TOP ACTIVATIONS
MAX = 0.117

big farm a long time ago . Lily listened as the
her birthday a few days ago . She liked to practice
had been made many years ago , but it still looked
this house a long time ago ." L ily
flyer posted a few days ago , looking for help around
says that a long time ago , a dragon used to
me here a long time ago . They forgot about me
I built it many years ago and I am very proud
found the truck many years ago and worked hard to fix
They lived a long time ago . They had big bones
They were here a minute ago ." " Maybe
started smoking a long time ago and now it 's hard
She told her three - year - old daughter to attach
bracelet for her three - year - old child . The
One day , three - year - old Billy saw his
ac orn a few days ago so I could have some
the wardrobe a few days ago , so she opened it
it away a long time ago . It is not good
in the park many years ago . Toby was amazed !
mother took her 3 - year - old daughter to the

MIN ACTIVATIONS
MIN = -0.113

They want to make snow fl akes for the window .
and see Tom 's sun fl owers . They are very
beautiful -- but different -- fl owers . Each morning ,
window and saw the snow fl akes falling . She thought
'm afraid I can 't let it go for any less
and Lib by couldn 't WA IT to plan the next
much lighter and it made Br andy feel so happy .
naughty . He does not let anyone go on the slide
was tough and didn 't let anything stop him . Every
strong like the other sun fl owers . The weak sun
saw the veil and couldn â € ™ t wait to
was scared and wouldn 't let them near . But the
Daisy was amazed and couldn â € ™ t take her
lots of trees and wild fl owers . As he stepped
' things and didn 't let them play with him .
, but he did not let that stop him . He
on the fence and couldn â € ™ t get out
, but she didn 't let the ducks bring her down
with it and wouldn 't let anyone else play with it
too full and could not let him stay .

INTERVAL 0.060 - 0.117
CONTAINS 0.285%

says . " We forgive you . But you have to
Joy is a good name for that star . It reminds
And they all lived happily ever after . The end .
hugs her . " Thank you , Mia . You are
, mom . Thank you for the vegetables ," Tommy said

INTERVAL 0.002 - 0.060
CONTAINS 43.933%

playing . When it was time to go home , Tim
else instead of scissors . How about some string or some
Sam had learned an important lesson : it 's always a
day of the test , the little car woke up early
there was a cow . The cow was lost in a

INTERVAL -0.055 - 0.002
CONTAINS 55.646%

time , there lived a little girl . She had beautiful
a hole for the door . She drew windows and wings
my hoop ?" His mom said , " Yes you can
says . They follow the trail and find Tom
house ." The lion was very proud of himself . From

INTERVAL -0.113 - -0.055
CONTAINS 0.136%

crying because he lost his toy . L
understand why she could not have the wine .
The bird was sad , but it did not give up
that he had made a terrible mistake and felt bad .
, but she wouldn 't let them . She was fierce
Token big
Token ID1263
Feature activation-2.73e-03

Pos logit contributions
 cheese+0.023
 Some+0.022
 of+0.020
 pizz+0.020
oke+0.019
Neg logit contributions
 forth-0.041
irling-0.041
 salon-0.039
ault-0.039
inge-0.037
Token farm
Token ID5318
Feature activation+2.62e-02

Pos logit contributions
 forth+0.005
irling+0.005
 salon+0.005
ault+0.005
 wrist+0.005
Neg logit contributions
 cheese-0.004
 Some-0.004
oke-0.004
 of-0.004
 Their-0.004
Token a
Token ID257
Feature activation+2.01e-02

Pos logit contributions
 Some+0.029
 cheese+0.028
oke+0.025
 Their+0.025
 There+0.024
Neg logit contributions
 forth-0.059
 salon-0.057
irling-0.056
ault-0.056
 wrist-0.054
Token long
Token ID890
Feature activation+3.16e-02

Pos logit contributions
 Some+0.027
 cheese+0.027
oke+0.024
 of+0.024
 Their+0.024
Neg logit contributions
 forth-0.040
irling-0.039
 salon-0.038
ault-0.038
 wrist-0.036
Token time
Token ID640
Feature activation+4.10e-02

Pos logit contributions
 Some+0.030
 cheese+0.029
oke+0.026
 Their+0.025
 pizz+0.025
Neg logit contributions
 forth-0.077
irling-0.074
 salon-0.073
ault-0.072
 wrist-0.070
Token ago
Token ID2084
Feature activation+1.17e-01

Pos logit contributions
 cheese+0.029
 Some+0.027
 pizz+0.022
oke+0.021
 Their+0.020
Neg logit contributions
 forth-0.110
irling-0.108
 salon-0.105
ault-0.104
 wrist-0.100
Token.
Token ID13
Feature activation+1.30e-02

