activation+1.14e+00

Pos logit contributions
arl+0.032
pering+0.029
obb+0.029
ows+0.029
oms+0.028
Neg logit contributions
 flavor-0.016
 ornament-0.014
 penny-0.014
 peanut-0.014
 cube-0.013
Tokenbel
Token ID6667
Feature activation+8.75e+00

Pos logit contributions
pering+0.036
ows+0.036
arl+0.035
obb+0.035
oms+0.032
Neg logit contributions
 flavor-0.037
 penny-0.036
 ornament-0.036
 cube-0.035
 peanut-0.035
Tokenieve
Token ID12311
Feature activation+1.35e+00

Pos logit contributions
arl+0.216
pering+0.213
ows+0.204
iving+0.181
oms+0.177
Neg logit contributions
 ornament-0.339
 flavor-0.338
 penny-0.326
 cube-0.310
 pencil-0.302
Token fun
Token ID1257
Feature activation+4.73e-01

Pos logit contributions
arl+0.056
obb+0.053
pering+0.052
ows+0.050
adders+0.048
Neg logit contributions
 flavor-0.035
 cube-0.033
 ornament-0.033
 penny-0.033
 color-0.030
Token.
Token ID13
Feature activation+2.98e-01

Pos logit contributions
arl+0.019
pering+0.018
obb+0.018
ows+0.017
ighters+0.017
Neg logit contributions
 flavor-0.013
 cube-0.012
 ornament-0.012
 color-0.012
 penny-0.012
Token<|endoftext|>
Token ID50256
Feature activation+4.33e+00

Pos logit contributions
pering+0.011
ows+0.011
obb+0.011
arl+0.011
iving+0.010
Neg logit contributions
 flavor-0.007
 penny-0.007
 ornament-0.007
 cube-0.007
 peanut-0.007
TokenOnce
Token ID7454
Feature activation-4.67e-01

Pos logit contributions
pering+0.143
ows+0.143
obb+0.140
arl+0.136
 announcements+0.131
Neg logit contributions
 flavor-0.126
 penny-0.123
 ornament-0.121
 cube-0.119
 peanut-0.117
Token a
Token ID257
Feature activation+1.38e+00

Pos logit contributions
 flavor+0.048
 penny+0.048
 ornament+0.047
 peanut+0.046
 cube+0.045
Neg logit contributions
ows-0.055
pering-0.054
obb-0.052
arl-0.052
iving-0.050
Token world
Token ID995
Feature activation+3.07e+00

Pos logit contributions
pering+0.040
ows+0.037
obb+0.036
 announcements+0.036
aults+0.035
Neg logit contributions
 flavor-0.043
 penny-0.042
 cube-0.040
 ornament-0.040
pol-0.039
Token of
Token ID286
Feature activation+1.48e+00

Pos logit contributions
obb+0.102
pering+0.102
arl+0.102
ows+0.098
ighters+0.095
Neg logit contributions
 ornament-0.089
 flavor-0.088
 penny-0.088
 cube-0.084
 peanut-0.081
Token make
Token ID787
Feature activation+8.19e-01

Pos logit contributions
ows+0.051
pering+0.050
obb+0.048
arl+0.048
iving+0.046
Neg logit contributions
 flavor-0.042
 penny-0.041
 ornament-0.041
 peanut-0.040
 cube-0.039
Token-
Token ID12
Feature activation+1.11e+00

Pos logit contributions
arl+0.038
pering+0.034
obb+0.034
ows+0.031
oms+0.031
Neg logit contributions
 flavor-0.018
 ornament-0.018
 peanut-0.017
 color-0.016
c-0.016
Tokenbel
Token ID6667
Feature activation+8.74e+00

Pos logit contributions
pering+0.025
ows+0.025
obb+0.024
arl+0.024
iving+0.022
Neg logit contributions
 flavor-0.044
 ornament-0.043
 penny-0.043
 peanut-0.042
 cube-0.042
Tokenieve
Token ID12311
Feature activation+7.32e-01

Pos logit contributions
pering+0.163
arl+0.159
ows+0.158
iving+0.139
obb+0.138
Neg logit contributions
 ornament-0.381
 flavor-0.377
 penny-0.370
 cube-0.356
 pencil-0.345
Token.
Token ID13
Feature activation-9.56e-02

Pos logit contributions
arl+0.030
obb+0.029
pering+0.028
ows+0.027
oms+0.026
Neg logit contributions
 ornament-0.018
 flavor-0.018
 penny-0.017
 color-0.016
 symbol-0.016
Token
Token ID198
Feature activation-3.40e-01

Pos logit contributions
 penny+0.003
 flavor+0.003
 ornament+0.003
 cube+0.003
 peanut+0.003
Neg logit contributions
ows-0.003
pering-0.003
arl-0.003
oms-0.003
obb-0.003
Token
Token ID198
Feature activation-4.22e-01

Pos logit contributions
 penny+0.009
 flavor+0.009
 ornament+0.009
 cube+0.008
 peanut+0.008
Neg logit contributions
ows-0.012
pering-0.012
arl-0.011
obb-0.011
oms-0.011
TokenShe
Token ID3347
Feature activation+1.42e+00

Pos logit contributions
 ornament+0.013
 penny+0.013
 flavor+0.013
 peanut+0.012
 cube+0.012
Neg logit contributions
ows-0.014
pering-0.013
obb-0.013
arl-0.013
oms-0.012
TokenL
Token ID43
Feature activation+3.58e+00

Pos logit contributions
 penny+0.015
 flavor+0.015
 ornament+0.015
 cube+0.015
 peanut+0.014
Neg logit contributions
ows-0.024
pering-0.024
obb-0.023
oms-0.023
adders-0.022
Tokenily
Token ID813
Feature activation-1.92e+00

Pos logit contributions
pering+0.098
 announcements+0.095
ows+0.087
aults+0.087
obb+0.086
Neg logit contributions
 ornament-0.125
 flavor-0.124
 cube-0.120
 penny-0.120
 peanut-0.117
Token watched
Token ID7342
Feature activation+2.84e+00

Pos logit contributions
 penny+0.046
 flavor+0.046
 ornament+0.044
 cube+0.043
 peanut+0.043
Neg logit contributions
ows-0.073
pering-0.073
arl-0.070
obb-0.070
iving-0.068
Token as
Token ID355
Feature activation+3.13e+00

Pos logit contributions
ows+0.117
obb+0.109
arl+0.108
pering+0.106
adders+0.105
Neg logit contributions
 ornament-0.070
 penny-0.068
 cube-0.066
 flavor-0.065
 peanut-0.064
Token the
Token ID262
Feature activation+2.34e+00

Pos logit contributions
ows+0.166
iving+0.149
arl+0.149
immers+0.149
ets+0.146
Neg logit contributions
 penny-0.051
 ornament-0.050
 mint-0.045
 avocado-0.044
 pencil-0.044
Token ze
Token ID41271
Feature activation+8.69e+00

Pos logit contributions
ows+0.079
pering+0.078
obb+0.075
arl+0.073
iving+0.072
Neg logit contributions
 flavor-0.069
 penny-0.068
 peanut-0.066
 ornament-0.065
 cube-0.065
Tokenbr
Token ID1671
Feature activation+4.09e-01

Pos logit contributions
pering+0.380
 sons+0.360
ows+0.357
arl+0.355
 stations+0.352
Neg logit contributions
 nut-0.141
 flavor-0.140
 peanut-0.136
 penny-0.136
 ornament-0.130
Tokenas
Token ID292
Feature activation+3.64e+00

Pos logit contributions
pering+0.006
ows+0.005
obb+0.005
arl+0.005
 announcements+0.004
Neg logit contributions
 flavor-0.020
 penny-0.019
 ornament-0.019
 cube-0.019
 peanut-0.019
Token ran
Token ID4966
Feature activation+4.40e+00

Pos logit contributions
pering+0.144
arl+0.142
obb+0.141
ows+0.138
ighters+0.132
Neg logit contributions
 penny-0.086
 cube-0.083
 flavor-0.082
 ornament-0.079
 comb-0.075
Token as
Token ID355
Feature activation+3.14e+00

Pos logit contributions
ighters+0.176
obb+0.174
arl+0.171
ows+0.168
ains+0.166
Neg logit contributions
 penny-0.098
 cube-0.091
 ornament-0.088
 mine-0.088
 flavor-0.083
Token fast
Token ID3049
Feature activation+1.74e+00

Pos logit contributions
ows+0.116
arl+0.111
iving+0.110
pering+0.110
oms+0.103
Neg logit contributions
 penny-0.089
 ornament-0.084
 flavor-0.083
 cube-0.081
 peanut-0.075
Token and
Token ID290
Feature activation-1.19e+00

Pos logit contributions
 flavor+0.018
 penny+0.018
 ornament+0.017
 cube+0.017
 peanut+0.017
Neg logit contributions
pering-0.021
arl-0.021
obb-0.020
ows-0.020
 announcements-0.019
Token they
Token ID484
Feature activation+1.84e+00

Pos logit contributions
 flavor+0.033
 penny+0.032
 ornament+0.031
 peanut+0.031
 cube+0.030
Neg logit contributions
pering-0.044
ows-0.043
obb-0.042
arl-0.042
oms-0.040
Token played
Token ID2826
Feature activation+2.36e+00

Pos logit contributions
ows+0.069
pering+0.069
obb+0.066
arl+0.065
iving+0.064
Neg logit contributions
 penny-0.046
 flavor-0.045
 ornament-0.044
 peanut-0.043
 cube-0.043
Token make
Token ID787
Feature activation+4.82e-01

Pos logit contributions
arl+0.103
pering+0.101
obb+0.099
oms+0.097
ows+0.095
Neg logit contributions
 flavor-0.047
 ornament-0.045
 cube-0.043
 penny-0.043
 color-0.039
Token-
Token ID12
Feature activation+1.04e+00

Pos logit contributions
arl+0.022
pering+0.022
obb+0.021
oms+0.019
ows+0.019
Neg logit contributions
 flavor-0.010
 ornament-0.009
 peanut-0.009
 pencil-0.008
 cube-0.008
Tokenbel
Token ID6667
Feature activation+8.66e+00

Pos logit contributions
pering+0.019
ows+0.019
obb+0.018
arl+0.017
iving+0.016
Neg logit contributions
 flavor-0.046
 penny-0.045
 ornament-0.045
 cube-0.044
 peanut-0.044
Tokenieve
Token ID12311
Feature activation+4.57e-01

Pos logit contributions
pering+0.175
arl+0.167
ows+0.163
iving+0.146
obb+0.143
Neg logit contributions
 ornament-0.374
 flavor-0.368
 penny-0.361
 cube-0.350
 pencil-0.335
Token.
Token ID13
Feature activation+5.13e-02

Pos logit contributions
arl+0.019
pering+0.019
obb+0.018
ows+0.018
oms+0.017
Neg logit contributions
 flavor-0.011
 ornament-0.010
 penny-0.010
 cube-0.010
 color-0.009
Token Finally
Token ID9461
Feature activation+2.28e+00

Pos logit contributions
pering+0.001
ows+0.001
obb+0.001
arl+0.001
iving+0.001
Neg logit contributions
 flavor-0.002
 penny-0.002
 peanut-0.002
 ornament-0.002
 cube-0.002
Token,
Token ID11
Feature activation+1.41e+00

Pos logit contributions
ows+0.101
pering+0.099
arl+0.094
adders+0.093
 announcements+0.093
Neg logit contributions
 penny-0.047
 flavor-0.046
 peanut-0.045
 cube-0.041
 ornament-0.038
Token they
Token ID484
Feature activation+3.35e+00

Pos logit contributions
ows+0.037
pering+0.036
arl+0.034
obb+0.033
adders+0.033
Neg logit contributions
 penny-0.054
 flavor-0.054
 peanut-0.052
 cube-0.050
 ornament-0.050
Token that
Token ID326
Feature activation-5.80e-01

Pos logit contributions
ows+0.013
pering+0.013
arl+0.012
obb+0.012
oms+0.012
Neg logit contributions
 flavor-0.013
 penny-0.013
 ornament-0.012
 peanut-0.012
 cube-0.012
Token says
Token ID1139
Feature activation+3.29e-01

Pos logit contributions
 penny+0.019
 flavor+0.019
 ornament+0.019
 peanut+0.019
 cube+0.019
Neg logit contributions
pering-0.017
ows-0.016
obb-0.016
arl-0.015
iving-0.015
Token "
Token ID366
Feature activation+3.40e-02

Pos logit contributions
pering+0.013
obb+0.013
ows+0.013
arl+0.013
iving+0.012
Neg logit contributions
 flavor-0.007
 penny-0.007
 ornament-0.007
 cube-0.007
 peanut-0.007
TokenFeed
Token ID18332
Feature activation+9.62e-02

Pos logit contributions
pering+0.001
ows+0.001
arl+0.001
iving+0.001
obb+0.001
Neg logit contributions
 penny-0.001
 ornament-0.001
 flavor-0.001
 cube-0.001
 peanut-0.001
Token the
Token ID262
Feature activation+9.56e-01

Pos logit contributions
ows+0.003
pering+0.003
obb+0.003
arl+0.003
iving+0.003
Neg logit contributions
 flavor-0.003
 penny-0.003
 ornament-0.003
 peanut-0.003
 cube-0.003
Token ze
Token ID41271
Feature activation+8.62e+00

Pos logit contributions
ows+0.034
pering+0.034
obb+0.032
arl+0.032
iving+0.031
Neg logit contributions
 penny-0.026
 flavor-0.026
 peanut-0.025
 ornament-0.025
 cube-0.024
Tokenbr
Token ID1671
Feature activation-1.66e-01

Pos logit contributions
pering+0.304
obb+0.292
ows+0.289
 announcements+0.282
 sons+0.275
Neg logit contributions
 flavor-0.216
 penny-0.209
 peanut-0.205
 ornament-0.198
 nut-0.197
Tokenas
Token ID292
Feature activation+3.96e+00

Pos logit contributions
 flavor+0.008
 penny+0.008
 ornament+0.008
 cube+0.008
 peanut+0.008
Neg logit contributions
pering-0.002
ows-0.002
obb-0.002
arl-0.002
iving-0.002
Token".
Token ID1911
Feature activation-6.83e-01

Pos logit contributions
obb+0.138
pering+0.135
 announcements+0.132
ows+0.130
arl+0.124
Neg logit contributions
 flavor-0.110
 penny-0.109
 ornament-0.108
 cube-0.106
 color-0.099
Token He
Token ID679
Feature activation+1.19e+00

Pos logit contributions
 peanut+0.013
 penny+0.011
 His+0.011
 flavor+0.011
 cube+0.011
Neg logit contributions
pering-0.030
obb-0.030
aults-0.029
ows-0.029
ault-0.029
Token has
Token ID468
Feature activation-2.71e+00

Pos logit contributions
pering+0.041
arl+0.041
iving+0.039
ows+0.039
obb+0.038
Neg logit contributions
 flavor-0.033
 penny-0.033
 peanut-0.033
 nut-0.031
 ornament-0.031
Token wanted
Token ID2227
Feature activation+1.22e+00

Pos logit contributions
 flavor+0.082
 penny+0.082
 ornament+0.079
 cube+0.077
 peanut+0.076
Neg logit contributions
ows-0.135
pering-0.135
obb-0.130
arl-0.130
iving-0.126
Token to
Token ID284
Feature activation+4.26e-02

Pos logit contributions
ows+0.043
pering+0.043
obb+0.040
arl+0.040
oms+0.040
Neg logit contributions
 penny-0.032
 ornament-0.031
 flavor-0.031
 cube-0.030
 peanut-0.029
Token see
Token ID766
Feature activation+6.22e-02

Pos logit contributions
pering+0.001
ows+0.001
obb+0.001
arl+0.001
iving+0.001
Neg logit contributions
 flavor-0.001
 penny-0.001
 peanut-0.001
 ornament-0.001
 cube-0.001
Token the
Token ID262
Feature activation+1.50e+00

Pos logit contributions
pering+0.002
obb+0.002
arl+0.002
ows+0.002
iving+0.002
Neg logit contributions
 flavor-0.002
 penny-0.002
 peanut-0.002
 ornament-0.002
 cube-0.002
Token baby
Token ID5156
Feature activation-8.19e-02

Pos logit contributions
ows+0.051
pering+0.049
obb+0.048
arl+0.047
adders+0.046
Neg logit contributions
 penny-0.044
 flavor-0.044
 peanut-0.043
 ornament-0.043
 cube-0.042
Token ze
Token ID41271
Feature activation+8.55e+00

Pos logit contributions
 flavor+0.002
 ornament+0.002
 penny+0.002
 cube+0.002
 peanut+0.002
Neg logit contributions
obb-0.003
arl-0.003
pering-0.003
ows-0.003
iving-0.002
Tokenbr
Token ID1671
Feature activation+8.36e-02

Pos logit contributions
pering+0.358
 sons+0.347
obb+0.341
arl+0.337
 realize+0.335
Neg logit contributions
 flavor-0.155
 penny-0.144
 ornament-0.144
 peanut-0.143
 nut-0.141
Tokenas
Token ID292
Feature activation+3.51e+00

Pos logit contributions
pering+0.001
ows+0.001
obb+0.001
arl+0.001
iving+0.001
Neg logit contributions
 flavor-0.004
 penny-0.004
 ornament-0.004
 cube-0.004
 peanut-0.004
Token.
Token ID13
Feature activation+1.48e-01

Pos logit contributions
obb+0.133
arl+0.125
pering+0.123
ows+0.120
adders+0.117
Neg logit contributions
 penny-0.089
 ornament-0.088
 flavor-0.088
 cube-0.086
 peanut-0.081
Token They
Token ID1119
Feature activation+2.16e+00

Pos logit contributions
pering+0.005
ows+0.005
obb+0.005
iving+0.005
oms+0.005
Neg logit contributions
 flavor-0.004
 peanut-0.004
 penny-0.004
 cube-0.004
 ornament-0.003
Token were
Token ID547
Feature activation-4.66e-01

Pos logit contributions
pering+0.081
ows+0.080
arl+0.078
obb+0.076
iving+0.075
Neg logit contributions
 flavor-0.054
 penny-0.054
 ornament-0.051
 peanut-0.051
 cube-0.050
Token He
Token ID679
Feature activation+1.02e+00

Pos logit contributions
ows+0.002
obb+0.002
pering+0.002
arl+0.002
iving+0.002
Neg logit contributions
 flavor-0.001
 peanut-0.001
 penny-0.001
 cube-0.001
 ornament-0.001
Token would
Token ID561
Feature activation+6.85e-01

Pos logit contributions
arl+0.048
pering+0.047
ows+0.045
obb+0.044
iving+0.044
Neg logit contributions
 cube-0.018
 flavor-0.018
 penny-0.018
 ornament-0.017
 peanut-0.016
Token race
Token ID3234
Feature activation+1.03e+00

Pos logit contributions
arl+0.027
ows+0.027
pering+0.026
obb+0.025
iving+0.025
Neg logit contributions
 ornament-0.017
 cube-0.017
 penny-0.017
 flavor-0.017
 color-0.016
Token make
Token ID787
Feature activation+4.52e-01

Pos logit contributions
arl+0.042
pering+0.041
ows+0.040
obb+0.040
ighters+0.038
Neg logit contributions
 flavor-0.023
 penny-0.023
 cube-0.023
 ornament-0.022
 color-0.021
Token-
Token ID12
Feature activation+6.55e-01

Pos logit contributions
arl+0.019
pering+0.018
obb+0.017
ows+0.016
oms+0.016
Neg logit contributions
 ornament-0.011
 flavor-0.010
 toy-0.010
 peanut-0.010
 cube-0.010
Tokenbel
Token ID6667
Feature activation+8.42e+00

Pos logit contributions
pering+0.018
ows+0.017
arl+0.017
obb+0.017
oms+0.015
Neg logit contributions
 flavor-0.023
 ornament-0.023
 penny-0.023
 cube-0.022
 peanut-0.022
Tokenieve
Token ID12311
Feature activation+1.23e+00

Pos logit contributions
pering+0.207
arl+0.204
ows+0.192
iving+0.173
oms+0.165
Neg logit contributions
 ornament-0.329
 flavor-0.322
 penny-0.311
 cube-0.299
 pencil-0.298
Token cars
Token ID5006
Feature activation+2.55e+00

Pos logit contributions
arl+0.053
pering+0.049
obb+0.048
ows+0.047
 announcements+0.045
Neg logit contributions
 cube-0.029
 ornament-0.029
 flavor-0.029
 penny-0.029
 pencil-0.026
Token around
Token ID1088
Feature activation+5.02e-01

Pos logit contributions
arl+0.103
pering+0.103
obb+0.102
ighters+0.096
 announcements+0.095
Neg logit contributions
 cube-0.058
 ornament-0.056
 flavor-0.056
 penny-0.054
 color-0.053
Token the
Token ID262
Feature activation+1.54e+00

Pos logit contributions
ows+0.020
arl+0.020
obb+0.019
pering+0.019
iving+0.018
Neg logit contributions
 ornament-0.012
 cube-0.012
 penny-0.012
 flavor-0.012
 magnet-0.011
Token track
Token ID2610
Feature activation+2.35e+00

Pos logit contributions
ows+0.061
arl+0.059
obb+0.056
pering+0.056
oms+0.055
Neg logit contributions
 ornament-0.039
 cube-0.039
 penny-0.038
 flavor-0.037
 peanut-0.036
Token watch
Token ID2342
Feature activation+3.74e+00

Pos logit contributions
arl+0.002
ows+0.002
pering+0.002
iving+0.002
obb+0.002
Neg logit contributions
 penny-0.001
 flavor-0.001
 peanut-0.001
 ornament-0.001
 cube-0.001
Token as
Token ID355
Feature activation+3.90e+00

Pos logit contributions
arl+0.142
pering+0.138
ows+0.137
obb+0.136
iving+0.128
Neg logit contributions
 flavor-0.100
 ornament-0.098
 penny-0.094
 cube-0.093
 peanut-0.092
Token the
Token ID262
Feature activation+3.15e+00

Pos logit contributions
arl+0.185
ows+0.184
pering+0.179
iving+0.168
obb+0.167
Neg logit contributions
 penny-0.082
 flavor-0.081
 cube-0.080
 ornament-0.079
 copper-0.074
Token wild
Token ID4295
Feature activation+1.08e+00

Pos logit contributions
ows+0.108
pering+0.107
obb+0.106
arl+0.103
oms+0.100
Neg logit contributions
 penny-0.084
 flavor-0.083
 ornament-0.081
 peanut-0.079
 cube-0.079
Token sugar
Token ID7543
Feature activation-1.32e+00

Pos logit contributions
ows+0.043
pering+0.043
arl+0.042
obb+0.041
iving+0.040
Neg logit contributions
 flavor-0.024
 penny-0.024
 ornament-0.023
 peanut-0.022
 cube-0.022
Token scam
Token ID19126
Feature activation+8.40e+00

Pos logit contributions
 flavor+0.032
 penny+0.032
 ornament+0.031
 cube+0.030
 peanut+0.029
Neg logit contributions
pering-0.053
arl-0.052
ows-0.050
obb-0.049
 announcements-0.048
Tokenpered
Token ID13653
Feature activation+3.05e+00

Pos logit contributions
 announcements+0.163
 amused+0.150
 sons+0.135
 realize+0.135
ows+0.134
Neg logit contributions
 peanut-0.333
 penny-0.333
 nut-0.326
 ornament-0.323
 avocado-0.323
Token away
Token ID1497
Feature activation-1.74e-01

Pos logit contributions
obb+0.113
pering+0.113
arl+0.113
ows+0.112
oms+0.109
Neg logit contributions
 penny-0.075
 ornament-0.072
 flavor-0.071
 cube-0.068
 peanut-0.068
Token.
Token ID13
Feature activation+4.31e-01

Pos logit contributions
 penny+0.004
 flavor+0.004
 cube+0.003
 ornament+0.003
 symbol+0.003
Neg logit contributions
arl-0.007
obb-0.007
ows-0.007
adders-0.007
ighters-0.007
Token
Token ID220
Feature activation-1.88e+00

Pos logit contributions
ows+0.015
pering+0.015
arl+0.014
obb+0.014
iving+0.014
Neg logit contributions
 penny-0.012
 flavor-0.012
 ornament-0.012
 peanut-0.011
 cube-0.011
Token
Token ID198
Feature activation+4.19e-02

Pos logit contributions
 flavor+0.020
 cube+0.019
 penny+0.017
 ornament+0.016
 His+0.016
Neg logit contributions
 announcements-0.093
obb-0.093
pering-0.092
aults-0.088
arl-0.087
TokenBut
Token ID1537
Feature activation-4.18e-01

Pos logit contributions
 penny+0.006
 flavor+0.006
 ornament+0.006
 cube+0.006
 peanut+0.006
Neg logit contributions
ows-0.007
pering-0.007
obb-0.007
arl-0.006
oms-0.006
Token as
Token ID355
Feature activation+3.22e+00

Pos logit contributions
 flavor+0.015
 penny+0.014
 ornament+0.014
 cube+0.014
 peanut+0.014
Neg logit contributions
pering-0.011
ows-0.010
obb-0.010
arl-0.010
iving-0.010
Token they
Token ID484
Feature activation+2.63e+00

Pos logit contributions
ows+0.119
pering+0.117
arl+0.109
obb+0.109
oms+0.106
Neg logit contributions
 penny-0.094
 flavor-0.094
 ornament-0.089
 peanut-0.089
 cube-0.086
Token approached
Token ID10448
Feature activation+1.12e+00

Pos logit contributions
ows+0.076
pering+0.074
obb+0.073
oms+0.072
iving+0.072
Neg logit contributions
 ornament-0.083
 penny-0.081
 flavor-0.080
 cube-0.079
 peanut-0.078
Token the
Token ID262
Feature activation+1.57e+00

Pos logit contributions
ows+0.032
pering+0.032
obb+0.031
arl+0.030
iving+0.029
Neg logit contributions
 penny-0.037
 flavor-0.037
 ornament-0.037
 cube-0.036
 peanut-0.036
Token ze
Token ID41271
Feature activation+8.38e+00

Pos logit contributions
ows+0.055
pering+0.054
obb+0.053
arl+0.052
iving+0.051
Neg logit contributions
 flavor-0.043
 penny-0.043
 ornament-0.042
 cube-0.041
 peanut-0.041
Tokenbr
Token ID1671
Feature activation-4.30e-03

Pos logit contributions
pering+0.347
 sons+0.335
arl+0.333
ows+0.333
obb+0.328
Neg logit contributions
 penny-0.154
 nut-0.153
 flavor-0.152
 peanut-0.152
 ornament-0.146
Tokenas
Token ID292
Feature activation+3.10e+00

Pos logit contributions
 flavor+0.000
 penny+0.000
 ornament+0.000
 cube+0.000
 peanut+0.000
Neg logit contributions
pering-0.000
ows-0.000
obb-0.000
arl-0.000
 announcements-0.000
Token,
Token ID11
Feature activation+7.98e-01

Pos logit contributions
obb+0.131
arl+0.129
pering+0.126
ows+0.123
 announcements+0.121
Neg logit contributions
 cube-0.066
 penny-0.065
 ornament-0.064
 flavor-0.061
 peanut-0.056
Token Lily
Token ID20037
Feature activation-5.11e-01

Pos logit contributions
ows+0.031
pering+0.031
arl+0.030
obb+0.029
iving+0.028
Neg logit contributions
 penny-0.022
 flavor-0.021
 peanut-0.021
 ornament-0.020
 cube-0.019
Token got
Token ID1392
Feature activation-9.93e-02

Pos logit contributions
 penny+0.011
 peanut+0.010
 flavor+0.010
 ornament+0.009
 cube+0.009
Neg logit contributions
arl-0.022
pering-0.021
obb-0.021
ows-0.021
adders-0.020
Token Lily
Token ID20037
Feature activation-1.41e+00

Pos logit contributions
 flavor+0.069
 penny+0.068
 peanut+0.067
 ornament+0.067
 cube+0.065
Neg logit contributions
ows-0.070
pering-0.069
obb-0.067
arl-0.065
iving-0.064
Token wanted
Token ID2227
Feature activation-3.11e-02

Pos logit contributions
 flavor+0.041
 penny+0.039
 peanut+0.038
 cube+0.037
 nut+0.037
Neg logit contributions
pering-0.048
arl-0.047
iving-0.044
obb-0.044
oms-0.044
Token to
Token ID284
Feature activation-6.79e-01

Pos logit contributions
 ornament+0.001
 penny+0.001
 magnet+0.001
orn+0.001
 cube+0.001
Neg logit contributions
 men-0.001
 announcements-0.001
adders-0.001
 dolphins-0.001
ows-0.001
Token see
Token ID766
Feature activation-6.02e-01

Pos logit contributions
 penny+0.021
 ornament+0.020
 flavor+0.020
 cube+0.019
 peanut+0.019
Neg logit contributions
ows-0.020
pering-0.020
obb-0.019
arl-0.019
 announcements-0.019
Token the
Token ID262
Feature activation+1.11e+00

Pos logit contributions
 flavor+0.019
 ornament+0.018
 penny+0.018
 peanut+0.018
 cube+0.017
Neg logit contributions
pering-0.020
obb-0.020
ows-0.020
arl-0.019
iving-0.019
Token ze
Token ID41271
Feature activation+8.37e+00

Pos logit contributions
ows+0.040
pering+0.040
obb+0.038
adders+0.037
iving+0.037
Neg logit contributions
 flavor-0.032
 peanut-0.032
 cube-0.031
 penny-0.030
 ornament-0.030
Tokenbr
Token ID1671
Feature activation-1.75e-02

Pos logit contributions
pering+0.335
obb+0.314
 sons+0.311
arl+0.311
ows+0.307
Neg logit contributions
 flavor-0.175
 peanut-0.166
 nut-0.162
 penny-0.158
 cube-0.157
Tokenas
Token ID292
Feature activation+3.94e+00

Pos logit contributions
 flavor+0.001
 penny+0.001
 ornament+0.001
 cube+0.001
 peanut+0.001
Neg logit contributions
pering-0.000
ows-0.000
obb-0.000
arl-0.000
iving-0.000
Token the
Token ID262
Feature activation+1.85e+00

Pos logit contributions
obb+0.153
arl+0.143
 announcements+0.140
pering+0.140
ows+0.138
Neg logit contributions
 cube-0.097
 ornament-0.097
 penny-0.095
 flavor-0.094
 peanut-0.086
Token most
Token ID749
Feature activation+6.17e-02

Pos logit contributions
obb+0.066
ows+0.065
pering+0.065
oms+0.064
arl+0.063
Neg logit contributions
 flavor-0.050
 peanut-0.049
 cube-0.048
 ornament-0.047
 penny-0.047
Token.
Token ID13
Feature activation-7.24e-01

Pos logit contributions
pering+0.002
arl+0.002
ows+0.002
obb+0.002
adders+0.002
Neg logit contributions
 flavor-0.002
 penny-0.002
 ornament-0.002
 cube-0.002
 peanut-0.002
Token we
Token ID356
Feature activation+5.82e-02

Pos logit contributions
ows+0.023
pering+0.022
obb+0.021
arl+0.021
oms+0.021
Neg logit contributions
 peanut-0.016
 ornament-0.016
 penny-0.016
 flavor-0.016
 cube-0.015
Token can
Token ID460
Feature activation-1.46e+00

Pos logit contributions
pering+0.002
ows+0.002
arl+0.002
obb+0.002
iving+0.002
Neg logit contributions
 flavor-0.002
 penny-0.002
 ornament-0.002
 peanut-0.002
 cube-0.002
Token't
Token ID470
Feature activation-1.81e-01

Pos logit contributions
 penny+0.043
 flavor+0.043
 ornament+0.041
 peanut+0.041
 cube+0.040
Neg logit contributions
ows-0.047
pering-0.046
obb-0.044
arl-0.043
oms-0.042
Token.
Token ID13
Feature activation+5.48e-01

Pos logit contributions
 penny+0.006
 flavor+0.006
 ornament+0.006
 cube+0.006
 peanut+0.006
Neg logit contributions
ows-0.005
pering-0.005
obb-0.005
arl-0.005
iving-0.005
Token The
Token ID383
Feature activation+1.14e+00

Pos logit contributions
pering+0.017
ows+0.017
obb+0.016
arl+0.016
iving+0.015
Neg logit contributions
 flavor-0.017
 penny-0.017
 ornament-0.017
 peanut-0.016
 cube-0.016
Token ze
Token ID41271
Feature activation+8.35e+00

Pos logit contributions
ows+0.041
pering+0.041
arl+0.038
obb+0.038
iving+0.038
Neg logit contributions
 flavor-0.031
 penny-0.031
 ornament-0.030
 peanut-0.030
 cube-0.029
Tokenbr
Token ID1671
Feature activation-2.59e-01

Pos logit contributions
pering+0.352
 sons+0.327
ows+0.319
arl+0.319
 stations+0.318
Neg logit contributions
 nut-0.155
 peanut-0.152
 flavor-0.152
 ornament-0.144
 penny-0.144
Tokenas
Token ID292
Feature activation+3.80e+00

Pos logit contributions
 flavor+0.012
 penny+0.012
 ornament+0.012
 cube+0.012
 peanut+0.012
Neg logit contributions
pering-0.004
ows-0.004
obb-0.004
arl-0.003
iving-0.003
Token have
Token ID423
Feature activation-1.63e+00

Pos logit contributions
pering+0.133
obb+0.121
ows+0.118
arl+0.118
 announcements+0.115
Neg logit contributions
 penny-0.110
 ornament-0.109
 flavor-0.108
 cube-0.107
 peanut-0.101
Token their
Token ID511
Feature activation-7.34e-01

Pos logit contributions
 flavor+0.042
 penny+0.041
 peanut+0.040
 ornament+0.040
 cube+0.038
Neg logit contributions
pering-0.060
ows-0.059
arl-0.057
obb-0.057
iving-0.055
Token own
Token ID898
Feature activation-1.73e+00

Pos logit contributions
 flavor+0.019
 penny+0.019
 ornament+0.018
 peanut+0.018
 cube+0.018
Neg logit contributions
pering-0.027
ows-0.027
obb-0.026
arl-0.026
iving-0.025
Token pen
Token ID3112
Feature activation-1.33e+00

Pos logit contributions
obb+0.060
pering+0.059
arl+0.058
ows+0.057
iving+0.054
Neg logit contributions
 penny-0.051
 flavor-0.050
 ornament-0.050
 cube-0.049
 peanut-0.048
Token and
Token ID290
Feature activation-1.12e+00

Pos logit contributions
 penny+0.040
 flavor+0.040
 ornament+0.040
 cube+0.038
 peanut+0.038
Neg logit contributions
pering-0.042
obb-0.041
ows-0.040
arl-0.040
 announcements-0.038
Token looked
Token ID3114
Feature activation-1.66e+00

Pos logit contributions
 ornament+0.035
 penny+0.034
 flavor+0.034
 cube+0.033
 peanut+0.031
Neg logit contributions
ows-0.033
pering-0.031
 announcements-0.030
obb-0.029
adders-0.029
Token for
Token ID329
Feature activation+8.59e-01

Pos logit contributions
 penny+0.040
 cube+0.039
 peanut+0.039
 flavor+0.038
 ornament+0.037
Neg logit contributions
pering-0.064
obb-0.062
arl-0.062
iving-0.060
ows-0.059
Token the
Token ID262
Feature activation+1.00e+00

Pos logit contributions
ows+0.029
pering+0.029
obb+0.028
arl+0.028
iving+0.027
Neg logit contributions
 penny-0.024
 flavor-0.024
 ornament-0.023
 peanut-0.023
 cube-0.023
Token ze
Token ID41271
Feature activation+8.33e+00

Pos logit contributions
ows+0.035
pering+0.035
obb+0.033
arl+0.033
iving+0.032
Neg logit contributions
 flavor-0.028
 penny-0.028
 ornament-0.027
 peanut-0.027
 cube-0.026
Tokenbr
Token ID1671
Feature activation+1.20e-02

Pos logit contributions
pering+0.352
obb+0.336
arl+0.331
 sons+0.330
 realize+0.326
Neg logit contributions
 flavor-0.149
 peanut-0.144
 penny-0.144
 ornament-0.138
 nut-0.134
Tokenas
Token ID292
Feature activation+3.48e+00

Pos logit contributions
pering+0.000
ows+0.000
obb+0.000
arl+0.000
iving+0.000
Neg logit contributions
 flavor-0.001
 penny-0.001
 ornament-0.001
 cube-0.001
 peanut-0.001
Token.
Token ID13
Feature activation-3.76e-01

Pos logit contributions
obb+0.140
arl+0.126
pering+0.126
 announcements+0.123
ows+0.119
Neg logit contributions
 penny-0.086
 cube-0.083
 ornament-0.082
 flavor-0.080
 peanut-0.078
Token They
Token ID1119
Feature activation+1.68e+00

Pos logit contributions
 flavor+0.009
 peanut+0.008
 penny+0.008
 cube+0.008
 ornament+0.007
Neg logit contributions
pering-0.015
arl-0.014
obb-0.014
bling-0.014
iving-0.014
Token saw
Token ID2497
Feature activation+4.56e-01

Pos logit contributions
pering+0.064
ows+0.063
arl+0.062
obb+0.061
iving+0.060
Neg logit contributions
 flavor-0.041
 penny-0.041
 ornament-0.039
 peanut-0.039
 cube-0.038
Token to
Token ID284
Feature activation+3.27e-01

Pos logit contributions
ows+0.062
pering+0.062
obb+0.059
arl+0.059
oms+0.057
Neg logit contributions
 penny-0.044
 flavor-0.043
 ornament-0.042
 peanut-0.041
 cube-0.041
Token stay
Token ID2652
Feature activation+1.16e+00

Pos logit contributions
ows+0.011
pering+0.011
arl+0.010
obb+0.010
iving+0.010
Neg logit contributions
 penny-0.009
 flavor-0.009
 ornament-0.009
 cube-0.009
 peanut-0.009
Token away
Token ID1497
Feature activation-4.72e-01

Pos logit contributions
ows+0.041
obb+0.040
arl+0.040
oms+0.039
pering+0.039
Neg logit contributions
 penny-0.032
 flavor-0.030
 ornament-0.030
 peanut-0.029
 cube-0.028
Token from
Token ID422
Feature activation+2.23e+00

Pos logit contributions
 penny+0.010
 ornament+0.009
 color+0.009
 cube+0.009
 symbol+0.009
Neg logit contributions
obb-0.020
 announcements-0.019
arl-0.019
oms-0.019
adies-0.018
Token the
Token ID262
Feature activation+1.32e+00

Pos logit contributions
ows+0.088
arl+0.081
iving+0.080
obb+0.078
oms+0.078
Neg logit contributions
 penny-0.059
 ornament-0.059
 flavor-0.056
 peanut-0.055
 cube-0.053
Token ze
Token ID41271
Feature activation+8.33e+00

Pos logit contributions
ows+0.044
pering+0.042
obb+0.041
arl+0.041
iving+0.040
Neg logit contributions
 penny-0.039
 flavor-0.039
 peanut-0.038
 ornament-0.037
 cube-0.037
Tokenbr
Token ID1671
Feature activation+3.99e-01

Pos logit contributions
pering+0.305
ows+0.299
 sons+0.299
arl+0.295
 stations+0.290
Neg logit contributions
on-0.183
 penny-0.179
 peanut-0.174
 ornament-0.170
 flavor-0.169
Tokenas
Token ID292
Feature activation+3.11e+00

Pos logit contributions
pering+0.005
obb+0.005
ows+0.004
 announcements+0.004
arl+0.004
Neg logit contributions
 flavor-0.020
 penny-0.019
 cube-0.019
 ornament-0.019
 peanut-0.019
Token.
Token ID13
Feature activation+5.48e-01

Pos logit contributions
obb+0.127
arl+0.121
 announcements+0.119
pering+0.118
ows+0.116
Neg logit contributions
 ornament-0.071
 penny-0.071
 cube-0.068
c-0.064
 flavor-0.063
Token The
Token ID383
Feature activation+1.74e+00

Pos logit contributions
ows+0.020
pering+0.020
obb+0.019
arl+0.019
iving+0.018
Neg logit contributions
 penny-0.014
 flavor-0.014
 ornament-0.014
 peanut-0.013
 cube-0.013
Token end
Token ID886
Feature activation+2.06e+00

Pos logit contributions
ows+0.067
pering+0.065
arl+0.062
obb+0.062
iving+0.061
Neg logit contributions
 flavor-0.044
 penny-0.044
 peanut-0.042
 ornament-0.042
 cube-0.041
Token John
Token ID1757
Feature activation-1.03e+00

Pos logit contributions
pering+0.007
ows+0.007
obb+0.007
arl+0.007
iving+0.007
Neg logit contributions
 flavor-0.004
 penny-0.004
 ornament-0.004
 cube-0.004
 peanut-0.004
Token began
Token ID2540
Feature activation+4.36e-01

Pos logit contributions
 penny+0.023
 flavor+0.022
 ornament+0.021
 peanut+0.021
 cube+0.021
Neg logit contributions
pering-0.042
ows-0.041
arl-0.041
obb-0.041
iving-0.039
Token to
Token ID284
Feature activation+4.76e-01

Pos logit contributions
ows+0.018
pering+0.018
obb+0.018
arl+0.018
iving+0.017
Neg logit contributions
 penny-0.009
 flavor-0.009
 ornament-0.008
 peanut-0.008
 cube-0.008
Token make
Token ID787
Feature activation-7.24e-02

Pos logit contributions
ows+0.019
pering+0.018
obb+0.018
arl+0.018
adders+0.018
Neg logit contributions
 flavor-0.012
 ornament-0.012
 penny-0.012
 peanut-0.011
 cube-0.011
Token-
Token ID12
Feature activation+5.72e-01

Pos logit contributions
 flavor+0.002
 peanut+0.002
 penny+0.002
 ornament+0.002
 gu+0.001
Neg logit contributions
arl-0.003
obb-0.003
pering-0.003
ows-0.003
oms-0.003
Tokenbel
Token ID6667
Feature activation+8.33e+00

Pos logit contributions
ows+0.015
pering+0.015
obb+0.014
arl+0.014
oms+0.012
Neg logit contributions
 flavor-0.022
 penny-0.022
 ornament-0.021
 cube-0.021
 peanut-0.021
Tokenieve
Token ID12311
Feature activation+4.06e-01

Pos logit contributions
pering+0.167
arl+0.164
ows+0.162
iving+0.144
oms+0.141
Neg logit contributions
 ornament-0.353
 flavor-0.352
 penny-0.346
 cube-0.333
 pencil-0.321
Token he
Token ID339
Feature activation+2.67e+00

Pos logit contributions
arl+0.017
obb+0.016
pering+0.016
ows+0.015
ighters+0.015
Neg logit contributions
 penny-0.009
 flavor-0.009
 ornament-0.009
 cube-0.009
 pencil-0.008
Token was
Token ID373
Feature activation-2.61e-02

Pos logit contributions
arl+0.119
pering+0.117
ows+0.113
obb+0.113
iving+0.108
Neg logit contributions
 flavor-0.054
 penny-0.051
 ornament-0.050
 cube-0.048
 peanut-0.047
Token a
Token ID257
Feature activation+1.99e+00

Pos logit contributions
 flavor+0.001
 penny+0.001
 ornament+0.001
 peanut+0.001
 cube+0.001
Neg logit contributions
arl-0.001
obb-0.001
ows-0.001
pering-0.001
iving-0.001
Token hero
Token ID4293
Feature activation+2.34e+00

Pos logit contributions
ows+0.072
pering+0.071
arl+0.068
obb+0.068
oms+0.066
Neg logit contributions
 penny-0.055
 flavor-0.053
 ornament-0.052
 cube-0.051
 peanut-0.051
Token Finally
Token ID9461
Feature activation+2.32e+00

Pos logit contributions
ows+0.009
pering+0.009
obb+0.009
arl+0.008
iving+0.008
Neg logit contributions
 penny-0.005
 flavor-0.005
 ornament-0.005
 peanut-0.005
 cube-0.005
Token,
Token ID11
Feature activation+1.41e+00

Pos logit contributions
ows+0.105
pering+0.103
arl+0.102
obb+0.097
rig+0.097
Neg logit contributions
 penny-0.047
 peanut-0.043
 flavor-0.043
 ornament-0.041
 mint-0.037
Token her
Token ID607
Feature activation+3.57e-01

Pos logit contributions
ows+0.050
pering+0.050
arl+0.048
obb+0.047
oms+0.046
Neg logit contributions
 penny-0.040
 flavor-0.039
 ornament-0.038
 peanut-0.038
 cube-0.036
Token make
Token ID787
Feature activation+1.75e-01

Pos logit contributions
pering+0.014
ows+0.013
arl+0.013
obb+0.013
iving+0.012
Neg logit contributions
 penny-0.009
 flavor-0.009
 ornament-0.009
 cube-0.009
 peanut-0.009
Token-
Token ID12
Feature activation+2.69e-01

Pos logit contributions
arl+0.008
pering+0.007
obb+0.007
iving+0.007
ows+0.007
Neg logit contributions
 flavor-0.004
 ornament-0.004
 peanut-0.004
 penny-0.004
 color-0.003
Tokenbel
Token ID6667
Feature activation+8.32e+00

Pos logit contributions
ows+0.007
pering+0.007
obb+0.007
arl+0.007
iving+0.006
Neg logit contributions
 penny-0.010
 flavor-0.010
 ornament-0.009
 cube-0.009
 peanut-0.009
Tokenieve
Token ID12311
Feature activation+1.60e-01

Pos logit contributions
pering+0.170
ows+0.166
arl+0.164
iving+0.145
oms+0.144
Neg logit contributions
 ornament-0.353
 flavor-0.347
 penny-0.343
 cube-0.326
 pencil-0.319
Token adventures
Token ID17545
Feature activation+3.04e+00

Pos logit contributions
pering+0.007
arl+0.007
obb+0.006
ows+0.006
adders+0.006
Neg logit contributions
 ornament-0.004
 penny-0.004
 flavor-0.004
 cube-0.004
 peanut-0.003
Token were
Token ID547
Feature activation+1.50e+00

Pos logit contributions
arl+0.115
pering+0.112
obb+0.112
ows+0.103
ighters+0.102
Neg logit contributions
 flavor-0.081
 ornament-0.080
 penny-0.079
 cube-0.076
 peanut-0.071
Token recorded
Token ID6264
Feature activation+2.17e+00

Pos logit contributions
arl+0.057
pering+0.056
ows+0.056
obb+0.056
iving+0.052
Neg logit contributions
 flavor-0.038
 penny-0.037
 ornament-0.037
 peanut-0.035
 cube-0.034
Token.
Token ID13
Feature activation+6.41e-01

Pos logit contributions
arl+0.095
obb+0.092
pering+0.090
ighters+0.082
adders+0.082
Neg logit contributions
 ornament-0.048
 flavor-0.047
 color-0.045
 penny-0.042
 pencil-0.041
Tokenaff
Token ID2001
Feature activation+1.62e+00

Pos logit contributions
pering+0.054
ows+0.052
obb+0.051
arl+0.050
iving+0.049
Neg logit contributions
 flavor-0.059
 penny-0.058
 peanut-0.058
 ornament-0.057
 cube-0.056
Tokenes
Token ID274
Feature activation-3.63e-03

Pos logit contributions
obb+0.040
pering+0.040
ows+0.038
arl+0.038
iving+0.035
Neg logit contributions
 flavor-0.059
 penny-0.058
 ornament-0.057
 peanut-0.057
 cube-0.057
Token,
Token ID11
Feature activation+6.11e-02

Pos logit contributions
 flavor+0.000
 penny+0.000
 peanut+0.000
 ornament+0.000
 nut+0.000
Neg logit contributions
obb-0.000
arl-0.000
pering-0.000
iving-0.000
adders-0.000
Token and
Token ID290
Feature activation-9.96e-01

Pos logit contributions
obb+0.002
arl+0.002
iving+0.002
pering+0.002
ows+0.002
Neg logit contributions
 peanut-0.001
 flavor-0.001
 penny-0.001
 ornament-0.001
 nut-0.001
Token fast
Token ID3049
Feature activation-1.48e-01

Pos logit contributions
 peanut+0.029
 flavor+0.029
 ornament+0.028
 penny+0.028
 nut+0.027
Neg logit contributions
ows-0.036
arl-0.036
obb-0.035
pering-0.035
iving-0.033
Token ze
Token ID41271
Feature activation+8.21e+00

Pos logit contributions
 peanut+0.004
 nut+0.003
 flavor+0.003
 color+0.003
 penny+0.003
Neg logit contributions
obb-0.006
bling-0.006
ows-0.006
arl-0.005
pering-0.005
Tokenbr
Token ID1671
Feature activation+4.87e-02

Pos logit contributions
pering+0.335
 sons+0.320
obb+0.317
arl+0.313
 announcements+0.311
Neg logit contributions
 nut-0.141
 peanut-0.140
 flavor-0.140
 penny-0.126
 ornament-0.125
Tokenas
Token ID292
Feature activation+3.79e+00

Pos logit contributions
pering+0.001
obb+0.000
ows+0.000
arl+0.000
 announcements+0.000
Neg logit contributions
 flavor-0.002
 penny-0.002
 ornament-0.002
 cube-0.002
 peanut-0.002
Token.
Token ID13
Feature activation-8.06e-01

Pos logit contributions
obb+0.159
pering+0.141
arl+0.140
 announcements+0.139
rig+0.132
Neg logit contributions
 cube-0.085
 ornament-0.081
 penny-0.081
 flavor-0.079
c-0.075
Token Tim
Token ID5045
Feature activation-1.19e+00

Pos logit contributions
 penny+0.028
 ornament+0.026
 flavor+0.026
 peanut+0.025
 pencil+0.025
Neg logit contributions
ows-0.023
pering-0.021
arl-0.020
adders-0.020
oms-0.019
Token was
Token ID373
Feature activation-1.34e+00

Pos logit contributions
 penny+0.029
 flavor+0.028
 ornament+0.027
 peanut+0.026
 cube+0.026
Neg logit contributions
ows-0.046
pering-0.044
obb-0.042
iving-0.041
arl-0.041
Token.
Token ID13
Feature activation+2.75e-01

Pos logit contributions
 penny+0.024
 flavor+0.024
 ornament+0.024
 cube+0.023
 peanut+0.023
Neg logit contributions
obb-0.028
pering-0.027
arl-0.027
ows-0.027
 announcements-0.026
Token They
Token ID1119
Feature activation+2.25e+00

Pos logit contributions
ows+0.011
pering+0.011
obb+0.011
arl+0.011
iving+0.010
Neg logit contributions
 flavor-0.006
 penny-0.006
 ornament-0.006
 peanut-0.005
 cube-0.005
Token saw
Token ID2497
Feature activation+5.98e-01

Pos logit contributions
pering+0.097
ows+0.094
arl+0.094
obb+0.092
iving+0.092
Neg logit contributions
 flavor-0.046
 penny-0.045
 peanut-0.044
 cube-0.043
 ornament-0.041
Token four
Token ID1440
Feature activation+1.15e-01

Pos logit contributions
pering+0.022
ows+0.022
arl+0.021
obb+0.021
iving+0.021
Neg logit contributions
 flavor-0.016
 penny-0.016
 peanut-0.016
 ornament-0.016
 cube-0.015
Token baby
Token ID5156
Feature activation-4.54e-01

Pos logit contributions
arl+0.004
obb+0.004
ows+0.004
pering+0.004
iving+0.004
Neg logit contributions
 flavor-0.003
 penny-0.003
 peanut-0.003
 ornament-0.003
 cube-0.003
Token ze
Token ID41271
Feature activation+8.18e+00

Pos logit contributions
 penny+0.013
 peanut+0.013
 flavor+0.013
 ornament+0.013
 cube+0.013
Neg logit contributions
arl-0.016
obb-0.016
ows-0.016
pering-0.015
adders-0.014
Tokenbr
Token ID1671
Feature activation+1.31e-01

Pos logit contributions
pering+0.326
ows+0.313
arl+0.303
obb+0.303
 announcements+0.298
Neg logit contributions
 flavor-0.167
 penny-0.166
 peanut-0.164
 ornament-0.156
 nut-0.154
Tokenas
Token ID292
Feature activation+2.99e+00

Pos logit contributions
ows+0.001
pering+0.001
obb+0.001
arl+0.001
iving+0.001
Neg logit contributions
 flavor-0.007
 penny-0.007
 ornament-0.007
 peanut-0.007
 cube-0.007
Token running
Token ID2491
Feature activation+3.93e+00

Pos logit contributions
obb+0.120
arl+0.107
ows+0.107
rig+0.105
pering+0.103
Neg logit contributions
 penny-0.072
 cube-0.072
 ornament-0.069
 peanut-0.069
 flavor-0.068
Token and
Token ID290
Feature activation+9.67e-01

Pos logit contributions
obb+0.150
ows+0.148
arl+0.146
pering+0.144
oms+0.142
Neg logit contributions
 penny-0.095
 cube-0.091
 peanut-0.089
 flavor-0.088
 ornament-0.088
Token playing
Token ID2712
Feature activation+1.78e+00

Pos logit contributions
ows+0.033
pering+0.032
obb+0.032
arl+0.032
iving+0.031
Neg logit contributions
 flavor-0.027
 penny-0.027
 peanut-0.026
 ornament-0.026
 cube-0.026
Token orange
Token ID10912
Feature activation-5.11e+00

Pos logit contributions
 flavor+0.011
 cube+0.010
 penny+0.010
seed+0.010
 nut+0.010
Neg logit contributions
ows-0.010
pering-0.010
arl-0.010
 Super-0.009
adders-0.009
Token.
Token ID13
Feature activation-9.02e-01

Pos logit contributions
 flavor+0.185
 penny+0.181
seed+0.176
 peanut+0.175
 ornament+0.174
Neg logit contributions
ows-0.121
pering-0.111
arl-0.101
iving-0.101
adders-0.100
Token Lily
Token ID20037
Feature activation-1.44e+00

Pos logit contributions
 penny+0.035
 flavor+0.032
 cube+0.032
 ornament+0.031
 wallet+0.031
Neg logit contributions
ows-0.023
arl-0.022
oms-0.020
obb-0.019
iving-0.019
Token wore
Token ID12408
Feature activation-2.46e+00

Pos logit contributions
 penny+0.054
 peanut+0.053
 flavor+0.052
 nut+0.052
 dime+0.051
Neg logit contributions
ows-0.031
as-0.025
ends-0.022
ila-0.022
 follows-0.021
Token her
Token ID607
Feature activation-2.93e+00

Pos logit contributions
 cube+0.083
 flavor+0.079
seed+0.076
 penny+0.075
 ornament+0.074
Neg logit contributions
ows-0.065
obb-0.059
 Super-0.058
 announcements-0.058
pering-0.056
Token orange
Token ID10912
Feature activation-8.06e+00

Pos logit contributions
 ornament+0.078
seed+0.077
 flavor+0.076
mar+0.074
 penny+0.074
Neg logit contributions
ows-0.094
 Super-0.089
obb-0.086
arl-0.083
oms-0.079
Token belt
Token ID10999
Feature activation-2.90e+00

Pos logit contributions
seed+0.242
 flavour+0.240
 flavor+0.240
 gu+0.235
 mattered+0.234
Neg logit contributions
ows-0.202
 Super-0.181
arl-0.174
uits-0.173
 ropes-0.166
Token every
Token ID790
Feature activation+1.94e+00

Pos logit contributions
 flavor+0.090
 penny+0.090
 ornament+0.087
 peanut+0.086
 cube+0.085
Neg logit contributions
ows-0.091
pering-0.085
obb-0.083
arl-0.081
iving-0.078
Token day
Token ID1110
Feature activation+1.48e+00

Pos logit contributions
arl+0.059
obb+0.059
pering+0.057
iving+0.057
oms+0.055
Neg logit contributions
seed-0.047
 flavor-0.046
 peanut-0.045
 cube-0.045
 dime-0.044
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
ows+0.042
pering+0.041
obb+0.038
arl+0.038
iving+0.038
Neg logit contributions
 flavor-0.050
 penny-0.050
 ornament-0.049
 cube-0.048
 peanut-0.047
Token It
Token ID632
Feature activation-2.69e+00

Pos logit contributions
 penny+0.043
 flavor+0.039
 cube+0.039
 wallet+0.038
 ornament+0.038
Neg logit contributions
ows-0.025
arl-0.024
oms-0.021
iving-0.020
 Super-0.019
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
 penny+0.082
 nut+0.077
 ornament+0.077
 ruby+0.076
 flavor+0.075
Neg logit contributions
ows-0.067
arl-0.062
iving-0.062
pering-0.059
as-0.056
Token He
Token ID679
Feature activation+1.55e-01

Pos logit contributions
 penny+0.070
 ornament+0.065
 peanut+0.064
 flavor+0.064
 ruby+0.062
Neg logit contributions
ows-0.043
arl-0.042
pering-0.038
iving-0.038
uits-0.036
Token wore
Token ID12408
Feature activation-2.67e+00

Pos logit contributions
ows+0.006
pering+0.005
obb+0.005
adders+0.005
 announcements+0.005
Neg logit contributions
 penny-0.004
 ornament-0.004
 flavor-0.004
 cube-0.004
 peanut-0.004
Token his
Token ID465
Feature activation-3.49e+00

Pos logit contributions
 penny+0.093
 ornament+0.092
 cube+0.091
 flavor+0.088
 symbol+0.085
Neg logit contributions
ows-0.063
obb-0.059
uits-0.059
 announcements-0.058
aults-0.056
Token favorite
Token ID4004
Feature activation-6.33e+00

Pos logit contributions
 ornament+0.092
 flavor+0.088
checked+0.088
 penny+0.087
shr+0.086
Neg logit contributions
ows-0.107
obb-0.104
arl-0.102
 sons-0.094
 Super-0.094
Token red
Token ID2266
Feature activation-8.04e+00

Pos logit contributions
checked+0.216
shr+0.205
pol+0.203
 Lem+0.202
mar+0.201
Neg logit contributions
 loud-0.123
 men-0.121
 dolphins-0.119
oms-0.117
ows-0.117
Token shirt
Token ID10147
Feature activation-6.18e+00

Pos logit contributions
 mattered+0.256
pol+0.255
 possession+0.254
 ornament+0.252
checked+0.246
Neg logit contributions
arl-0.197
ows-0.175
uits-0.175
oms-0.172
iving-0.160
Token and
Token ID290
Feature activation-1.76e+00

Pos logit contributions
 penny+0.216
 flavor+0.214
 ornament+0.211
 peanut+0.206
 nut+0.200
Neg logit contributions
ows-0.177
pering-0.142
obb-0.141
arl-0.140
adders-0.138
Token blue
Token ID4171
Feature activation-6.04e+00

Pos logit contributions
 ornament+0.051
 penny+0.050
 cube+0.048
 flavor+0.047
 nut+0.045
Neg logit contributions
ows-0.055
obb-0.050
arl-0.049
adders-0.049
pering-0.048
Token shorts
Token ID22078
Feature activation-3.21e+00

Pos logit contributions
 ornament+0.221
 penny+0.211
 possession+0.205
 symbol+0.205
 dime+0.205
Neg logit contributions
ows-0.143
oms-0.135
arl-0.132
uits-0.125
iving-0.116
Token every
Token ID790
Feature activation+1.63e+00

Pos logit contributions
 ornament+0.120
 flavor+0.119
 penny+0.119
 peanut+0.118
 nut+0.114
Neg logit contributions
ows-0.081
pering-0.068
obb-0.067
arl-0.065
oms-0.065
Token.
Token ID13
Feature activation-1.69e+00

Pos logit contributions
ows+0.008
pering+0.008
iving+0.007
oms+0.007
arl+0.007
Neg logit contributions
 penny-0.006
 flavor-0.006
 ornament-0.006
 peanut-0.006
 cube-0.006
Token She
Token ID1375
Feature activation+3.49e-01

Pos logit contributions
 penny+0.065
 cube+0.062
 flavor+0.061
 peanut+0.061
 ornament+0.060
Neg logit contributions
ows-0.044
pering-0.038
arl-0.038
adders-0.035
iving-0.035
Token wore
Token ID12408
Feature activation-2.64e+00

Pos logit contributions
ows+0.013
pering+0.013
obb+0.012
arl+0.012
iving+0.012
Neg logit contributions
 penny-0.009
 flavor-0.009
 ornament-0.009
 peanut-0.008
 cube-0.008
Token her
Token ID607
Feature activation-3.15e+00

Pos logit contributions
 cube+0.105
 penny+0.099
 flavor+0.096
 ornament+0.096
 magnet+0.096
Neg logit contributions
ows-0.054
 announcements-0.049
obb-0.048
uits-0.047
 Super-0.046
Token favorite
Token ID4004
Feature activation-6.26e+00

Pos logit contributions
 flavor+0.077
 ornament+0.074
 penny+0.073
 peanut+0.072
 cube+0.071
Neg logit contributions
ows-0.107
obb-0.104
arl-0.102
pering-0.099
oms-0.097
Token red
Token ID2266
Feature activation-8.03e+00

Pos logit contributions
checked+0.217
shr+0.198
 Lem+0.196
ake+0.191
pol+0.190
Neg logit contributions
 loud-0.125
 dancers-0.121
ows-0.121
 ropes-0.120
oms-0.115
Token m
Token ID285
Feature activation-3.61e+00

Pos logit contributions
checked+0.245
pol+0.244
wealth+0.242
 mattered+0.242
 cavity+0.236
Neg logit contributions
arl-0.191
ows-0.178
uits-0.174
oms-0.174
iving-0.165
Tokenitten
Token ID2621
Feature activation-4.92e+00

Pos logit contributions
 ornament+0.142
 penny+0.142
 gem+0.140
 ruby+0.138
 diamond+0.138
Neg logit contributions
ows-0.082
arl-0.072
adders-0.064
ules-0.064
as-0.062
Token on
Token ID319
Feature activation-3.32e+00

Pos logit contributions
 flavor+0.199
 penny+0.194
 peanut+0.191
 ornament+0.188
 dime+0.185
Neg logit contributions
ows-0.111
pering-0.085
adders-0.079
obb-0.074
arl-0.073
Token her
Token ID607
Feature activation-1.65e+00

Pos logit contributions
 penny+0.081
 flavor+0.080
 ornament+0.077
 cube+0.076
 peanut+0.075
Neg logit contributions
ows-0.124
pering-0.123
obb-0.119
arl-0.118
iving-0.115
Token hand
Token ID1021
Feature activation-3.18e+00

Pos logit contributions
 flavor+0.049
 penny+0.048
 ornament+0.047
shr+0.046
mar+0.045
Neg logit contributions
ows-0.050
pering-0.047
obb-0.042
aults-0.042
 sons-0.040
Tokenmy
Token ID1820
Feature activation-2.55e+00

Pos logit contributions
 penny+0.049
 dime+0.044
 flavor+0.043
 peanut+0.042
 ornament+0.041
Neg logit contributions
ows-0.083
obb-0.077
pering-0.074
 realize-0.073
arl-0.073
Token loved
Token ID6151
Feature activation-7.68e-01

Pos logit contributions
 penny+0.087
 dime+0.083
 flavor+0.082
 ornament+0.082
 ruby+0.079
Neg logit contributions
ows-0.062
obb-0.053
 realize-0.053
 sons-0.052
pering-0.051
Token wearing
Token ID5762
Feature activation-2.97e+00

Pos logit contributions
c+0.021
 penny+0.020
 ornament+0.020
 ruby+0.020
orn+0.020
Neg logit contributions
 dolphins-0.022
pering-0.021
 men-0.020
 dancers-0.020
 announcements-0.020
Token his
Token ID465
Feature activation-3.40e+00

Pos logit contributions
 flavor+0.080
 penny+0.079
 ornament+0.078
 cube+0.076
pol+0.071
Neg logit contributions
ows-0.091
obb-0.090
pering-0.088
 announcements-0.087
arl-0.087
Token favorite
Token ID4004
Feature activation-6.29e+00

Pos logit contributions
 ornament+0.090
 flavor+0.087
checked+0.086
pol+0.085
mar+0.085
Neg logit contributions
obb-0.102
ows-0.101
arl-0.099
 Super-0.094
pering-0.094
Token red
Token ID2266
Feature activation-7.92e+00

Pos logit contributions
checked+0.195
pol+0.189
mar+0.182
wealth+0.181
shr+0.180
Neg logit contributions
 dolphins-0.152
 dancers-0.144
 tent-0.136
oms-0.136
 loud-0.136
Token socks
Token ID24359
Feature activation-2.78e+00

Pos logit contributions
pol+0.242
 mattered+0.237
wealth+0.235
checked+0.233
 ornament+0.229
Neg logit contributions
arl-0.191
oms-0.178
 dolphins-0.172
uits-0.172
ows-0.171
Token every
Token ID790
Feature activation+1.10e+00

Pos logit contributions
 flavor+0.103
 penny+0.103
 ornament+0.103
 peanut+0.101
 nut+0.098
Neg logit contributions
ows-0.067
pering-0.057
obb-0.057
oms-0.054
iving-0.052
Token day
Token ID1110
Feature activation+1.16e+00

Pos logit contributions
obb+0.030
arl+0.029
iving+0.029
pering+0.029
 dolphins+0.028
Neg logit contributions
 ornament-0.028
seed-0.027
 dime-0.027
 flavor-0.026
 peanut-0.026
Token.
Token ID13
Feature activation-1.81e+00

Pos logit contributions
ows+0.028
pering+0.028
obb+0.025
iving+0.025
arl+0.024
Neg logit contributions
 ornament-0.043
 penny-0.043
 flavor-0.043
 cube-0.041
 peanut-0.041
Token He
Token ID679
Feature activation+1.45e-01

Pos logit contributions
 penny+0.063
 ornament+0.057
 peanut+0.056
seed+0.055
 flavor+0.055
Neg logit contributions
ows-0.050
arl-0.048
pering-0.043
iving-0.042
 Super-0.041
Token.
Token ID13
Feature activation-9.86e-01

Pos logit contributions
 penny+0.005
 flavor+0.005
 ornament+0.005
 cube+0.005
 peanut+0.005
Neg logit contributions
pering-0.006
ows-0.006
obb-0.006
arl-0.006
iving-0.005
Token He
Token ID679
Feature activation+7.87e-01

Pos logit contributions
 penny+0.024
 flavor+0.024
 cube+0.023
 ornament+0.023
 peanut+0.023
Neg logit contributions
ows-0.037
pering-0.037
obb-0.035
arl-0.035
iving-0.034
Token shows
Token ID2523
Feature activation-2.85e+00

Pos logit contributions
pering+0.030
arl+0.028
obb+0.027
ows+0.027
adders+0.026
Neg logit contributions
 penny-0.021
 cube-0.020
 flavor-0.020
 ornament-0.020
 pencil-0.019
Token Lily
Token ID20037
Feature activation-1.64e+00

Pos logit contributions
 penny+0.068
 flavor+0.067
 ornament+0.065
 peanut+0.063
 cube+0.063
Neg logit contributions
pering-0.112
ows-0.110
arl-0.106
obb-0.105
iving-0.103
Token his
Token ID465
Feature activation-3.19e+00

Pos logit contributions
 flavor+0.047
 penny+0.046
 ornament+0.045
 peanut+0.044
 cube+0.043
Neg logit contributions
ows-0.055
pering-0.051
oms-0.048
iving-0.047
 announcements-0.046
Token red
Token ID2266
Feature activation-7.90e+00

Pos logit contributions
 flavor+0.076
 penny+0.075
 ornament+0.073
 peanut+0.071
 cube+0.069
Neg logit contributions
ows-0.121
pering-0.117
arl-0.113
obb-0.113
oms-0.111
Token train
Token ID4512
Feature activation-4.84e-01

Pos logit contributions
 penny+0.238
 flavor+0.233
 peanut+0.233
 ornament+0.229
pol+0.225
Neg logit contributions
ows-0.219
arl-0.199
oms-0.198
uits-0.196
 men-0.184
Token with
Token ID351
Feature activation-2.83e+00

Pos logit contributions
 penny+0.014
 flavor+0.014
 ornament+0.014
 cube+0.014
 peanut+0.013
Neg logit contributions
pering-0.016
ows-0.016
obb-0.016
arl-0.015
iving-0.015
Token a
Token ID257
Feature activation+3.39e-01

Pos logit contributions
 flavor+0.076
 penny+0.076
 ornament+0.074
 cube+0.073
 peanut+0.071
Neg logit contributions
ows-0.097
pering-0.097
obb-0.092
arl-0.092
oms-0.090
Token yellow
Token ID7872
Feature activation-5.45e+00

Pos logit contributions
ows+0.011
pering+0.010
arl+0.010
oms+0.010
 announcements+0.010
Neg logit contributions
 flavor-0.009
 ornament-0.009
 penny-0.009
 peanut-0.009
seed-0.008
Token bow
Token ID9563
Feature activation-2.76e+00

Pos logit contributions
 flavor+0.145
 penny+0.143
mar+0.142
 ornament+0.141
pol+0.141
Neg logit contributions
ows-0.162
oms-0.158
arl-0.157
uits-0.149
iving-0.142
Tokenmy
Token ID1820
Feature activation-2.42e+00

Pos logit contributions
 penny+0.045
 flavor+0.040
 dime+0.040
 peanut+0.038
 ornament+0.037
Neg logit contributions
ows-0.083
obb-0.077
pering-0.075
arl-0.073
 realize-0.073
Token loved
Token ID6151
Feature activation-5.22e-01

Pos logit contributions
 penny+0.080
 flavor+0.077
 dime+0.075
 ornament+0.075
 ruby+0.071
Neg logit contributions
ows-0.063
obb-0.055
 sons-0.053
 realize-0.053
pering-0.053
Token wearing
Token ID5762
Feature activation-2.72e+00

Pos logit contributions
 penny+0.014
c+0.014
 flavor+0.013
 ornament+0.013
 ruby+0.013
Neg logit contributions
pering-0.015
 dolphins-0.015
 announcements-0.014
 men-0.014
arl-0.014
Token his
Token ID465
Feature activation-3.20e+00

Pos logit contributions
 flavor+0.071
 penny+0.070
 ornament+0.068
 cube+0.066
 peanut+0.062
Neg logit contributions
ows-0.089
obb-0.087
pering-0.087
arl-0.086
 announcements-0.085
Token favorite
Token ID4004
Feature activation-6.18e+00

Pos logit contributions
 flavor+0.086
 ornament+0.086
 penny+0.083
checked+0.083
mar+0.082
Neg logit contributions
ows-0.096
obb-0.094
arl-0.091
 sons-0.086
 Super-0.085
Token red
Token ID2266
Feature activation-7.87e+00

Pos logit contributions
checked+0.196
pol+0.186
mar+0.186
 Lem+0.185
iw+0.184
Neg logit contributions
 loud-0.141
 dolphins-0.135
 dancers-0.133
 men-0.131
 tent-0.130
Token cap
Token ID1451
Feature activation-2.56e+00

Pos logit contributions
pol+0.238
 mattered+0.233
checked+0.232
 Lem+0.231
wealth+0.229
Neg logit contributions
arl-0.185
uits-0.173
ows-0.169
oms-0.165
 men-0.161
Token everywhere
Token ID8347
Feature activation+7.08e-01

Pos logit contributions
 flavor+0.091
 penny+0.091
 ornament+0.088
 peanut+0.087
 cube+0.085
Neg logit contributions
ows-0.071
pering-0.058
obb-0.058
adders-0.056
iving-0.055
Token he
Token ID339
Feature activation+1.56e+00

Pos logit contributions
ows+0.020
pering+0.019
obb+0.019
arl+0.018
iving+0.018
Neg logit contributions
 penny-0.024
 flavor-0.024
 ornament-0.023
 peanut-0.023
 cube-0.022
Token went
Token ID1816
Feature activation+3.38e+00

Pos logit contributions
ows+0.043
obb+0.042
pering+0.042
arl+0.041
iving+0.040
Neg logit contributions
 ornament-0.048
 flavor-0.048
 penny-0.048
 cube-0.047
 peanut-0.044
Token.
Token ID13
Feature activation-1.41e+00

Pos logit contributions
ows+0.112
pering+0.110
obb+0.106
arl+0.105
iving+0.102
Neg logit contributions
 penny-0.099
 flavor-0.098
 ornament-0.096
 cube-0.094
 peanut-0.093
Token.
Token ID13
Feature activation-2.35e+00

Pos logit contributions
 penny+0.062
 flavor+0.061
 ornament+0.058
 peanut+0.058
 flavour+0.056
Neg logit contributions
pering-0.028
ows-0.027
arl-0.026
iving-0.023
obb-0.023
Token Tim
Token ID5045
Feature activation-2.31e+00

Pos logit contributions
 penny+0.093
 ornament+0.086
 jewel+0.081
 peanut+0.081
 ruby+0.081
Neg logit contributions
ows-0.055
arl-0.054
pering-0.052
obb-0.051
adders-0.048
Tokenmy
Token ID1820
Feature activation-2.45e+00

Pos logit contributions
 penny+0.056
 dime+0.050
 flavor+0.049
 peanut+0.048
 mint+0.046
Neg logit contributions
ows-0.085
obb-0.078
pering-0.074
 realize-0.074
arl-0.074
Token loved
Token ID6151
Feature activation-7.40e-01

Pos logit contributions
 penny+0.090
 dime+0.088
 flavor+0.085
 gu+0.083
 ruby+0.082
Neg logit contributions
ows-0.050
 realize-0.042
obb-0.041
 sons-0.040
 Super-0.039
Token his
Token ID465
Feature activation-2.89e+00

Pos logit contributions
c+0.021
 ruby+0.021
 penny+0.020
 flavor+0.020
 ornament+0.020
Neg logit contributions
 dolphins-0.019
pering-0.019
 men-0.018
 dancers-0.018
 Super-0.018
Token red
Token ID2266
Feature activation-7.86e+00

Pos logit contributions
seed+0.072
c+0.070
checked+0.068
mar+0.068
pol+0.066
Neg logit contributions
arl-0.092
 sons-0.088
 Super-0.086
obb-0.085
ows-0.084
Token shirt
Token ID10147
Feature activation-6.08e+00

Pos logit contributions
 mattered+0.223
checked+0.221
pol+0.220
wealth+0.217
mar+0.214
Neg logit contributions
arl-0.182
 men-0.168
 loud-0.165
ows-0.164
 ropes-0.164
Token and
Token ID290
Feature activation-1.62e+00

Pos logit contributions
 penny+0.193
 flavor+0.189
shr+0.188
 peanut+0.187
seed+0.186
Neg logit contributions
ows-0.175
obb-0.149
pering-0.138
adders-0.134
iving-0.133
Token wore
Token ID12408
Feature activation-2.54e+00

Pos logit contributions
 ornament+0.046
 penny+0.045
shr+0.044
ake+0.043
ase+0.043
Neg logit contributions
 Super-0.042
ows-0.042
 realize-0.041
uits-0.039
 announcements-0.039
Token it
Token ID340
Feature activation-4.68e+00

Pos logit contributions
 ornament+0.077
 flavor+0.075
 cube+0.075
 penny+0.073
seed+0.072
Neg logit contributions
ows-0.069
 Super-0.066
 announcements-0.066
aults-0.066
uits-0.065
Token every
Token ID790
Feature activation+1.16e+00

Pos logit contributions
 flavor+0.153
 penny+0.151
 ornament+0.148
 peanut+0.146
 cube+0.143
Neg logit contributions
ows-0.137
obb-0.127
pering-0.124
arl-0.118
iving-0.114
Token.
Token ID13
Feature activation-1.73e+00

Pos logit contributions
 penny+0.086
 flavor+0.085
 ornament+0.084
 peanut+0.081
 cube+0.080
Neg logit contributions
ows-0.057
pering-0.056
arl-0.052
iving-0.051
oms-0.049
Token Tim
Token ID5045
Feature activation-1.89e+00

Pos logit contributions
 penny+0.074
 ornament+0.071
 flavor+0.069
 peanut+0.068
 ruby+0.066
Neg logit contributions
ows-0.036
arl-0.035
pering-0.032
obb-0.030
iving-0.030
Token wore
Token ID12408
Feature activation-2.82e+00

Pos logit contributions
 flavor+0.037
 penny+0.037
 ornament+0.035
 cube+0.034
 peanut+0.034
Neg logit contributions
pering-0.080
ows-0.080
arl-0.078
obb-0.077
iving-0.075
Token his
Token ID465
Feature activation-3.49e+00

Pos logit contributions
 ornament+0.100
 penny+0.100
 cube+0.099
 flavor+0.097
 occasion+0.095
Neg logit contributions
ows-0.061
obb-0.057
 Super-0.055
 announcements-0.055
uits-0.054
Token big
Token ID1263
Feature activation-3.35e+00

Pos logit contributions
 ornament+0.086
 flavor+0.085
checked+0.083
 penny+0.082
shr+0.080
Neg logit contributions
ows-0.112
obb-0.111
arl-0.109
oms-0.102
pering-0.102
Token red
Token ID2266
Feature activation-7.84e+00

Pos logit contributions
checked+0.100
shr+0.099
pol+0.098
 ornament+0.096
mar+0.096
Neg logit contributions
oms-0.087
 men-0.087
arl-0.085
obb-0.085
ows-0.083
Token coat
Token ID13209
Feature activation-3.21e+00

Pos logit contributions
checked+0.238
pol+0.236
 ornament+0.234
 mattered+0.233
 flavour+0.227
Neg logit contributions
arl-0.201
uits-0.185
oms-0.184
ows-0.183
obb-0.166
Token because
Token ID780
Feature activation-1.83e-01

Pos logit contributions
 penny+0.108
 flavor+0.108
 ornament+0.106
 peanut+0.103
 cube+0.103
Neg logit contributions
ows-0.091
pering-0.088
obb-0.083
arl-0.082
iving-0.079
Token it
Token ID340
Feature activation-3.40e+00

Pos logit contributions
 flavor+0.005
 penny+0.005
 ornament+0.005
 peanut+0.005
 cube+0.005
Neg logit contributions
ows-0.006
pering-0.006
adders-0.006
obb-0.006
arl-0.006
Token was
Token ID373
Feature activation-1.75e-01

Pos logit contributions
 flavor+0.092
 dime+0.091
 peanut+0.089
 penny+0.089
 ornament+0.088
Neg logit contributions
ows-0.113
obb-0.102
 Super-0.094
pering-0.092
 announcements-0.092
Token cold
Token ID4692
Feature activation+7.86e-02

Pos logit contributions
 penny+0.005
 flavor+0.005
 ornament+0.005
 cube+0.005
 peanut+0.005
Neg logit contributions
ows-0.006
pering-0.006
obb-0.005
arl-0.005
iving-0.005
Token He
Token ID679
Feature activation+4.18e-02

Pos logit contributions
 penny+0.096
 ornament+0.088
 peanut+0.083
 possession+0.083
 jewel+0.082
Neg logit contributions
ows-0.059
arl-0.057
pering-0.054
obb-0.053
adders-0.051
Token loved
Token ID6151
Feature activation-3.87e-01

Pos logit contributions
ows+0.001
obb+0.001
 Super+0.001
pering+0.001
 announcements+0.001
Neg logit contributions
 penny-0.001
 flavor-0.001
 ornament-0.001
 dime-0.001
seed-0.001
Token to
Token ID284
Feature activation-1.32e+00

Pos logit contributions
 penny+0.010
 flavor+0.010
 ornament+0.010
c+0.010
orn+0.010
Neg logit contributions
pering-0.011
 dolphins-0.011
 announcements-0.011
 men-0.010
 dancers-0.010
Token wear
Token ID5806
Feature activation-3.14e+00

Pos logit contributions
 penny+0.035
 flavor+0.033
 ornament+0.033
 peanut+0.032
 cube+0.032
Neg logit contributions
ows-0.045
pering-0.044
obb-0.044
arl-0.043
iving-0.042
Token his
Token ID465
Feature activation-3.32e+00

Pos logit contributions
 flavor+0.077
 penny+0.077
 ornament+0.076
 cube+0.073
 peanut+0.070
Neg logit contributions
ows-0.114
pering-0.111
obb-0.110
arl-0.109
oms-0.104
Token red
Token ID2266
Feature activation-7.80e+00

Pos logit contributions
 ornament+0.085
 flavor+0.083
checked+0.080
 penny+0.079
seed+0.079
Neg logit contributions
ows-0.103
obb-0.103
arl-0.102
 Super-0.095
 sons-0.094
Token hat
Token ID6877
Feature activation-3.68e+00

Pos logit contributions
checked+0.248
pol+0.236
 mattered+0.232
wealth+0.231
seed+0.229
Neg logit contributions
arl-0.181
uits-0.165
ows-0.164
oms-0.164
 Super-0.154
Token everywhere
Token ID8347
Feature activation+4.40e-01

Pos logit contributions
 flavor+0.120
 penny+0.119
 ornament+0.114
 peanut+0.113
 cube+0.112
Neg logit contributions
ows-0.109
pering-0.097
obb-0.095
arl-0.094
iving-0.093
Token he
Token ID339
Feature activation+1.26e+00

Pos logit contributions
ows+0.014
pering+0.014
obb+0.013
arl+0.013
iving+0.013
Neg logit contributions
 penny-0.013
 flavor-0.013
 ornament-0.013
 peanut-0.013
 cube-0.012
Token went
Token ID1816
Feature activation+3.40e+00

Pos logit contributions
ows+0.037
obb+0.035
pering+0.035
arl+0.034
oms+0.034
Neg logit contributions
 penny-0.038
 flavor-0.038
 ornament-0.038
 cube-0.037
 peanut-0.035
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
ows+0.109
pering+0.109
obb+0.104
arl+0.103
iving+0.100
Neg logit contributions
 penny-0.102
 flavor-0.101
 ornament-0.099
 peanut-0.096
 cube-0.096
Token She
Token ID1375
Feature activation+1.03e-01

Pos logit contributions
 penny+0.098
 flavor+0.093
 ornament+0.089
 cube+0.088
 peanut+0.087
Neg logit contributions
ows-0.059
arl-0.056
pering-0.055
obb-0.051
iving-0.051
Token loved
Token ID6151
Feature activation-4.16e-01

Pos logit contributions
ows+0.003
obb+0.003
pering+0.003
 announcements+0.003
 Super+0.002
Neg logit contributions
 penny-0.003
 flavor-0.003
 ornament-0.003
 dime-0.003
 peanut-0.003
Token to
Token ID284
Feature activation-1.38e+00

Pos logit contributions
 penny+0.012
 ruby+0.011
 flavor+0.011
orn+0.011
c+0.011
Neg logit contributions
 dancers-0.011
pering-0.011
 dolphins-0.011
arl-0.011
 announcements-0.011
Token wear
Token ID5806
Feature activation-3.11e+00

Pos logit contributions
 penny+0.038
 flavor+0.036
 ornament+0.035
 cube+0.034
 peanut+0.034
Neg logit contributions
ows-0.046
obb-0.045
pering-0.044
arl-0.044
iving-0.042
Token her
Token ID607
Feature activation-3.00e+00

Pos logit contributions
 cube+0.091
 flavor+0.091
 penny+0.090
 ornament+0.087
 nut+0.084
Neg logit contributions
ows-0.096
obb-0.093
arl-0.092
pering-0.089
 announcements-0.087
Token orange
Token ID10912
Feature activation-7.79e+00

Pos logit contributions
 flavor+0.080
 nut+0.075
 ornament+0.074
 cube+0.074
seed+0.073
Neg logit contributions
ows-0.094
obb-0.092
arl-0.091
oms-0.085
 Super-0.084
Token bath
Token ID7837
Feature activation-2.76e+00

Pos logit contributions
 dime+0.228
checked+0.227
pol+0.225
 flavour+0.223
wealth+0.221
Neg logit contributions
 dancers-0.172
oms-0.166
arl-0.164
ows-0.163
 ropes-0.158
Tokenrobe
Token ID25481
Feature activation-9.49e-01

Pos logit contributions
 penny+0.081
 flavor+0.080
 ornament+0.078
 peanut+0.076
 cube+0.076
Neg logit contributions
ows-0.091
pering-0.090
obb-0.086
arl-0.085
iving-0.083
Token after
Token ID706
Feature activation+9.11e-01

Pos logit contributions
 penny+0.028
 flavor+0.028
 ornament+0.027
 peanut+0.026
 cube+0.026
Neg logit contributions
ows-0.031
pering-0.031
obb-0.030
arl-0.029
iving-0.028
Token taking
Token ID2263
Feature activation+2.50e+00

Pos logit contributions
pering+0.033
ows+0.033
obb+0.032
arl+0.031
iving+0.030
Neg logit contributions
 penny-0.023
 flavor-0.023
 ornament-0.022
 cube-0.022
 peanut-0.022
Token a
Token ID257
Feature activation+1.61e+00

Pos logit contributions
ows+0.074
pering+0.072
obb+0.072
 announcements+0.071
arl+0.068
Neg logit contributions
 cube-0.077
 flavor-0.076
 ornament-0.074
 penny-0.074
 magnet-0.070
Token.
Token ID13
Feature activation-1.54e+00

Pos logit contributions
ows+0.011
pering+0.011
iving+0.010
arl+0.010
oms+0.010
Neg logit contributions
 penny-0.016
 flavor-0.016
 ornament-0.016
 peanut-0.015
 cube-0.015
Token She
Token ID1375
Feature activation+3.98e-01

Pos logit contributions
 penny+0.052
 flavor+0.052
 ornament+0.050
 cube+0.050
 peanut+0.048
Neg logit contributions
ows-0.044
pering-0.043
arl-0.041
iving-0.039
obb-0.039
Token wore
Token ID12408
Feature activation-2.54e+00

Pos logit contributions
ows+0.013
pering+0.013
obb+0.013
oms+0.012
 announcements+0.012
Neg logit contributions
 penny-0.011
 flavor-0.011
 ornament-0.011
 cube-0.010
 peanut-0.010
Token her
Token ID607
Feature activation-3.19e+00

Pos logit contributions
 cube+0.099
 flavor+0.094
 penny+0.093
 ornament+0.090
 magnet+0.088
Neg logit contributions
ows-0.054
obb-0.049
 announcements-0.049
aults-0.048
uits-0.048
Token favorite
Token ID4004
Feature activation-6.25e+00

Pos logit contributions
 flavor+0.081
 ornament+0.078
 penny+0.076
 cube+0.074
 peanut+0.074
Neg logit contributions
ows-0.106
obb-0.102
arl-0.098
pering-0.095
adders-0.092
Token pink
Token ID11398
Feature activation-7.78e+00

Pos logit contributions
checked+0.210
 Lem+0.195
shr+0.193
 Smith+0.193
mar+0.190
Neg logit contributions
ows-0.128
 loud-0.128
 ropes-0.120
iet-0.119
 dancers-0.116
Token boots
Token ID14412
Feature activation-1.43e+00

Pos logit contributions
checked+0.248
pol+0.243
wealth+0.243
 Lem+0.243
 flavor+0.240
Neg logit contributions
ows-0.156
arl-0.154
oms-0.151
uits-0.148
 dancers-0.147
Token,
Token ID11
Feature activation-7.90e-01

Pos logit contributions
 flavor+0.050
 penny+0.049
 ornament+0.048
 peanut+0.048
 cube+0.047
Neg logit contributions
ows-0.040
pering-0.037
obb-0.035
arl-0.035
iving-0.034
Token which
Token ID543
Feature activation-2.08e+00

Pos logit contributions
 penny+0.025
 flavor+0.024
 ornament+0.024
 peanut+0.023
 cube+0.023
Neg logit contributions
ows-0.025
pering-0.024
obb-0.023
arl-0.023
iving-0.022
Token made
Token ID925
Feature activation-6.34e-01

Pos logit contributions
 penny+0.050
 flavor+0.050
 ornament+0.049
 cube+0.048
 peanut+0.048
Neg logit contributions
ows-0.077
pering-0.072
obb-0.071
adders-0.070
oms-0.069
Token her
Token ID607
Feature activation-4.08e-01

Pos logit contributions
 flavor+0.008
 ornament+0.008
 peanut+0.007
 penny+0.007
 color+0.007
Neg logit contributions
pering-0.034
arl-0.032
ows-0.031
obb-0.031
 sons-0.030
Token who
Token ID508
Feature activation-2.72e+00

Pos logit contributions
pering+0.003
ows+0.003
oms+0.003
iving+0.003
obb+0.003
Neg logit contributions
 penny-0.007
 flavor-0.007
 ornament-0.007
 peanut-0.007
 cube-0.007
Token liked
Token ID8288
Feature activation-1.38e+00

Pos logit contributions
 penny+0.072
 flavor+0.070
 ornament+0.070
 peanut+0.067
 cube+0.065
Neg logit contributions
ows-0.096
pering-0.091
obb-0.091
arl-0.087
iving-0.086
Token to
Token ID284
Feature activation-1.47e+00

Pos logit contributions
 penny+0.029
 flavor+0.029
 ornament+0.028
 peanut+0.026
 cube+0.026
Neg logit contributions
pering-0.053
ows-0.052
arl-0.050
obb-0.050
iving-0.050
Token wear
Token ID5806
Feature activation-3.10e+00

Pos logit contributions
 flavor+0.039
 penny+0.038
 ornament+0.037
 cube+0.036
 peanut+0.036
Neg logit contributions
pering-0.054
ows-0.053
arl-0.051
obb-0.050
iving-0.049
Token his
Token ID465
Feature activation-3.11e+00

Pos logit contributions
 penny+0.064
 flavor+0.064
 ornament+0.062
 cube+0.059
 peanut+0.059
Neg logit contributions
ows-0.128
pering-0.127
obb-0.123
arl-0.122
iving-0.119
Token red
Token ID2266
Feature activation-7.77e+00

Pos logit contributions
 flavor+0.074
 ornament+0.071
 penny+0.070
 peanut+0.068
seed+0.066
Neg logit contributions
ows-0.105
obb-0.105
arl-0.103
pering-0.100
oms-0.100
Token cap
Token ID1451
Feature activation-2.68e+00

Pos logit contributions
 flavor+0.212
 flavour+0.209
 dime+0.209
pol+0.208
checked+0.207
Neg logit contributions
ows-0.211
arl-0.211
oms-0.202
uits-0.198
iving-0.184
Token.
Token ID13
Feature activation-1.96e+00

Pos logit contributions
 penny+0.089
 flavor+0.089
 ornament+0.087
 peanut+0.085
 cube+0.084
Neg logit contributions
ows-0.077
pering-0.075
obb-0.072
arl-0.071
iving-0.069
Token He
Token ID679
Feature activation+9.48e-02

Pos logit contributions
 penny+0.060
 ornament+0.058
 peanut+0.056
 flavor+0.056
 cube+0.054
Neg logit contributions
ows-0.062
arl-0.060
pering-0.059
obb-0.059
iving-0.057
Token always
Token ID1464
Feature activation-2.00e+00

Pos logit contributions
ows+0.004
pering+0.003
obb+0.003
oms+0.003
arl+0.003
Neg logit contributions
 penny-0.002
 flavor-0.002
 ornament-0.002
 peanut-0.002
 cube-0.002
Token did
Token ID750
Feature activation-6.11e-01

Pos logit contributions
 penny+0.044
 ornament+0.044
 flavor+0.043
 peanut+0.041
 cube+0.041
Neg logit contributions
ows-0.079
pering-0.075
obb-0.074
arl-0.073
 announcements-0.072
Token who
Token ID508
Feature activation-2.98e+00

Pos logit contributions
 flavor+0.017
 penny+0.017
 ornament+0.017
 peanut+0.017
 cube+0.017
Neg logit contributions
ows-0.011
pering-0.011
oms-0.009
iving-0.009
arl-0.009
Token liked
Token ID8288
Feature activation-1.33e+00

Pos logit contributions
 penny+0.068
 flavor+0.067
 ornament+0.065
 cube+0.063
 peanut+0.063
Neg logit contributions
ows-0.117
pering-0.116
obb-0.112
arl-0.111
iving-0.108
Token to
Token ID284
Feature activation-1.55e+00

Pos logit contributions
 penny+0.027
 flavor+0.027
 ornament+0.026
 cube+0.025
 peanut+0.025
Neg logit contributions
pering-0.052
ows-0.051
arl-0.049
obb-0.049
iving-0.049
Token wear
Token ID5806
Feature activation-3.14e+00

Pos logit contributions
 flavor+0.043
 penny+0.042
 ornament+0.041
 peanut+0.040
 cube+0.040
Neg logit contributions
ows-0.054
pering-0.054
obb-0.051
arl-0.051
iving-0.050
Token her
Token ID607
Feature activation-2.91e+00

Pos logit contributions
 penny+0.078
 flavor+0.077
 ornament+0.075
 cube+0.074
 peanut+0.072
Neg logit contributions
ows-0.116
pering-0.114
obb-0.111
arl-0.110
oms-0.107
Token red
Token ID2266
Feature activation-7.75e+00

Pos logit contributions
 flavor+0.069
 penny+0.067
 ornament+0.067
 cube+0.065
 peanut+0.064
Neg logit contributions
ows-0.104
obb-0.099
pering-0.098
arl-0.098
oms-0.097
Token dress
Token ID6576
Feature activation-5.63e+00

Pos logit contributions
 dime+0.216
 flavor+0.214
 penny+0.211
checked+0.209
pol+0.209
Neg logit contributions
ows-0.214
arl-0.213
oms-0.206
uits-0.194
iving-0.188
Token and
Token ID290
Feature activation-1.58e+00

Pos logit contributions
 penny+0.173
 flavor+0.173
 ornament+0.169
 cube+0.164
 peanut+0.164
Neg logit contributions
pering-0.177
ows-0.173
obb-0.167
arl-0.165
iving-0.160
Token her
Token ID607
Feature activation-2.55e+00

Pos logit contributions
 penny+0.044
 flavor+0.043
 ornament+0.043
 cube+0.043
 peanut+0.040
Neg logit contributions
ows-0.051
pering-0.049
arl-0.048
 announcements-0.047
obb-0.047
Token shiny
Token ID22441
Feature activation-5.86e+00

Pos logit contributions
 flavor+0.056
 penny+0.055
 ornament+0.053
 peanut+0.052
 cube+0.052
Neg logit contributions
ows-0.098
pering-0.093
obb-0.093
arl-0.093
oms-0.090
Token shoes
Token ID10012
Feature activation-3.70e+00

Pos logit contributions
 flavor+0.142
 peanut+0.136
 penny+0.135
 ornament+0.133
 cube+0.132
Neg logit contributions
ows-0.209
arl-0.194
obb-0.192
oms-0.192
pering-0.184
Token outside
Token ID2354
Feature activation-2.16e-01

Pos logit contributions
ows+0.013
pering+0.013
obb+0.013
iving+0.013
arl+0.013
Neg logit contributions
 penny-0.013
 flavor-0.013
 ornament-0.012
 peanut-0.012
 cube-0.011
Token,
Token ID11
Feature activation-1.12e+00

Pos logit contributions
 penny+0.006
 flavor+0.006
 ornament+0.006
 peanut+0.006
 cube+0.006
Neg logit contributions
ows-0.007
pering-0.007
obb-0.007
arl-0.007
iving-0.007
Token especially
Token ID2592
Feature activation-2.93e+00

Pos logit contributions
 flavor+0.035
 cube+0.034
 penny+0.034
 ornament+0.033
 peanut+0.033
Neg logit contributions
ows-0.037
arl-0.036
pering-0.036
obb-0.036
oms-0.034
Token with
Token ID351
Feature activation-3.12e+00

Pos logit contributions
 penny+0.094
 flavor+0.093
 ornament+0.091
 cube+0.089
 peanut+0.089
Neg logit contributions
pering-0.084
ows-0.084
arl-0.079
obb-0.079
iving-0.078
Token his
Token ID465
Feature activation-3.28e+00

Pos logit contributions
 penny+0.064
 flavor+0.064
 ornament+0.062
 cube+0.059
 peanut+0.059
Neg logit contributions
ows-0.128
pering-0.128
obb-0.123
arl-0.123
iving-0.120
Token red
Token ID2266
Feature activation-7.75e+00

Pos logit contributions
 flavor+0.090
 penny+0.089
 ornament+0.089
 peanut+0.084
 cube+0.081
Neg logit contributions
ows-0.105
pering-0.101
arl-0.101
obb-0.100
iving-0.096
Token flag
Token ID6056
Feature activation-3.61e+00

Pos logit contributions
 penny+0.232
pol+0.230
 ornament+0.230
 flavor+0.227
 dime+0.220
Neg logit contributions
arl-0.206
ows-0.196
iving-0.187
oms-0.184
obb-0.181
Token.
Token ID13
Feature activation-1.65e+00

Pos logit contributions
 flavor+0.128
 penny+0.128
 ornament+0.124
 peanut+0.122
 cube+0.120
Neg logit contributions
ows-0.096
pering-0.092
arl-0.087
obb-0.086
iving-0.084
Token One
Token ID1881
Feature activation+3.37e-03

Pos logit contributions
 penny+0.057
 ornament+0.052
 flavor+0.050
 peanut+0.050
 jewel+0.048
Neg logit contributions
ows-0.047
arl-0.045
pering-0.042
iving-0.041
 Super-0.040
Token day
Token ID1110
Feature activation-1.49e-01

Pos logit contributions
iving+0.000
obb+0.000
ila+0.000
wing+0.000
ows+0.000
Neg logit contributions
 dime-0.000
 penny-0.000
 ornament-0.000
 ruby-0.000
 magnet-0.000
Token,
Token ID11
Feature activation-5.11e-01

Pos logit contributions
 ornament+0.006
 penny+0.006
 flavor+0.006
 ruby+0.006
c+0.006
Neg logit contributions
iving-0.003
arl-0.003
oms-0.002
obb-0.002
ows-0.002
Token loved
Token ID6151
Feature activation-7.58e-01

Pos logit contributions
 penny+0.085
 dime+0.080
 flavor+0.080
 ornament+0.079
 ruby+0.075
Neg logit contributions
ows-0.065
obb-0.056
 realize-0.054
pering-0.054
 sons-0.053
Token to
Token ID284
Feature activation-1.81e+00

Pos logit contributions
c+0.021
 ruby+0.021
 penny+0.020
orn+0.020
 ornament+0.020
Neg logit contributions
 dolphins-0.020
 dancers-0.019
 men-0.019
pering-0.019
 announcements-0.019
Token play
Token ID711
Feature activation+2.90e-01

Pos logit contributions
 penny+0.047
 flavor+0.045
 ornament+0.045
 peanut+0.044
 cube+0.043
Neg logit contributions
ows-0.063
pering-0.061
obb-0.060
arl-0.060
oms-0.058
Token with
Token ID351
Feature activation-2.79e+00

Pos logit contributions
ows+0.010
pering+0.009
obb+0.009
arl+0.009
iving+0.009
Neg logit contributions
 penny-0.008
 flavor-0.008
 ornament-0.008
 peanut-0.008
 cube-0.008
Token his
Token ID465
Feature activation-3.10e+00

Pos logit contributions
 penny+0.068
 flavor+0.067
 ornament+0.064
 peanut+0.061
 cube+0.059
Neg logit contributions
obb-0.095
ows-0.093
pering-0.093
arl-0.091
adders-0.090
Token red
Token ID2266
Feature activation-7.73e+00

Pos logit contributions
 flavor+0.072
 penny+0.069
 ornament+0.068
 peanut+0.066
pol+0.065
Neg logit contributions
arl-0.105
ows-0.104
obb-0.104
pering-0.103
 sons-0.102
Token ball
Token ID2613
Feature activation-4.45e+00

Pos logit contributions
pol+0.237
 mattered+0.233
wealth+0.232
mar+0.228
checked+0.219
Neg logit contributions
arl-0.186
 men-0.171
ows-0.167
iving-0.166
oms-0.166
Token outside
Token ID2354
Feature activation-7.82e-01

Pos logit contributions
 flavor+0.150
 penny+0.149
 ornament+0.142
 peanut+0.142
 cube+0.137
Neg logit contributions
ows-0.126
pering-0.121
obb-0.118
arl-0.113
iving-0.113
Token.
Token ID13
Feature activation-1.91e+00

Pos logit contributions
 flavor+0.021
 cube+0.021
 ornament+0.021
 penny+0.021
 peanut+0.019
Neg logit contributions
ows-0.029
pering-0.028
arl-0.027
obb-0.027
oms-0.026
Token One
Token ID1881
Feature activation-1.63e-01

Pos logit contributions
 penny+0.067
 ornament+0.061
 peanut+0.061
seed+0.060
 flavor+0.059
Neg logit contributions
ows-0.052
arl-0.050
pering-0.046
iving-0.046
 Super-0.045
Token day
Token ID1110
Feature activation-2.83e-01

Pos logit contributions
 dime+0.005
 penny+0.004
 ruby+0.004
 ornament+0.004
 cand+0.004
Neg logit contributions
iving-0.005
obb-0.004
arl-0.004
ila-0.004
ows-0.004
Token loved
Token ID6151
Feature activation-5.21e-01

Pos logit contributions
ows+0.001
obb+0.001
pering+0.000
 announcements+0.000
arl+0.000
Neg logit contributions
 penny-0.001
 flavor-0.001
 ornament-0.001
 dime-0.001
 peanut-0.001
Token to
Token ID284
Feature activation-1.45e+00

Pos logit contributions
 penny+0.014
 flavor+0.014
 ruby+0.014
orn+0.014
 ornament+0.014
Neg logit contributions
pering-0.014
 dancers-0.014
 dolphins-0.014
 announcements-0.014
arl-0.013
Token wear
Token ID5806
Feature activation-3.16e+00

Pos logit contributions
 penny+0.038
 flavor+0.037
 ornament+0.037
 cube+0.035
 peanut+0.035
Neg logit contributions
ows-0.050
pering-0.049
obb-0.048
arl-0.047
iving-0.046
Token her
Token ID607
Feature activation-3.13e+00

Pos logit contributions
 flavor+0.090
 penny+0.089
 cube+0.089
 ornament+0.088
 nut+0.082
Neg logit contributions
ows-0.102
obb-0.097
arl-0.097
pering-0.096
 announcements-0.092
Token favorite
Token ID4004
Feature activation-6.28e+00

Pos logit contributions
 flavor+0.083
 ornament+0.081
 penny+0.077
 nut+0.076
 cube+0.075
Neg logit contributions
ows-0.099
obb-0.098
arl-0.096
oms-0.092
pering-0.089
Token pink
Token ID11398
Feature activation-7.71e+00

Pos logit contributions
checked+0.212
shr+0.198
mar+0.195
 Smith+0.194
pol+0.191
Neg logit contributions
 loud-0.121
 dancers-0.120
iet-0.119
 dolphins-0.119
 ropes-0.119
Token dress
Token ID6576
Feature activation-5.62e+00

Pos logit contributions
checked+0.231
pol+0.231
wealth+0.227
 flavour+0.223
 flavor+0.223
Neg logit contributions
oms-0.168
arl-0.168
 dancers-0.159
uits-0.157
ows-0.155
Token every
Token ID790
Feature activation+1.37e+00

Pos logit contributions
 penny+0.187
 flavor+0.185
 ornament+0.180
 peanut+0.179
 cube+0.177
Neg logit contributions
ows-0.167
pering-0.148
obb-0.146
arl-0.144
iving-0.139
Token day
Token ID1110
Feature activation+1.20e+00

Pos logit contributions
arl+0.040
obb+0.039
iving+0.038
oms+0.037
pering+0.037
Neg logit contributions
 flavor-0.034
 dime-0.033
seed-0.033
 peanut-0.033
 cube-0.032
Token.
Token ID13
Feature activation-1.69e+00

Pos logit contributions
ows+0.029
pering+0.028
obb+0.025
arl+0.025
oms+0.025
Neg logit contributions
 penny-0.045
 flavor-0.045
 ornament-0.045
 cube-0.044
 nut-0.043
Token One
Token ID1881
Feature activation-5.80e-02

Pos logit contributions
 penny+0.061
 cube+0.053
 possession+0.052
 symbol+0.052
 nut+0.052
Neg logit contributions
ows-0.049
arl-0.046
oms-0.041
iving-0.040
ains-0.039
Token loved
Token ID6151
Feature activation-6.63e-01

Pos logit contributions
 penny+0.085
 dime+0.082
 flavor+0.081
 ornament+0.079
 gu+0.078
Neg logit contributions
ows-0.054
 realize-0.047
obb-0.047
 sons-0.045
 Super-0.043
Token to
Token ID284
Feature activation-1.66e+00

Pos logit contributions
c+0.018
 penny+0.018
 ruby+0.018
 ornament+0.018
seed+0.017
Neg logit contributions
 dolphins-0.018
pering-0.018
 men-0.017
 announcements-0.017
 dancers-0.017
Token play
Token ID711
Feature activation+3.29e-01

Pos logit contributions
 penny+0.042
 flavor+0.041
 ornament+0.040
 peanut+0.039
 cube+0.038
Neg logit contributions
ows-0.060
pering-0.059
obb-0.058
arl-0.057
iving-0.056
Token with
Token ID351
Feature activation-2.74e+00

Pos logit contributions
ows+0.011
pering+0.011
obb+0.010
iving+0.010
arl+0.010
Neg logit contributions
 penny-0.009
 flavor-0.009
 ornament-0.009
 peanut-0.009
 cube-0.009
Token his
Token ID465
Feature activation-3.16e+00

Pos logit contributions
 penny+0.071
 flavor+0.069
 ornament+0.067
mar+0.064
 peanut+0.063
Neg logit contributions
obb-0.088
ows-0.084
pering-0.083
adders-0.083
arl-0.082
Token red
Token ID2266
Feature activation-7.71e+00

Pos logit contributions
 flavor+0.080
mar+0.078
 ornament+0.077
c+0.077
pol+0.077
Neg logit contributions
 sons-0.099
arl-0.094
obb-0.093
ows-0.092
 men-0.092
Token wagon
Token ID31860
Feature activation-3.93e+00

Pos logit contributions
pol+0.243
mar+0.243
wealth+0.239
 mattered+0.237
checked+0.233
Neg logit contributions
arl-0.168
 men-0.158
 ropes-0.156
uits-0.147
iving-0.146
Token.
Token ID13
Feature activation-1.84e+00

Pos logit contributions
 flavor+0.142
 penny+0.140
 peanut+0.136
 ornament+0.133
 cube+0.126
Neg logit contributions
ows-0.102
pering-0.093
obb-0.088
adders-0.085
iving-0.084
Token He
Token ID679
Feature activation+2.96e-02

Pos logit contributions
 penny+0.067
 ornament+0.062
 peanut+0.061
seed+0.060
 jewel+0.058
Neg logit contributions
ows-0.048
arl-0.046
iving-0.042
pering-0.041
 Super-0.041
Token would
Token ID561
Feature activation+2.69e-01

Pos logit contributions
ows+0.001
adders+0.001
obb+0.001
as+0.001
uits+0.001
Neg logit contributions
 penny-0.001
 flavor-0.001
 ornament-0.001
 peanut-0.001
 avocado-0.001
Token pull
Token ID2834
Feature activation-1.12e+00

Pos logit contributions
ows+0.008
pering+0.008
arl+0.008
obb+0.008
oms+0.008
Neg logit contributions
 penny-0.009
 flavor-0.009
 ornament-0.008
 cube-0.008
 peanut-0.008
Token loved
Token ID6151
Feature activation-5.89e-01

Pos logit contributions
 penny+0.060
 flavor+0.056
 dime+0.055
 peanut+0.054
 ornament+0.053
Neg logit contributions
ows-0.061
obb-0.055
pering-0.052
adders-0.051
 realize-0.050
Token to
Token ID284
Feature activation-1.47e+00

Pos logit contributions
c+0.016
 penny+0.016
 ornament+0.016
seed+0.015
orn+0.015
Neg logit contributions
 dolphins-0.016
pering-0.016
 men-0.016
 dancers-0.016
 travelers-0.015
Token play
Token ID711
Feature activation+3.89e-01

Pos logit contributions
 penny+0.037
 flavor+0.036
 ornament+0.035
 peanut+0.034
 cube+0.034
Neg logit contributions
ows-0.054
pering-0.053
obb-0.052
arl-0.051
iving-0.050
Token with
Token ID351
Feature activation-2.64e+00

Pos logit contributions
ows+0.014
pering+0.013
obb+0.013
arl+0.013
iving+0.013
Neg logit contributions
 penny-0.010
 flavor-0.010
 ornament-0.010
 peanut-0.010
 cube-0.010
Token his
Token ID465
Feature activation-2.89e+00

Pos logit contributions
 penny+0.068
 flavor+0.065
 ornament+0.064
mar+0.060
 peanut+0.060
Neg logit contributions
obb-0.086
ows-0.084
adders-0.082
pering-0.081
arl-0.080
Token red
Token ID2266
Feature activation-7.70e+00

Pos logit contributions
 flavor+0.064
mar+0.062
c+0.062
seed+0.061
 peanut+0.060
Neg logit contributions
 sons-0.098
arl-0.096
obb-0.096
ows-0.094
 men-0.094
Token blocks
Token ID7021
Feature activation-2.48e+00

Pos logit contributions
mar+0.250
seed+0.249
pol+0.245
 mattered+0.240
checked+0.239
Neg logit contributions
arl-0.168
 men-0.156
oms-0.154
 ropes-0.151
iving-0.148
Token.
Token ID13
Feature activation-1.70e+00

Pos logit contributions
 penny+0.091
 flavor+0.090
 ornament+0.088
 peanut+0.088
 cube+0.085
Neg logit contributions
ows-0.064
pering-0.060
obb-0.058
arl-0.057
iving-0.056
Token Every
Token ID3887
Feature activation+1.97e+00

Pos logit contributions
 penny+0.065
 ornament+0.058
 peanut+0.058
seed+0.055
 jewel+0.055
Neg logit contributions
ows-0.047
arl-0.042
adders-0.040
obb-0.039
iving-0.039
Token day
Token ID1110
Feature activation+4.29e-01

Pos logit contributions
obb+0.068
arl+0.064
iving+0.064
ows+0.064
pering+0.062
Neg logit contributions
 penny-0.045
 ornament-0.045
 peanut-0.043
seed-0.043
 dime-0.043
Token,
Token ID11
Feature activation-4.68e-01

Pos logit contributions
iving+0.006
 men+0.006
oms+0.006
obb+0.006
adders+0.006
Neg logit contributions
 ornament-0.019
c-0.017
 possession-0.017
seed-0.017
 penny-0.017
Tokenmy
Token ID1820
Feature activation-2.49e+00

Pos logit contributions
 penny+0.044
 dime+0.039
 flavor+0.038
 peanut+0.037
 ornament+0.037
Neg logit contributions
ows-0.082
obb-0.075
pering-0.074
arl-0.072
 realize-0.071
Token loved
Token ID6151
Feature activation-7.26e-01

Pos logit contributions
 penny+0.083
 dime+0.079
 flavor+0.079
 ornament+0.078
 peanut+0.074
Neg logit contributions
ows-0.065
obb-0.055
pering-0.054
 realize-0.054
 sons-0.053
Token to
Token ID284
Feature activation-1.77e+00

Pos logit contributions
c+0.019
 ruby+0.019
 penny+0.019
 flavor+0.019
 ornament+0.019
Neg logit contributions
 dolphins-0.020
pering-0.020
 dancers-0.019
 men-0.019
 announcements-0.019
Token wear
Token ID5806
Feature activation-3.38e+00

Pos logit contributions
 penny+0.047
 flavor+0.045
 ornament+0.045
 peanut+0.043
 cube+0.043
Neg logit contributions
ows-0.060
pering-0.058
obb-0.058
arl-0.057
oms-0.055
Token his
Token ID465
Feature activation-3.57e+00

Pos logit contributions
 flavor+0.088
 penny+0.088
 ornament+0.087
 cube+0.084
 peanut+0.079
Neg logit contributions
ows-0.115
arl-0.111
obb-0.111
pering-0.111
iving-0.105
Token red
Token ID2266
Feature activation-7.69e+00

Pos logit contributions
 ornament+0.095
 flavor+0.093
checked+0.092
pol+0.088
 dime+0.088
Neg logit contributions
obb-0.107
arl-0.106
ows-0.105
 Super-0.098
oms-0.095
Token cap
Token ID1451
Feature activation-2.38e+00

Pos logit contributions
checked+0.241
 mattered+0.234
pol+0.232
wealth+0.228
 flavour+0.226
Neg logit contributions
arl-0.192
ows-0.167
oms-0.166
uits-0.164
 ropes-0.156
Token everywhere
Token ID8347
Feature activation+7.06e-01

Pos logit contributions
 flavor+0.076
 penny+0.076
 ornament+0.074
 peanut+0.072
 cube+0.071
Neg logit contributions
ows-0.074
obb-0.066
pering-0.066
arl-0.065
iving-0.063
Token he
Token ID339
Feature activation+1.47e+00

Pos logit contributions
ows+0.019
pering+0.018
obb+0.017
arl+0.016
iving+0.016
Neg logit contributions
 penny-0.025
 flavor-0.024
 ornament-0.024
 peanut-0.024
 cube-0.023
Token went
Token ID1816
Feature activation+3.52e+00

Pos logit contributions
ows+0.041
obb+0.041
pering+0.040
arl+0.039
iving+0.038
Neg logit contributions
 flavor-0.045
 ornament-0.045
 penny-0.045
 cube-0.044
 peanut-0.041
Token.
Token ID13
Feature activation-1.42e+00

Pos logit contributions
ows+0.119
pering+0.118
obb+0.114
arl+0.112
iving+0.109
Neg logit contributions
 penny-0.099
 flavor-0.099
 ornament-0.096
 peanut-0.094
 cube-0.094
Token swim
Token ID9422
Feature activation+1.12e+00

Pos logit contributions
 flavor+0.049
 penny+0.047
 ornament+0.047
 cube+0.045
 peanut+0.045
Neg logit contributions
ows-0.074
pering-0.073
obb-0.070
arl-0.070
iving-0.067
Token.
Token ID13
Feature activation-2.44e+00

Pos logit contributions
pering+0.045
obb+0.043
ows+0.043
arl+0.042
 announcements+0.042
Neg logit contributions
 penny-0.027
 flavor-0.026
 cube-0.026
 peanut-0.024
 ornament-0.024
Token She
Token ID1375
Feature activation-3.21e-02

Pos logit contributions
 flavor+0.062
 penny+0.061
 ornament+0.060
 cube+0.058
 peanut+0.057
Neg logit contributions
ows-0.090
pering-0.090
obb-0.086
arl-0.085
iving-0.082
Token had
Token ID550
Feature activation-4.11e+00

Pos logit contributions
 flavor+0.000
 penny+0.000
 cube+0.000
 peanut+0.000
 color+0.000
Neg logit contributions
pering-0.002
arl-0.002
ows-0.002
obb-0.002
adders-0.001
Token her
Token ID607
Feature activation-2.33e+00

Pos logit contributions
 flavor+0.102
 peanut+0.099
 penny+0.098
 ornament+0.089
 cube+0.089
Neg logit contributions
arl-0.161
ows-0.160
pering-0.159
obb-0.157
iving-0.149
Token red
Token ID2266
Feature activation-7.69e+00

Pos logit contributions
 flavor+0.047
 ornament+0.046
 penny+0.046
 peanut+0.044
 cube+0.043
Neg logit contributions
ows-0.091
pering-0.089
obb-0.088
arl-0.087
oms-0.085
Token swimming
Token ID14899
Feature activation+7.58e-01

Pos logit contributions
 ornament+0.206
pol+0.204
checked+0.203
 penny+0.200
 flavor+0.198
Neg logit contributions
ows-0.219
arl-0.215
oms-0.214
uits-0.205
pering-0.205
Token suit
Token ID6050
Feature activation-2.54e+00

Pos logit contributions
pering+0.029
ows+0.028
 announcements+0.028
ighters+0.027
obb+0.027
Neg logit contributions
 flavor-0.019
 penny-0.019
 cube-0.019
 peanut-0.017
 ornament-0.017
Token ready
Token ID3492
Feature activation+5.59e-01

Pos logit contributions
 flavor+0.062
 penny+0.061
 ornament+0.058
 cube+0.058
 color+0.055
Neg logit contributions
pering-0.101
arl-0.097
obb-0.096
ighters-0.093
 announcements-0.092
Token,
Token ID11
Feature activation+3.95e-01

Pos logit contributions
pering+0.023
obb+0.022
arl+0.022
ows+0.022
ighters+0.021
Neg logit contributions
 flavor-0.013
 penny-0.012
 ornament-0.012
 color-0.011
 peanut-0.011
Token her
Token ID607
Feature activation-6.45e-01

Pos logit contributions
obb+0.015
arl+0.015
ows+0.015
pering+0.014
ighters+0.014
Neg logit contributions
 peanut-0.010
 penny-0.010
 flavor-0.010
 ornament-0.010
 color-0.010
Token racing
Token ID11717
Feature activation+1.11e+00

Pos logit contributions
 flavor+0.057
 penny+0.056
 cube+0.055
 ornament+0.055
 color+0.053
Neg logit contributions
arl-0.091
obb-0.090
ows-0.089
pering-0.087
adders-0.082
Token each
Token ID1123
Feature activation-2.56e+00

Pos logit contributions
pering+0.042
obb+0.041
arl+0.041
ows+0.041
oms+0.038
Neg logit contributions
 flavor-0.027
 penny-0.027
 ornament-0.026
 cube-0.026
 color-0.024
Token other
Token ID584
Feature activation-9.94e-01

Pos logit contributions
 penny+0.074
 flavor+0.074
 ornament+0.072
 cube+0.070
 peanut+0.068
Neg logit contributions
ows-0.088
pering-0.085
arl-0.082
obb-0.082
oms-0.079
Token and
Token ID290
Feature activation-2.04e-01

Pos logit contributions
 penny+0.025
 ornament+0.024
 flavor+0.024
 cube+0.023
 color+0.022
Neg logit contributions
arl-0.038
obb-0.037
pering-0.036
oms-0.034
 announcements-0.034
Token making
Token ID1642
Feature activation+2.60e-01

Pos logit contributions
 penny+0.006
 flavor+0.006
 ornament+0.006
 peanut+0.006
 cube+0.006
Neg logit contributions
ows-0.006
pering-0.006
obb-0.006
arl-0.006
iving-0.006
Token noises
Token ID26782
Feature activation+5.62e+00

Pos logit contributions
arl+0.011
pering+0.010
obb+0.010
ows+0.010
oms+0.010
Neg logit contributions
 flavor-0.006
 ornament-0.006
 penny-0.006
 toy-0.006
 peanut-0.006
Token.
Token ID13
Feature activation-6.65e-01

Pos logit contributions
arl+0.273
obb+0.257
pering+0.244
ighters+0.236
adders+0.235
Neg logit contributions
 color-0.093
 flavor-0.091
 ornament-0.090
 cube-0.090
 penny-0.084
Token
Token ID198
Feature activation-1.17e+00

Pos logit contributions
 penny+0.020
 ornament+0.020
 flavor+0.019
 peanut+0.019
 cube+0.018
Neg logit contributions
ows-0.022
pering-0.021
arl-0.020
adders-0.020
obb-0.020
Token
Token ID198
Feature activation-1.19e+00

Pos logit contributions
 penny+0.032
 flavor+0.031
 ornament+0.031
 peanut+0.030
 cube+0.029
Neg logit contributions
ows-0.041
pering-0.041
arl-0.039
obb-0.039
oms-0.038
TokenOne
Token ID3198
Feature activation+2.58e-01

Pos logit contributions
 penny+0.027
 ornament+0.027
 flavor+0.025
 cube+0.025
 peanut+0.025
Neg logit contributions
pering-0.046
ows-0.045
arl-0.044
obb-0.044
iving-0.044
Token day
Token ID1110
Feature activation+3.10e-01

Pos logit contributions
pering+0.014
ows+0.014
obb+0.014
arl+0.013
ighters+0.013
Neg logit contributions
 flavor-0.002
 penny-0.002
 cube-0.002
 ornament-0.002
 peanut-0.002
Token I
Token ID314
Feature activation-8.46e-01

Pos logit contributions
pering+0.009
ows+0.009
obb+0.009
arl+0.009
oms+0.009
Neg logit contributions
 flavor-0.006
 penny-0.006
 ornament-0.006
 cube-0.006
 peanut-0.006
Token love
Token ID1842
Feature activation-1.09e+00

Pos logit contributions
 flavor+0.025
 penny+0.025
 ornament+0.024
 peanut+0.023
 cube+0.023
Neg logit contributions
pering-0.029
ows-0.028
arl-0.027
obb-0.026
iving-0.026
Token seeing
Token ID4379
Feature activation+9.32e-01

Pos logit contributions
 penny+0.029
 flavor+0.029
 ornament+0.028
 peanut+0.027
 cube+0.027
Neg logit contributions
ows-0.039
pering-0.039
obb-0.038
arl-0.037
iving-0.036
Token all
Token ID477
Feature activation-9.81e-01

Pos logit contributions
pering+0.036
ows+0.036
obb+0.036
arl+0.036
iving+0.033
Neg logit contributions
 ornament-0.024
 flavor-0.024
 penny-0.023
 cube-0.022
 peanut-0.022
Token the
Token ID262
Feature activation+1.54e+00

Pos logit contributions
 flavor+0.024
 ornament+0.024
 color+0.024
 cube+0.023
 penny+0.022
Neg logit contributions
obb-0.039
ows-0.039
pering-0.039
arl-0.038
ighters-0.035
Token animals
Token ID4695
Feature activation+5.50e+00

Pos logit contributions
pering+0.058
ows+0.058
arl+0.057
obb+0.056
oms+0.053
Neg logit contributions
 flavor-0.042
 ornament-0.040
 penny-0.040
 cube-0.039
 peanut-0.039
Token!"
Token ID2474
Feature activation-8.18e-02

Pos logit contributions
obb+0.204
arl+0.200
pering+0.189
ows+0.188
 announcements+0.182
Neg logit contributions
 ornament-0.144
 flavor-0.144
 penny-0.141
 cube-0.139
 color-0.133
Token
Token ID220
Feature activation-1.11e+00

Pos logit contributions
 penny+0.002
 flavor+0.002
 ornament+0.002
 cube+0.002
 peanut+0.002
Neg logit contributions
ows-0.003
pering-0.003
arl-0.003
obb-0.003
oms-0.003
Token
Token ID198
Feature activation+2.69e-01

Pos logit contributions
 flavor+0.013
 ornament+0.012
 cube+0.011
 penny+0.011
 peanut+0.011
Neg logit contributions
pering-0.054
obb-0.053
 announcements-0.053
aults-0.051
ault-0.050
Token
Token ID198
Feature activation+5.06e-03

Pos logit contributions
ows+0.009
pering+0.009
arl+0.008
obb+0.008
iving+0.008
Neg logit contributions
 penny-0.008
 flavor-0.008
 ornament-0.008
 peanut-0.007
 cube-0.007
TokenHer
Token ID9360
Feature activation-1.32e+00

Pos logit contributions
pering+0.000
ows+0.000
arl+0.000
obb+0.000
iving+0.000
Neg logit contributions
 penny-0.000
 flavor-0.000
 peanut-0.000
 ornament-0.000
 cube-0.000
Token He
Token ID679
Feature activation+8.90e-01

Pos logit contributions
 penny+0.021
 flavor+0.021
 ornament+0.020
 peanut+0.020
 cube+0.019
Neg logit contributions
ows-0.023
pering-0.023
arl-0.022
obb-0.022
iving-0.021
Token was
Token ID373
Feature activation-1.16e+00

Pos logit contributions
ows+0.035
pering+0.035
obb+0.034
arl+0.033
oms+0.032
Neg logit contributions
 penny-0.020
 flavor-0.020
 ornament-0.019
 peanut-0.018
 cube-0.018
Token the
Token ID262
Feature activation+6.01e-01

Pos logit contributions
 penny+0.030
 flavor+0.030
 ornament+0.029
 cube+0.028
 peanut+0.028
Neg logit contributions
ows-0.043
pering-0.042
arl-0.041
obb-0.041
iving-0.039
Token best
Token ID1266
Feature activation-1.69e+00

Pos logit contributions
ows+0.021
pering+0.020
arl+0.019
obb+0.019
oms+0.019
Neg logit contributions
 penny-0.018
 flavor-0.017
 ornament-0.017
 cube-0.017
 peanut-0.016
Token n
Token ID299
Feature activation+2.91e-01

Pos logit contributions
 penny+0.044
 flavor+0.042
 cube+0.042
 ornament+0.042
 peanut+0.037
Neg logit contributions
ows-0.068
pering-0.067
arl-0.064
obb-0.063
 announcements-0.060
Tokenoder
Token ID12342
Feature activation+5.05e+00

Pos logit contributions
ows+0.008
pering+0.008
obb+0.007
 announcements+0.007
arl+0.007
Neg logit contributions
 penny-0.010
 flavor-0.010
 ornament-0.010
 cube-0.010
 peanut-0.010
Token in
Token ID287
Feature activation-7.79e-01

Pos logit contributions
pering+0.167
ows+0.162
obb+0.161
arl+0.159
 announcements+0.154
Neg logit contributions
 flavor-0.160
 cube-0.153
 penny-0.152
 ornament-0.146
 color-0.142
Token the
Token ID262
Feature activation+7.84e-01

Pos logit contributions
 penny+0.021
 flavor+0.021
 ornament+0.020
 cube+0.020
 peanut+0.019
Neg logit contributions
ows-0.032
pering-0.028
obb-0.028
oms-0.027
arl-0.027
Token world
Token ID995
Feature activation+3.20e+00

Pos logit contributions
ows+0.027
pering+0.027
obb+0.025
arl+0.025
iving+0.024
Neg logit contributions
 penny-0.022
 flavor-0.022
 ornament-0.021
 peanut-0.021
 cube-0.021
Token!
Token ID0
Feature activation-7.05e-02

Pos logit contributions
arl+0.117
pering+0.116
obb+0.115
ows+0.111
ighters+0.107
Neg logit contributions
 flavor-0.085
 penny-0.084
 cube-0.083
 ornament-0.083
 peanut-0.076
Token
Token ID198
Feature activation-5.55e-01

Pos logit contributions
 penny+0.002
 flavor+0.002
 ornament+0.002
 peanut+0.002
 cube+0.002
Neg logit contributions
ows-0.002
pering-0.002
arl-0.002
obb-0.002
iving-0.002
Token.
Token ID13
Feature activation-2.02e-01

Pos logit contributions
 penny+0.068
 flavor+0.067
 ornament+0.066
 peanut+0.064
 cube+0.064
Neg logit contributions
pering-0.069
ows-0.069
obb-0.068
arl-0.067
iving-0.065
Token They
Token ID1119
Feature activation+1.97e+00

Pos logit contributions
 penny+0.007
 ornament+0.007
 flavor+0.007
 cube+0.007
 peanut+0.007
Neg logit contributions
ows-0.006
pering-0.006
arl-0.005
obb-0.005
oms-0.005
Token pretend
Token ID16614
Feature activation+8.25e-02

Pos logit contributions
pering+0.074
arl+0.070
iving+0.067
obb+0.066
ows+0.065
Neg logit contributions
 flavor-0.053
 ornament-0.053
 penny-0.052
 peanut-0.052
 nut-0.051
Token they
Token ID484
Feature activation+3.20e+00

Pos logit contributions
pering+0.004
arl+0.004
ows+0.003
obb+0.003
iving+0.003
Neg logit contributions
 flavor-0.002
 penny-0.002
 ornament-0.002
 peanut-0.002
 cube-0.002
Token are
Token ID389
Feature activation-3.88e-01

Pos logit contributions
pering+0.104
arl+0.102
obb+0.095
iving+0.093
ows+0.092
Neg logit contributions
 flavor-0.100
 ornament-0.097
 penny-0.096
 color-0.092
 peanut-0.091
Token animals
Token ID4695
Feature activation+5.43e+00

Pos logit contributions
 color+0.008
 ornament+0.008
 flavor+0.008
 peanut+0.008
 penny+0.007
Neg logit contributions
obb-0.016
arl-0.016
ows-0.015
rig-0.015
oms-0.015
Token or
Token ID393
Feature activation-1.68e-01

Pos logit contributions
obb+0.216
arl+0.208
pering+0.200
ows+0.190
 announcements+0.187
Neg logit contributions
 ornament-0.132
 penny-0.132
 flavor-0.130
 peanut-0.128
 nut-0.124
Token pirates
Token ID27516
Feature activation+2.29e+00

Pos logit contributions
 flavor+0.006
 peanut+0.005
 penny+0.005
 ornament+0.005
 cube+0.005
Neg logit contributions
ows-0.005
pering-0.005
obb-0.005
arl-0.005
iving-0.005
Token or
Token ID393
Feature activation-4.83e-01

Pos logit contributions
obb+0.094
pering+0.089
arl+0.089
rig+0.084
oms+0.083
Neg logit contributions
 flavor-0.051
 penny-0.051
 ornament-0.049
 peanut-0.049
 cube-0.045
Token fair
Token ID3148
Feature activation-2.80e+00

Pos logit contributions
 flavor+0.016
 penny+0.015
 peanut+0.015
 ornament+0.015
 cube+0.015
Neg logit contributions
ows-0.015
pering-0.015
obb-0.014
arl-0.014
iving-0.014
Tokenies
Token ID444
Feature activation+3.46e+00

Pos logit contributions
 flavor+0.054
 color+0.053
 penny+0.051
 ornament+0.049
 cube+0.048
Neg logit contributions
obb-0.123
pering-0.114
arl-0.110
uits-0.109
Run-0.109
Token who
Token ID508
Feature activation-1.49e+00

Pos logit contributions
 flavor+0.007
 ornament+0.007
 penny+0.006
 peanut+0.006
 cube+0.006
Neg logit contributions
pering-0.009
obb-0.008
arl-0.008
ows-0.008
iving-0.008
Token can
Token ID460
Feature activation-1.02e+00

Pos logit contributions
 penny+0.038
 flavor+0.038
 cube+0.037
 ornament+0.037
c+0.034
Neg logit contributions
pering-0.060
obb-0.057
arl-0.056
ows-0.054
iving-0.051
Token spot
Token ID4136
Feature activation-8.41e-01

Pos logit contributions
 flavor+0.028
 penny+0.027
 ornament+0.027
 cube+0.027
 magnet+0.025
Neg logit contributions
pering-0.036
ows-0.036
arl-0.035
obb-0.035
iving-0.034
Token the
Token ID262
Feature activation+2.15e+00

Pos logit contributions
 flavor+0.022
 penny+0.021
 ornament+0.021
 peanut+0.021
 cube+0.020
Neg logit contributions
pering-0.031
obb-0.031
arl-0.030
iving-0.030
ows-0.030
Token most
Token ID749
Feature activation-1.76e-01

Pos logit contributions
ows+0.081
pering+0.078
arl+0.075
obb+0.073
iving+0.073
Neg logit contributions
 penny-0.061
 flavor-0.059
 ornament-0.059
 cube-0.056
 peanut-0.055
Token animals
Token ID4695
Feature activation+5.46e+00

Pos logit contributions
 flavor+0.005
 ornament+0.005
 penny+0.005
 cube+0.004
 peanut+0.004
Neg logit contributions
arl-0.007
pering-0.007
ows-0.007
obb-0.006
attering-0.006
Token on
Token ID319
Feature activation-2.68e+00

Pos logit contributions
pering+0.180
obb+0.178
arl+0.173
ows+0.172
iving+0.162
Neg logit contributions
 flavor-0.161
 penny-0.160
 ornament-0.158
 cube-0.150
 peanut-0.150
Token the
Token ID262
Feature activation+5.83e-01

Pos logit contributions
 ornament+0.066
 penny+0.066
 flavor+0.066
 color+0.059
 peanut+0.057
Neg logit contributions
ows-0.111
pering-0.106
arl-0.104
obb-0.103
iving-0.101
Token way
Token ID835
Feature activation-1.11e+00

Pos logit contributions
ows+0.021
arl+0.021
oms+0.021
pering+0.020
iving+0.020
Neg logit contributions
 ornament-0.015
 penny-0.015
 flavor-0.015
 cube-0.014
 peanut-0.014
Token,"
Token ID553
Feature activation-1.33e-01

Pos logit contributions
 ornament+0.026
 penny+0.025
 flavor+0.025
 cube+0.025
 color+0.023
Neg logit contributions
obb-0.046
pering-0.042
arl-0.041
 announcements-0.040
rig-0.040
Token dad
Token ID9955
Feature activation+3.88e-01

Pos logit contributions
 ornament+0.005
 penny+0.005
 cube+0.005
 flavor+0.005
orn+0.005
Neg logit contributions
 announcements-0.003
ows-0.003
ila-0.003
 men-0.002
obb-0.002
Token Her
Token ID2332
Feature activation-1.74e+00

Pos logit contributions
pering+0.001
obb+0.001
ows+0.001
 announcements+0.001
aults+0.001
Neg logit contributions
 penny-0.001
 peanut-0.000
 flavor-0.000
 mint-0.000
 cube-0.000
Token mom
Token ID1995
Feature activation-1.41e+00

Pos logit contributions
 flavor+0.052
 ornament+0.050
 penny+0.050
 peanut+0.049
 cube+0.048
Neg logit contributions
ows-0.054
obb-0.050
pering-0.050
arl-0.049
oms-0.048
Tokenmy
Token ID1820
Feature activation-1.38e+00

Pos logit contributions
 penny+0.024
 flavor+0.023
 ornament+0.022
 peanut+0.021
 nut+0.020
Neg logit contributions
ows-0.064
pering-0.060
oms-0.058
arl-0.058
iving-0.057
Token left
Token ID1364
Feature activation-3.95e-01

Pos logit contributions
 flavor+0.031
 penny+0.031
 ornament+0.030
 cube+0.029
 peanut+0.029
Neg logit contributions
pering-0.055
ows-0.054
obb-0.053
arl-0.053
iving-0.051
Token the
Token ID262
Feature activation+2.06e+00

Pos logit contributions
 penny+0.011
 flavor+0.010
 ornament+0.010
 peanut+0.010
 cube+0.009
Neg logit contributions
ows-0.015
pering-0.014
obb-0.014
iving-0.014
arl-0.014
Token little
Token ID1310
Feature activation+2.24e+00

Pos logit contributions
pering+0.072
ows+0.071
obb+0.070
arl+0.068
iving+0.066
Neg logit contributions
 flavor-0.052
 penny-0.049
 peanut-0.048
 ornament-0.047
 cube-0.046
Token girl
Token ID2576
Feature activation+1.08e+00

Pos logit contributions
ows+0.083
pering+0.081
arl+0.080
obb+0.079
adders+0.075
Neg logit contributions
 penny-0.064
 flavor-0.060
 ornament-0.060
 cube-0.059
 peanut-0.058
Token alone
Token ID3436
Feature activation+2.25e+00

Pos logit contributions
arl+0.040
pering+0.040
ows+0.040
obb+0.040
iving+0.038
Neg logit contributions
 penny-0.027
 flavor-0.027
 ornament-0.026
 cube-0.026
 peanut-0.026
Token with
Token ID351
Feature activation-1.91e+00

Pos logit contributions
arl+0.094
obb+0.093
ighters+0.091
ows+0.090
 announcements+0.090
Neg logit contributions
 penny-0.048
 flavor-0.043
 cube-0.043
 ornament-0.041
 color-0.039
Token the
Token ID262
Feature activation+3.65e-01

Pos logit contributions
 penny+0.058
 flavor+0.058
 ornament+0.056
 cube+0.055
 peanut+0.054
Neg logit contributions
ows-0.061
pering-0.060
obb-0.057
arl-0.057
oms-0.055
Token box
Token ID3091
Feature activation-3.08e+00

Pos logit contributions
pering+0.014
ows+0.014
arl+0.014
obb+0.014
iving+0.013
Neg logit contributions
 penny-0.009
 flavor-0.008
 ornament-0.008
 cube-0.008
 peanut-0.008
Token tree
Token ID5509
Feature activation-1.19e+00

Pos logit contributions
pering+0.056
ows+0.056
obb+0.054
arl+0.053
iving+0.052
Neg logit contributions
 flavor-0.035
 penny-0.035
 ornament-0.034
 cube-0.033
 peanut-0.033
Token.
Token ID13
Feature activation+4.87e-01

Pos logit contributions
 penny+0.034
 flavor+0.033
 ornament+0.033
 cube+0.033
 peanut+0.032
Neg logit contributions
obb-0.040
arl-0.039
pering-0.039
ows-0.038
 announcements-0.037
Token The
Token ID383
Feature activation+1.49e+00

Pos logit contributions
ows+0.021
pering+0.021
aults+0.021
arl+0.021
 announcements+0.021
Neg logit contributions
 peanut-0.009
 penny-0.008
 flavor-0.008
 cube-0.008
 nut-0.008
Token tree
Token ID5509
Feature activation-1.65e+00

Pos logit contributions
pering+0.067
ows+0.067
obb+0.066
arl+0.065
iving+0.064
Neg logit contributions
 penny-0.023
 flavor-0.023
 ornament-0.022
 cube-0.021
 peanut-0.021
Token yelled
Token ID22760
Feature activation+2.38e+00

Pos logit contributions
 flavor+0.042
 penny+0.042
 ornament+0.040
 cube+0.039
 peanut+0.039
Neg logit contributions
ows-0.060
pering-0.058
obb-0.056
oms-0.054
iving-0.054
Token,
Token ID11
Feature activation+1.57e+00

Pos logit contributions
arl+0.089
 announcements+0.089
pering+0.089
ows+0.088
obb+0.088
Neg logit contributions
 penny-0.053
 peanut-0.052
 cube-0.050
 flavor-0.049
 ornament-0.048
Token "
Token ID366
Feature activation-1.90e-01

Pos logit contributions
ows+0.064
obb+0.062
iving+0.061
pering+0.061
arl+0.061
Neg logit contributions
 penny-0.033
 flavor-0.030
 peanut-0.030
 cube-0.030
 ornament-0.030
TokenNo
Token ID2949
Feature activation-5.48e-01

Pos logit contributions
 penny+0.006
 flavor+0.006
 ornament+0.006
 cube+0.006
 peanut+0.006
Neg logit contributions
pering-0.006
ows-0.006
obb-0.005
arl-0.005
iving-0.005
Token!
Token ID0
Feature activation+9.81e-01

Pos logit contributions
 flavor+0.016
 penny+0.015
 peanut+0.014
 ornament+0.014
 cube+0.014
Neg logit contributions
ows-0.020
pering-0.020
arl-0.019
obb-0.019
ighters-0.018
Token Stop
Token ID13707
Feature activation+1.75e+00

Pos logit contributions
ows+0.036
pering+0.036
obb+0.035
 announcements+0.034
arl+0.033
Neg logit contributions
 penny-0.025
 flavor-0.025
 ornament-0.024
 peanut-0.024
 cube-0.023
Token!
Token ID0
Feature activation+7.42e-01

Pos logit contributions
ows+0.068
arl+0.064
obb+0.063
oms+0.062
adders+0.062
Neg logit contributions
 penny-0.047
 peanut-0.045
 flavor-0.045
 ornament-0.044
 cube-0.042
Token to
Token ID284
Feature activation+1.21e+00

Pos logit contributions
pering+0.027
obb+0.027
ows+0.027
arl+0.027
 announcements+0.025
Neg logit contributions
 flavor-0.012
 penny-0.011
 ornament-0.011
 cube-0.010
 peanut-0.010
Token draw
Token ID3197
Feature activation-6.98e-02

Pos logit contributions
ows+0.042
pering+0.042
obb+0.040
arl+0.040
iving+0.038
Neg logit contributions
 penny-0.033
 flavor-0.033
 ornament-0.032
 peanut-0.031
 cube-0.031
Token on
Token ID319
Feature activation-2.36e+00

Pos logit contributions
 flavor+0.002
 ornament+0.002
 penny+0.002
 peanut+0.002
 cube+0.002
Neg logit contributions
pering-0.002
arl-0.002
ows-0.002
obb-0.002
iving-0.002
Token it
Token ID340
Feature activation-2.80e+00

Pos logit contributions
 flavor+0.065
 penny+0.064
 ornament+0.063
 peanut+0.061
 cube+0.060
Neg logit contributions
ows-0.085
pering-0.084
arl-0.081
obb-0.080
iving-0.079
Token.
Token ID13
Feature activation-1.36e-01

Pos logit contributions
 flavor+0.085
 ornament+0.084
 penny+0.083
 cube+0.079
 peanut+0.079
Neg logit contributions
pering-0.091
arl-0.088
ows-0.088
obb-0.087
 announcements-0.082
Token She
Token ID1375
Feature activation+1.11e+00

Pos logit contributions
 flavor+0.003
 penny+0.003
 ornament+0.003
 peanut+0.003
 cube+0.003
Neg logit contributions
pering-0.005
ows-0.005
obb-0.005
arl-0.005
iving-0.005
Token took
Token ID1718
Feature activation+4.65e-01

Pos logit contributions
ows+0.040
pering+0.038
obb+0.038
oms+0.037
arl+0.036
Neg logit contributions
 penny-0.028
 flavor-0.028
 ornament-0.027
 cube-0.026
 peanut-0.026
Token her
Token ID607
Feature activation-1.07e+00

Pos logit contributions
ows+0.015
pering+0.015
obb+0.014
arl+0.014
oms+0.013
Neg logit contributions
 penny-0.014
 flavor-0.014
 ornament-0.014
 cube-0.013
 peanut-0.013
Token cr
Token ID1067
Feature activation-3.56e+00

Pos logit contributions
 flavor+0.020
 penny+0.019
 ornament+0.019
 peanut+0.018
 cube+0.018
Neg logit contributions
ows-0.045
pering-0.044
obb-0.043
oms-0.043
arl-0.042
Tokenay
Token ID323
Feature activation-3.11e+00

Pos logit contributions
 penny+0.121
 flavor+0.117
 ornament+0.113
 peanut+0.112
 cube+0.111
Neg logit contributions
ows-0.110
arl-0.102
pering-0.098
iving-0.097
obb-0.096
Tokenons
Token ID684
Feature activation-1.32e+00

Pos logit contributions
 penny+0.075
 flavor+0.071
 ornament+0.070
 nut+0.066
 peanut+0.064
Neg logit contributions
ows-0.120
oms-0.115
obb-0.111
arl-0.110
adders-0.109
Token
Token ID198
Feature activation-4.67e-01

Pos logit contributions
ows+0.003
obb+0.003
pering+0.003
arl+0.003
iving+0.003
Neg logit contributions
 flavor-0.002
 penny-0.002
 peanut-0.002
 cube-0.001
 ornament-0.001
Token
Token ID198
Feature activation-5.03e-01

Pos logit contributions
 flavor+0.009
 penny+0.008
 ornament+0.008
 cube+0.008
 peanut+0.008
Neg logit contributions
ows-0.020
pering-0.020
obb-0.020
iving-0.019
arl-0.019
TokenThe
Token ID464
Feature activation+1.08e+00

Pos logit contributions
 penny+0.013
 flavor+0.013
 ornament+0.012
 cube+0.012
 peanut+0.012
Neg logit contributions
ows-0.019
pering-0.017
obb-0.017
oms-0.017
arl-0.017
Token goat
Token ID26917
Feature activation+9.65e-01

Pos logit contributions
ows+0.045
pering+0.040
obb+0.040
arl+0.040
iving+0.039
Neg logit contributions
 penny-0.030
 peanut-0.027
 ornament-0.027
 flavor-0.026
 cube-0.026
Token felt
Token ID2936
Feature activation+2.17e+00

Pos logit contributions
arl+0.043
pering+0.042
ows+0.041
obb+0.040
iving+0.040
Neg logit contributions
 penny-0.018
 flavor-0.018
 peanut-0.017
 ornament-0.017
 cube-0.017
Token sad
Token ID6507
Feature activation+9.79e-01

Pos logit contributions
ows+0.079
arl+0.076
iving+0.074
pering+0.074
oms+0.072
Neg logit contributions
 penny-0.059
 peanut-0.057
 flavor-0.055
 nut-0.054
 mint-0.052
Token and
Token ID290
Feature activation+1.48e+00

Pos logit contributions
pering+0.037
obb+0.037
 announcements+0.037
adders+0.036
adies+0.036
Neg logit contributions
 penny-0.022
 flavor-0.021
 cube-0.021
 ornament-0.020
 peanut-0.020
Token didn
Token ID1422
Feature activation+4.36e+00

Pos logit contributions
ows+0.050
pering+0.047
arl+0.047
iving+0.046
obb+0.045
Neg logit contributions
 penny-0.045
 peanut-0.044
 cube-0.042
 flavor-0.042
 ornament-0.042
Token't
Token ID470
Feature activation+1.03e+00

Pos logit contributions
ows+0.190
pering+0.179
 announcements+0.175
iving+0.175
arl+0.174
Neg logit contributions
 penny-0.087
 flavor-0.080
 ornament-0.080
 cube-0.075
 peanut-0.073
Token know
Token ID760
Feature activation-1.70e-01

Pos logit contributions
ows+0.026
pering+0.026
obb+0.024
arl+0.024
oms+0.023
Neg logit contributions
 flavor-0.038
 penny-0.038
 ornament-0.037
 peanut-0.037
 cube-0.036
Token what
Token ID644
Feature activation+6.89e-01

Pos logit contributions
 flavor+0.005
 ornament+0.005
 penny+0.005
 cube+0.005
 peanut+0.005
Neg logit contributions
arl-0.006
pering-0.006
obb-0.006
ows-0.006
iving-0.005
Token hair
Token ID4190
Feature activation-2.40e+00

Pos logit contributions
 penny+0.044
 flavor+0.044
 ornament+0.043
 peanut+0.042
 cube+0.041
Neg logit contributions
ows-0.054
pering-0.054
obb-0.051
arl-0.051
iving-0.050
Token again
Token ID757
Feature activation+6.41e-01

Pos logit contributions
 penny+0.075
 flavor+0.075
 ornament+0.073
 peanut+0.070
 cube+0.070
Neg logit contributions
pering-0.076
ows-0.075
arl-0.072
obb-0.071
iving-0.069
Token and
Token ID290
Feature activation+1.11e+00

Pos logit contributions
pering+0.018
ows+0.018
obb+0.017
arl+0.016
iving+0.016
Neg logit contributions
 penny-0.022
 flavor-0.021
 ornament-0.021
 cube-0.021
 peanut-0.020
Token always
Token ID1464
Feature activation-5.58e-01

Pos logit contributions
pering+0.036
ows+0.036
obb+0.036
iving+0.034
oms+0.033
Neg logit contributions
 flavor-0.029
 penny-0.029
 ornament-0.029
 cube-0.027
 peanut-0.027
Token felt
Token ID2936
Feature activation+2.53e+00

Pos logit contributions
 penny+0.016
 ornament+0.015
 peanut+0.015
 flavor+0.015
 possession+0.014
Neg logit contributions
ows-0.016
 realize-0.016
pering-0.015
obb-0.015
oms-0.014
Token guilty
Token ID6717
Feature activation+2.36e+00

Pos logit contributions
ows+0.082
pering+0.081
arl+0.077
obb+0.076
iving+0.075
Neg logit contributions
 penny-0.077
 flavor-0.076
 ornament-0.074
 peanut-0.073
 cube-0.072
Token for
Token ID329
Feature activation+1.58e+00

Pos logit contributions
ows+0.090
pering+0.089
arl+0.088
obb+0.087
 announcements+0.086
Neg logit contributions
 penny-0.058
 ornament-0.055
 flavor-0.055
 cube-0.054
 peanut-0.050
Token what
Token ID644
Feature activation+6.14e-01

Pos logit contributions
ows+0.054
pering+0.054
obb+0.052
arl+0.051
iving+0.050
Neg logit contributions
 penny-0.044
 flavor-0.044
 ornament-0.043
 peanut-0.041
 cube-0.041
Token he
Token ID339
Feature activation+2.23e+00

Pos logit contributions
ows+0.014
pering+0.014
obb+0.014
 men+0.014
 announcements+0.014
Neg logit contributions
 ornament-0.020
 penny-0.019
 flavor-0.019
 peanut-0.019
c-0.018
Token had
Token ID550
Feature activation-2.81e+00

Pos logit contributions
ows+0.065
obb+0.064
pering+0.063
arl+0.059
 realize+0.058
Neg logit contributions
 ornament-0.069
 penny-0.069
 flavor-0.065
 cube-0.065
 peanut-0.064
Token done
Token ID1760
Feature activation-1.93e+00

Pos logit contributions
 ornament+0.087
 penny+0.086
 flavor+0.084
 peanut+0.083
 cube+0.082
Neg logit contributions
ows-0.085
pering-0.082
obb-0.081
iving-0.081
arl-0.079
Token made
Token ID925
Feature activation-9.34e-01

Pos logit contributions
 flavor+0.004
 penny+0.004
 ornament+0.004
 peanut+0.004
 cube+0.004
Neg logit contributions
pering-0.007
ows-0.007
arl-0.007
obb-0.007
 announcements-0.007
Token her
Token ID607
Feature activation-5.13e-01

Pos logit contributions
 flavor+0.025
 ornament+0.024
 penny+0.023
 peanut+0.022
 color+0.022
Neg logit contributions
pering-0.035
obb-0.034
arl-0.034
ows-0.033
 announcements-0.032
Token so
Token ID523
Feature activation-1.72e+00

Pos logit contributions
 penny+0.014
 flavor+0.014
 ornament+0.013
 peanut+0.013
 cube+0.013
Neg logit contributions
ows-0.018
pering-0.018
obb-0.017
arl-0.017
iving-0.017
Token excited
Token ID6568
Feature activation+2.65e-02

Pos logit contributions
 penny+0.044
 flavor+0.043
 ornament+0.042
 cube+0.042
 peanut+0.042
Neg logit contributions
pering-0.066
ows-0.065
arl-0.061
chers-0.060
iving-0.059
Token!
Token ID0
Feature activation-4.01e-01

Pos logit contributions
pering+0.001
ows+0.001
obb+0.001
arl+0.001
adders+0.001
Neg logit contributions
 flavor-0.001
 penny-0.001
 ornament-0.001
 peanut-0.001
 cube-0.001
Token There
Token ID1318
Feature activation+3.07e-02

Pos logit contributions
 penny+0.014
 flavor+0.014
 peanut+0.013
 cube+0.013
 ornament+0.013
Neg logit contributions
ows-0.011
pering-0.011
arl-0.010
obb-0.010
adders-0.010
Token was
Token ID373
Feature activation-1.89e-01

Pos logit contributions
ows+0.001
pering+0.001
oms+0.001
obb+0.001
adders+0.001
Neg logit contributions
 penny-0.001
 flavor-0.001
 peanut-0.001
 ornament-0.001
 cube-0.001
Token a
Token ID257
Feature activation+2.05e+00

Pos logit contributions
 flavor+0.005
 ornament+0.005
 penny+0.005
 peanut+0.005
 cube+0.004
Neg logit contributions
pering-0.007
arl-0.007
ows-0.007
obb-0.007
iving-0.007
Token little
Token ID1310
Feature activation+1.50e+00

Pos logit contributions
pering+0.051
ows+0.049
arl+0.048
obb+0.047
 announcements+0.046
Neg logit contributions
 flavor-0.071
 penny-0.069
 ornament-0.069
 cube-0.066
 peanut-0.066
Token puppy
Token ID26188
Feature activation+5.00e-02

Pos logit contributions
pering+0.049
ows+0.048
oms+0.046
iving+0.045
arl+0.045
Neg logit contributions
 flavor-0.041
 penny-0.040
 ornament-0.038
 peanut-0.038
 cube-0.037
Token outside
Token ID2354
Feature activation-2.10e-01

Pos logit contributions
obb+0.002
ows+0.002
arl+0.002
pering+0.002
adders+0.002
Neg logit contributions
 penny-0.001
 ornament-0.001
 peanut-0.001
 flavor-0.001
 cube-0.001
Token and
Token ID290
Feature activation-2.16e+00

Pos logit contributions
 flavor+0.021
 penny+0.021
 ornament+0.020
 peanut+0.020
 cube+0.020
Neg logit contributions
pering-0.040
ows-0.040
arl-0.039
obb-0.038
oms-0.037
Token her
Token ID607
Feature activation-2.25e+00

Pos logit contributions
 cube+0.075
 penny+0.074
 flavor+0.073
c+0.070
 dime+0.070
Neg logit contributions
 realize-0.047
 announcements-0.046
 Super-0.046
arl-0.046
obb-0.046
Token mom
Token ID1995
Feature activation-1.86e+00

Pos logit contributions
 flavor+0.062
 penny+0.062
 ornament+0.060
 peanut+0.059
 cube+0.058
Neg logit contributions
ows-0.076
pering-0.074
arl-0.072
obb-0.072
iving-0.069
Tokenmy
Token ID1820
Feature activation-1.85e+00

Pos logit contributions
 penny+0.048
 ornament+0.045
 possession+0.044
 ruby+0.044
 flavor+0.043
Neg logit contributions
ows-0.062
iving-0.061
arl-0.059
pering-0.059
 realize-0.058
Token went
Token ID1816
Feature activation+2.41e+00

Pos logit contributions
 penny+0.051
 flavor+0.050
 ornament+0.049
 cube+0.048
 peanut+0.046
Neg logit contributions
ows-0.063
pering-0.061
obb-0.059
arl-0.058
iving-0.058
Token outside
Token ID2354
Feature activation-6.06e-02

Pos logit contributions
pering+0.093
ows+0.093
arl+0.089
oms+0.087
iving+0.086
Neg logit contributions
 flavor-0.059
 penny-0.057
 ornament-0.056
 peanut-0.053
 cube-0.053
Token to
Token ID284
Feature activation-4.34e-01

Pos logit contributions
 penny+0.001
 flavor+0.001
 ornament+0.001
 peanut+0.001
 cube+0.001
Neg logit contributions
ows-0.003
pering-0.003
arl-0.003
obb-0.003
iving-0.002
Token play
Token ID711
Feature activation+1.40e+00

Pos logit contributions
 penny+0.014
 flavor+0.013
 ornament+0.013
 dime+0.013
 cube+0.012
Neg logit contributions
pering-0.011
 realize-0.011
oms-0.011
ows-0.011
arl-0.011
Token on
Token ID319
Feature activation-2.28e+00

Pos logit contributions
ows+0.038
pering+0.037
obb+0.036
arl+0.035
iving+0.034
Neg logit contributions
 penny-0.049
 flavor-0.048
 ornament-0.047
 peanut-0.046
 cube-0.046
Token the
Token ID262
Feature activation+5.49e-01

Pos logit contributions
 penny+0.083
 flavor+0.083
 ornament+0.081
 cube+0.080
 peanut+0.079
Neg logit contributions
pering-0.056
ows-0.055
obb-0.052
oms-0.050
arl-0.050
Token lawn
Token ID21133
Feature activation-9.93e-01

Pos logit contributions
ows+0.017
pering+0.017
arl+0.016
obb+0.016
oms+0.016
Neg logit contributions
 penny-0.017
 flavor-0.017
 ornament-0.017
 cube-0.017
 peanut-0.017
Token smiled
Token ID13541
Feature activation-1.16e-01

Pos logit contributions
ows+0.007
pering+0.006
obb+0.006
arl+0.006
iving+0.006
Neg logit contributions
 flavor-0.005
 penny-0.005
 ornament-0.005
 cube-0.004
 peanut-0.004
Token and
Token ID290
Feature activation-1.93e-03

Pos logit contributions
 penny+0.004
 flavor+0.004
 ornament+0.003
 peanut+0.003
 cube+0.003
Neg logit contributions
ows-0.004
pering-0.004
obb-0.003
arl-0.003
adders-0.003
Token flew
Token ID13112
Feature activation+3.65e+00

Pos logit contributions
 flavor+0.000
 ornament+0.000
 penny+0.000
 cube+0.000
 peanut+0.000
Neg logit contributions
ows-0.000
pering-0.000
obb-0.000
arl-0.000
iving-0.000
Token away
Token ID1497
Feature activation-5.15e-01

Pos logit contributions
ows+0.139
pering+0.137
obb+0.133
arl+0.131
oms+0.129
Neg logit contributions
 penny-0.090
 flavor-0.087
 ornament-0.086
 peanut-0.083
 cube-0.083
Token,
Token ID11
Feature activation+1.39e+00

Pos logit contributions
 penny+0.014
 flavor+0.014
 ornament+0.014
 cube+0.013
 peanut+0.013
Neg logit contributions
ows-0.018
pering-0.018
arl-0.017
obb-0.017
iving-0.017
Token happy
Token ID3772
Feature activation-4.76e-01

Pos logit contributions
pering+0.041
ows+0.040
obb+0.037
arl+0.037
iving+0.036
Neg logit contributions
 flavor-0.046
 penny-0.045
 ornament-0.044
 cube-0.043
 peanut-0.042
Token to
Token ID284
Feature activation+1.38e+00

Pos logit contributions
 flavor+0.013
 penny+0.013
 ornament+0.013
 cube+0.012
 peanut+0.012
Neg logit contributions
pering-0.016
ows-0.016
arl-0.015
obb-0.015
iving-0.015
Token help
Token ID1037
Feature activation+1.54e+00

Pos logit contributions
pering+0.039
arl+0.037
 realize+0.036
ows+0.034
obb+0.034
Neg logit contributions
 flavor-0.047
 penny-0.047
 ornament-0.046
 cube-0.044
 peanut-0.043
Token his
Token ID465
Feature activation+2.45e-02

Pos logit contributions
pering+0.049
ows+0.048
arl+0.044
iving+0.044
obb+0.043
Neg logit contributions
 penny-0.046
 flavor-0.045
 cube-0.044
 ornament-0.044
 peanut-0.042
Token friend
Token ID1545
Feature activation+1.17e+00

Pos logit contributions
pering+0.001
ows+0.001
arl+0.001
 sons+0.001
iving+0.001
Neg logit contributions
 flavor-0.001
 penny-0.001
 peanut-0.001
 cube-0.001
 ornament-0.001
Token.
Token ID13
Feature activation+1.34e-01

Pos logit contributions
obb+0.048
arl+0.047
pering+0.044
oms+0.044
 announcements+0.043
Neg logit contributions
 ornament-0.030
 flavor-0.029
 penny-0.029
 cube-0.029
 peanut-0.029
Token and
Token ID290
Feature activation-8.83e-01

Pos logit contributions
 penny+0.142
 flavor+0.137
 ornament+0.137
 cube+0.136
 peanut+0.132
Neg logit contributions
pering-0.153
obb-0.149
ows-0.147
arl-0.144
 announcements-0.143
Token says
Token ID1139
Feature activation-6.28e-01

Pos logit contributions
 flavor+0.025
 penny+0.024
 peanut+0.024
 ornament+0.023
 pencil+0.023
Neg logit contributions
pering-0.033
arl-0.032
ows-0.031
obb-0.030
iving-0.029
Token,
Token ID11
Feature activation+1.69e-01

Pos logit contributions
 penny+0.020
 flavor+0.020
 ornament+0.020
 cube+0.019
 peanut+0.019
Neg logit contributions
ows-0.018
oms-0.017
pering-0.017
adders-0.017
obb-0.017
Token "
Token ID366
Feature activation-1.01e+00

Pos logit contributions
ows+0.006
pering+0.006
obb+0.005
arl+0.005
iving+0.005
Neg logit contributions
 penny-0.005
 flavor-0.005
 ornament-0.005
 peanut-0.005
 cube-0.005
TokenThis
Token ID1212
Feature activation-2.18e+00

Pos logit contributions
 ornament+0.031
 penny+0.031
 cube+0.031
 nut+0.030
 magnet+0.029
Neg logit contributions
aults-0.026
Run-0.025
iving-0.025
 stations-0.025
pering-0.024
Token can
Token ID460
Feature activation-4.13e-01

Pos logit contributions
 flavor+0.059
 penny+0.059
 peanut+0.058
 cube+0.056
 ornament+0.056
Neg logit contributions
ows-0.075
obb-0.068
pering-0.068
oms-0.067
arl-0.067
Token be
Token ID307
Feature activation-1.52e+00

Pos logit contributions
 penny+0.012
 flavor+0.012
 peanut+0.011
 ornament+0.011
 cube+0.011
Neg logit contributions
ows-0.014
pering-0.013
obb-0.013
oms-0.012
arl-0.012
Token our
Token ID674
Feature activation-1.92e+00

Pos logit contributions
 penny+0.046
 flavor+0.045
 ornament+0.044
 cube+0.043
 peanut+0.042
Neg logit contributions
ows-0.050
pering-0.048
obb-0.046
arl-0.045
adders-0.044
Token roof
Token ID9753
Feature activation-5.02e-01

Pos logit contributions
 flavor+0.045
 penny+0.045
 ornament+0.043
 peanut+0.042
 cube+0.042
Neg logit contributions
ows-0.074
pering-0.073
obb-0.070
arl-0.070
iving-0.068
Token.
Token ID13
Feature activation-5.24e-01

Pos logit contributions
 flavor+0.015
 ornament+0.015
 cube+0.015
 penny+0.014
 color+0.014
Neg logit contributions
pering-0.017
obb-0.016
 announcements-0.016
arl-0.016
ighters-0.015
Token We
Token ID775
Feature activation+1.34e-01

Pos logit contributions
 penny+0.014
 flavor+0.014
 ornament+0.014
 peanut+0.013
 cube+0.013
Neg logit contributions
ows-0.018
pering-0.018
arl-0.017
obb-0.017
iving-0.017
Token They
Token ID1119
Feature activation+2.25e+00

Pos logit contributions
ows+0.012
pering+0.012
obb+0.011
arl+0.011
iving+0.011
Neg logit contributions
 flavor-0.012
 penny-0.012
 ornament-0.012
 peanut-0.012
 cube-0.012
Token wished
Token ID16555
Feature activation+1.27e+00

Pos logit contributions
pering+0.089
arl+0.086
ows+0.084
iving+0.084
oms+0.083
Neg logit contributions
 penny-0.055
 flavor-0.054
 peanut-0.053
 ornament-0.051
 cube-0.050
Token they
Token ID484
Feature activation+3.64e+00

Pos logit contributions
pering+0.038
ows+0.038
arl+0.037
obb+0.037
iving+0.035
Neg logit contributions
 flavor-0.041
 penny-0.041
 ornament-0.039
 cube-0.039
 peanut-0.039
Token had
Token ID550
Feature activation-1.84e+00

Pos logit contributions
ows+0.158
pering+0.157
obb+0.152
arl+0.151
iving+0.148
Neg logit contributions
 penny-0.067
 flavor-0.067
 ornament-0.064
 peanut-0.061
 cube-0.061
Token not
Token ID407
Feature activation+7.15e-01

Pos logit contributions
 ornament+0.058
 penny+0.055
 cube+0.055
orn+0.053
 magnet+0.052
Neg logit contributions
ows-0.054
pering-0.051
obb-0.051
 announcements-0.050
adders-0.050
Token gone
Token ID3750
Feature activation-2.79e-01

Pos logit contributions
ows+0.023
pering+0.022
adders+0.022
iving+0.021
obb+0.021
Neg logit contributions
 ornament-0.021
 penny-0.020
 flavor-0.019
 cube-0.019
 magnet-0.018
Token in
Token ID287
Feature activation-3.81e-01

Pos logit contributions
 penny+0.007
 flavor+0.007
 ornament+0.007
 peanut+0.006
 cube+0.006
Neg logit contributions
ows-0.011
pering-0.011
arl-0.010
obb-0.010
iving-0.010
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
 penny+0.011
 flavor+0.011
 ornament+0.010
 peanut+0.010
 cube+0.010
Neg logit contributions
ows-0.014
pering-0.013
arl-0.013
obb-0.013
iving-0.013
Token chamber
Token ID11847
Feature activation+1.58e+00

Pos logit contributions
pering+0.041
obb+0.041
ows+0.040
arl+0.039
iving+0.037
Neg logit contributions
 flavor-0.042
 penny-0.041
 peanut-0.039
 ornament-0.039
 cube-0.038
Token.
Token ID13
Feature activation+5.90e-01

Pos logit contributions
arl+0.065
obb+0.063
pering+0.062
ows+0.061
 announcements+0.060
Neg logit contributions
 penny-0.036
 ornament-0.036
 cube-0.036
 flavor-0.035
 peanut-0.032
Token They
Token ID1119
Feature activation+2.42e+00

Pos logit contributions
ows+0.019
pering+0.019
obb+0.018
arl+0.018
iving+0.017
Neg logit contributions
 flavor-0.018
 penny-0.017
 ornament-0.017
 peanut-0.017
 cube-0.017
Token
Token ID198
Feature activation-1.94e-01

Pos logit contributions
ows+0.011
pering+0.011
obb+0.011
arl+0.011
iving+0.010
Neg logit contributions
 penny-0.011
 flavor-0.011
 ornament-0.011
 peanut-0.011
 cube-0.011
Token
Token ID198
Feature activation-2.77e-01

Pos logit contributions
 flavor+0.004
 penny+0.004
 ornament+0.004
 cube+0.004
 peanut+0.004
Neg logit contributions
ows-0.008
pering-0.008
obb-0.007
arl-0.007
iving-0.007
TokenNow
Token ID3844
Feature activation+1.93e+00

Pos logit contributions
 flavor+0.008
 penny+0.008
 cube+0.008
 ornament+0.007
 peanut+0.007
Neg logit contributions
ows-0.010
pering-0.009
obb-0.009
arl-0.009
oms-0.009
Token,
Token ID11
Feature activation+6.70e-01

Pos logit contributions
pering+0.084
arl+0.083
ows+0.081
obb+0.080
 announcements+0.077
Neg logit contributions
 penny-0.041
 peanut-0.039
 flavor-0.039
 cube-0.036
 ornament-0.034
Token Tim
Token ID5045
Feature activation-4.65e-01

Pos logit contributions
pering+0.026
ows+0.026
obb+0.025
arl+0.025
oms+0.024
Neg logit contributions
 flavor-0.017
 penny-0.017
 peanut-0.016
 cube-0.016
 ornament-0.016
Token's
Token ID338
Feature activation-4.31e+00

Pos logit contributions
 penny+0.011
 cube+0.010
 peanut+0.010
 ornament+0.010
 flavor+0.010
Neg logit contributions
pering-0.019
arl-0.019
obb-0.018
 announcements-0.018
ows-0.018
Token room
Token ID2119
Feature activation-2.70e+00

Pos logit contributions
 penny+0.103
 ornament+0.102
 flavor+0.098
 cube+0.093
 peanut+0.089
Neg logit contributions
pering-0.175
ows-0.173
arl-0.164
obb-0.162
 announcements-0.160
Token was
Token ID373
Feature activation+1.09e+00

Pos logit contributions
 flavor+0.034
 penny+0.034
 cube+0.032
 ornament+0.031
 peanut+0.029
Neg logit contributions
pering-0.140
arl-0.135
ows-0.131
iving-0.130
obb-0.129
Token clean
Token ID3424
Feature activation-1.32e+00

Pos logit contributions
ows+0.038
pering+0.038
obb+0.036
arl+0.036
iving+0.035
Neg logit contributions
 penny-0.030
 flavor-0.030
 ornament-0.029
 peanut-0.028
 cube-0.028
Token,
Token ID11
Feature activation+1.96e+00

Pos logit contributions
 ornament+0.031
 flavor+0.030
 cube+0.030
 penny+0.030
 magnet+0.028
Neg logit contributions
arl-0.054
pering-0.053
adders-0.053
ighters-0.052
oms-0.051
Token and
Token ID290
Feature activation+9.53e-01

Pos logit contributions
ows+0.061
pering+0.061
arl+0.059
obb+0.058
oms+0.057
Neg logit contributions
 penny-0.061
 flavor-0.061
 ornament-0.060
 peanut-0.059
 cube-0.059
Token He
Token ID679
Feature activation+6.88e-01

Pos logit contributions
 flavor+0.005
 peanut+0.005
 penny+0.005
 ornament+0.005
 cube+0.005
Neg logit contributions
ows-0.010
obb-0.010
pering-0.009
arl-0.009
iving-0.009
Token had
Token ID550
Feature activation-3.45e+00

Pos logit contributions
arl+0.031
pering+0.031
iving+0.030
ows+0.029
obb+0.029
Neg logit contributions
 flavor-0.013
 penny-0.013
 peanut-0.012
 cube-0.012
 ornament-0.011
Token a
Token ID257
Feature activation+7.78e-01

Pos logit contributions
 flavor+0.084
 penny+0.082
 peanut+0.079
 ornament+0.076
 cube+0.075
Neg logit contributions
ows-0.135
pering-0.135
arl-0.132
iving-0.129
obb-0.128
Token big
Token ID1263
Feature activation-7.29e-01

Pos logit contributions
ows+0.024
pering+0.024
obb+0.023
arl+0.023
oms+0.022
Neg logit contributions
 flavor-0.023
 ornament-0.023
 penny-0.023
 cube-0.022
 peanut-0.021
Token,
Token ID11
Feature activation+1.01e+00

Pos logit contributions
 flavor+0.019
 penny+0.019
 ornament+0.019
 peanut+0.018
 cube+0.018
Neg logit contributions
ows-0.025
pering-0.025
obb-0.024
arl-0.024
oms-0.023
Token red
Token ID2266
Feature activation-5.83e+00

Pos logit contributions
ows+0.034
pering+0.033
obb+0.032
arl+0.031
 announcements+0.030
Neg logit contributions
 penny-0.028
 flavor-0.028
 ornament-0.027
 cube-0.026
 peanut-0.026
Token ball
Token ID2613
Feature activation-2.79e+00

Pos logit contributions
 flavor+0.144
 penny+0.143
 ornament+0.139
 peanut+0.133
 cube+0.133
Neg logit contributions
ows-0.207
pering-0.205
arl-0.202
obb-0.199
oms-0.195
Token.
Token ID13
Feature activation-4.00e-01

Pos logit contributions
 penny+0.082
 cube+0.080
 flavor+0.080
 ornament+0.079
 peanut+0.078
Neg logit contributions
pering-0.092
ows-0.091
obb-0.090
arl-0.088
 announcements-0.088
Token He
Token ID679
Feature activation+9.27e-01

Pos logit contributions
 flavor+0.009
 penny+0.009
 cube+0.009
 peanut+0.009
 ornament+0.008
Neg logit contributions
pering-0.016
ows-0.016
obb-0.016
 announcements-0.015
aults-0.015
Token loved
Token ID6151
Feature activation+1.54e-01

Pos logit contributions
pering+0.037
ows+0.037
arl+0.036
obb+0.035
iving+0.034
Neg logit contributions
 flavor-0.021
 penny-0.021
 ornament-0.020
 peanut-0.019
 cube-0.019
Token to
Token ID284
Feature activation-1.07e+00

Pos logit contributions
pering+0.006
ows+0.005
arl+0.005
obb+0.005
oms+0.005
Neg logit contributions
 penny-0.004
 flavor-0.004
 ornament-0.004
 cube-0.004
 peanut-0.004
Token gave
Token ID2921
Feature activation-2.31e+00

Pos logit contributions
 possession+0.058
 penny+0.056
 flavor+0.054
 ornament+0.054
 ruby+0.054
Neg logit contributions
ows-0.046
oms-0.039
 amused-0.038
chers-0.037
obb-0.037
Token her
Token ID607
Feature activation-1.61e+00

Pos logit contributions
 flavor+0.068
 penny+0.067
 cube+0.065
 ornament+0.062
 peanut+0.061
Neg logit contributions
ows-0.073
arl-0.070
pering-0.069
obb-0.068
oms-0.067
Token a
Token ID257
Feature activation+1.29e-01

Pos logit contributions
 penny+0.049
 flavor+0.049
 ornament+0.047
 cube+0.046
 peanut+0.046
Neg logit contributions
ows-0.051
pering-0.050
obb-0.048
arl-0.048
iving-0.046
Token big
Token ID1263
Feature activation-1.22e+00

Pos logit contributions
arl+0.003
ows+0.003
obb+0.003
 loud+0.003
 realize+0.003
Neg logit contributions
mar-0.004
ci-0.004
ake-0.004
 possession-0.004
 mattered-0.004
Token,
Token ID11
Feature activation+4.69e-01

Pos logit contributions
mar+0.031
 flavor+0.030
 mattered+0.030
shr+0.029
 penny+0.029
Neg logit contributions
arl-0.039
obb-0.037
oms-0.037
ows-0.037
iving-0.035
Token juicy
Token ID35075
Feature activation-4.97e+00

Pos logit contributions
pering+0.014
obb+0.014
ows+0.014
arl+0.013
 deter+0.012
Neg logit contributions
 flavor-0.013
 penny-0.013
 ornament-0.013
 cube-0.013
mar-0.013
Token apple
Token ID17180
Feature activation-4.14e+00

Pos logit contributions
ci+0.134
 mattered+0.131
Ell+0.127
mar+0.127
shr+0.121
Neg logit contributions
obb-0.144
arl-0.137
 loud-0.135
 realize-0.133
 men-0.130
Token.
Token ID13
Feature activation-7.03e-01

Pos logit contributions
 flavor+0.152
shr+0.148
 mattered+0.148
 penny+0.145
 possession+0.145
Neg logit contributions
ows-0.088
pering-0.074
arl-0.074
iving-0.070
adders-0.068
Token Lily
Token ID20037
Feature activation-1.31e+00

Pos logit contributions
 penny+0.020
 flavor+0.020
 ornament+0.019
 cube+0.019
 peanut+0.018
Neg logit contributions
ows-0.024
pering-0.023
arl-0.023
obb-0.022
iving-0.022
Token took
Token ID1718
Feature activation+4.80e-01

Pos logit contributions
 penny+0.038
 possession+0.038
 gem+0.038
 ornament+0.038
 ruby+0.037
Neg logit contributions
ows-0.035
obb-0.031
 sure-0.030
 screams-0.030
 realize-0.029
Token a
Token ID257
Feature activation+8.87e-01

Pos logit contributions
obb+0.011
ows+0.010
pering+0.010
adders+0.009
oms+0.009
Neg logit contributions
 cube-0.018
 flavor-0.017
 penny-0.017
 ornament-0.016
 possession-0.016
Token.
Token ID13
Feature activation-3.65e-01

Pos logit contributions
obb+0.050
pering+0.048
arl+0.048
ighters+0.047
uits+0.047
Neg logit contributions
 cube-0.021
 penny-0.021
 flavor-0.020
 peanut-0.020
 ornament-0.020
Token Where
Token ID6350
Feature activation+1.20e+00

Pos logit contributions
 penny+0.009
 flavor+0.009
 ornament+0.009
 cube+0.009
 peanut+0.009
Neg logit contributions
ows-0.013
pering-0.013
obb-0.013
arl-0.013
iving-0.012
Token is
Token ID318
Feature activation-1.28e+00

Pos logit contributions
pering+0.048
arl+0.043
ows+0.042
obb+0.042
 announcements+0.042
Neg logit contributions
 flavor-0.032
 cube-0.030
 penny-0.030
 ornament-0.030
 peanut-0.027
Token his
Token ID465
Feature activation-1.13e+00

Pos logit contributions
 flavor+0.037
 penny+0.037
 ornament+0.036
 cube+0.035
 peanut+0.034
Neg logit contributions
pering-0.040
ows-0.039
obb-0.038
arl-0.037
oms-0.037
Token blue
Token ID4171
Feature activation-5.29e+00

Pos logit contributions
 penny+0.029
 flavor+0.029
 ornament+0.029
 peanut+0.028
 cube+0.027
Neg logit contributions
ows-0.039
pering-0.039
obb-0.038
arl-0.037
oms-0.036
Token bowl
Token ID9396
Feature activation-4.12e+00

Pos logit contributions
 penny+0.127
 ornament+0.124
 flavor+0.121
 peanut+0.118
pol+0.113
Neg logit contributions
ows-0.180
arl-0.176
pering-0.173
oms-0.172
obb-0.170
Token?
Token ID30
Feature activation-3.56e-01

Pos logit contributions
 flavor+0.122
 penny+0.121
 ornament+0.118
 cube+0.118
 peanut+0.115
Neg logit contributions
pering-0.137
ows-0.135
obb-0.128
 announcements-0.128
arl-0.126
Token
Token ID198
Feature activation-6.56e-01

Pos logit contributions
 penny+0.010
 flavor+0.010
 ornament+0.010
 peanut+0.009
 cube+0.009
Neg logit contributions
ows-0.012
pering-0.012
arl-0.011
obb-0.011
oms-0.011
Token
Token ID198
Feature activation-6.64e-01

Pos logit contributions
 flavor+0.014
 penny+0.013
 ornament+0.013
 cube+0.013
 peanut+0.013
Neg logit contributions
ows-0.027
pering-0.027
obb-0.026
iving-0.026
arl-0.025
TokenHe
Token ID1544
Feature activation+1.39e+00

Pos logit contributions
 penny+0.019
 flavor+0.019
 ornament+0.018
 cube+0.018
 peanut+0.018
Neg logit contributions
ows-0.023
pering-0.022
obb-0.021
oms-0.021
arl-0.020
Token asks
Token ID7893
Feature activation-8.51e-01

Pos logit contributions
pering+0.048
arl+0.048
ows+0.047
iving+0.046
adders+0.043
Neg logit contributions
 peanut-0.039
 penny-0.039
 cube-0.038
 flavor-0.037
 ornament-0.037
Token guitar
Token ID10047
Feature activation-1.99e+00

Pos logit contributions
pering+0.013
ows+0.013
arl+0.013
obb+0.012
 announcements+0.012
Neg logit contributions
 penny-0.008
 ornament-0.008
 flavor-0.008
 cube-0.007
 peanut-0.007
Token.
Token ID13
Feature activation-2.29e+00

Pos logit contributions
 ornament+0.046
 flavor+0.043
 cube+0.043
 penny+0.042
 color+0.040
Neg logit contributions
arl-0.083
pering-0.083
obb-0.079
ows-0.076
 announcements-0.075
Token He
Token ID679
Feature activation-6.58e-02

Pos logit contributions
 penny+0.072
 flavor+0.071
 ornament+0.069
 peanut+0.068
 cube+0.067
Neg logit contributions
ows-0.070
pering-0.069
arl-0.066
obb-0.065
iving-0.064
Token had
Token ID550
Feature activation-4.03e+00

Pos logit contributions
 flavor+0.001
 penny+0.001
 ornament+0.001
 cube+0.001
 peanut+0.001
Neg logit contributions
pering-0.003
ows-0.003
arl-0.003
obb-0.003
iving-0.003
Token a
Token ID257
Feature activation+1.84e-01

Pos logit contributions
 flavor+0.121
 penny+0.121
 ornament+0.117
 peanut+0.115
 cube+0.114
Neg logit contributions
ows-0.131
pering-0.131
obb-0.125
arl-0.124
iving-0.120
Token nice
Token ID3621
Feature activation-4.11e+00

Pos logit contributions
arl+0.004
obb+0.004
pering+0.004
ows+0.004
iving+0.004
Neg logit contributions
 flavor-0.006
seed-0.006
 ornament-0.006
 penny-0.006
pol-0.006
Token guitar
Token ID10047
Feature activation-2.42e+00

Pos logit contributions
 penny+0.112
 flavor+0.111
 ornament+0.109
 peanut+0.108
 cube+0.106
Neg logit contributions
ows-0.131
arl-0.124
iving-0.123
pering-0.122
obb-0.122
Token with
Token ID351
Feature activation-2.47e+00

Pos logit contributions
 penny+0.063
 ornament+0.061
 flavor+0.061
 cube+0.061
 peanut+0.060
Neg logit contributions
pering-0.091
ows-0.088
obb-0.087
arl-0.086
 announcements-0.084
Token red
Token ID2266
Feature activation-6.21e+00

Pos logit contributions
 flavor+0.066
 penny+0.066
 ornament+0.063
 peanut+0.063
 cube+0.062
Neg logit contributions
ows-0.089
pering-0.088
obb-0.084
arl-0.084
iving-0.081
Token and
Token ID290
Feature activation-6.79e-01

Pos logit contributions
 penny+0.195
 flavor+0.191
 ornament+0.191
 cube+0.188
 peanut+0.186
Neg logit contributions
ows-0.182
arl-0.172
pering-0.172
oms-0.170
iving-0.167
Token blue
Token ID4171
Feature activation-5.17e+00

Pos logit contributions
 penny+0.019
 flavor+0.019
 ornament+0.019
 cube+0.018
 peanut+0.018
Neg logit contributions
ows-0.022
pering-0.022
obb-0.021
arl-0.021
iving-0.020