Pos logit contributions
 Some+0.112
 cheese+0.109
oke+0.092
 Their+0.088
 wine+0.086
Neg logit contributions
 forth-0.284
irling-0.277
 salon-0.273
ault-0.267
 wrist-0.266
Token Lily
Token ID20037
Feature activation-1.50e-02

Pos logit contributions
 cheese+0.014
 pizz+0.013
 Some+0.012
oke+0.012
 peppers+0.012
Neg logit contributions
 forth-0.027
 salon-0.027
irling-0.027
liv-0.026
 wrist-0.026
Token listened
Token ID16399
Feature activation-4.90e-03

Pos logit contributions
irling+0.037
 forth+0.037
ault+0.037
inge+0.034
 salon+0.034
Neg logit contributions
 cheese-0.014
 of-0.013
:-0.011
 can-0.011
 Their-0.011
Token as
Token ID355
Feature activation-8.80e-03

Pos logit contributions
 forth+0.012
irling+0.012
ault+0.011
 salon+0.011
 wrist+0.011
Neg logit contributions
 cheese-0.005
 Some-0.005
 pizz-0.004
oke-0.004
 wine-0.004
Token the
Token ID262
Feature activation+3.20e-02

Pos logit contributions
 forth+0.015
irling+0.014
 salon+0.014
ault+0.014
 wrist+0.013
Neg logit contributions
 Some-0.015
 cheese-0.014
oke-0.014
 pizz-0.014
 Their-0.013
Token her
Token ID607
Feature activation-3.17e-03

Pos logit contributions
 Some+0.071
 cheese+0.070
oke+0.067
 pizz+0.064
 There+0.063
Neg logit contributions
 forth-0.073
irling-0.071
ault-0.067
 salon-0.066
 wrist-0.062
Token birthday
Token ID10955
Feature activation+1.97e-02

Pos logit contributions
 forth+0.008
irling+0.008
 salon+0.008
ault+0.008
 wrist+0.007
Neg logit contributions
 cheese-0.003
 Some-0.003
 pizz-0.002
oke-0.002
 Their-0.002
Token a
Token ID257
Feature activation+1.64e-02

Pos logit contributions
 Some+0.017
 cheese+0.017
oke+0.014
 pizz+0.014
 Their+0.014
Neg logit contributions
 forth-0.049
irling-0.047
 salon-0.047
ault-0.047
 wrist-0.045
Token few
Token ID1178
Feature activation+1.12e-02

Pos logit contributions
 cheese+0.020
 Some+0.019
 of+0.017
 pizz+0.016
oke+0.016
Neg logit contributions
 forth-0.036
irling-0.036
ault-0.034
 salon-0.034
inge-0.033
Token days
Token ID1528
Feature activation+4.28e-02

Pos logit contributions
 Some+0.015
 cheese+0.015
oke+0.015
 Their+0.014
 There+0.014
Neg logit contributions
 forth-0.023
irling-0.022
ault-0.021
 salon-0.021
 wrist-0.021
Token ago
Token ID2084
Feature activation+1.17e-01

Pos logit contributions
 cheese+0.033
 Some+0.030
 of+0.028
oke+0.024
 pizz+0.024
Neg logit contributions
 forth-0.112
irling-0.111
ault-0.107
 salon-0.107
inge-0.103
Token.
Token ID13
Feature activation+7.48e-03

Pos logit contributions
 Some+0.104
 cheese+0.104
oke+0.086
 Their+0.081
 pizz+0.081
Neg logit contributions
 forth-0.290
irling-0.285
 salon-0.277
ault-0.275
 wrist-0.271
Token She
Token ID1375
Feature activation-2.46e-03

Pos logit contributions
 cheese+0.010
 pizz+0.009
oke+0.008
ocol+0.008
 meat+0.008
Neg logit contributions
 forth-0.015
irling-0.015
 wrist-0.014
 salon-0.014
icycle-0.014
Token liked
Token ID8288
Feature activation+3.58e-03

Pos logit contributions
 forth+0.006
irling+0.005
ault+0.005
 salon+0.005
inge+0.005
Neg logit contributions
 of-0.003
 cheese-0.003
 Some-0.003
 can-0.002
 Their-0.002
Token to
Token ID284
Feature activation-2.53e-02

Pos logit contributions
 cheese+0.004
 Some+0.004
oke+0.004
 pizz+0.004
 of+0.004
Neg logit contributions
 forth-0.008
irling-0.008
 salon-0.007
ault-0.007
 wrist-0.007
Token practice
Token ID3357
Feature activation+1.27e-02

Pos logit contributions
irling+0.048
 forth+0.048
 salon+0.045
liv+0.045
ault+0.044
Neg logit contributions
 cheese-0.037
 of-0.035
 Some-0.034
 time-0.033
 can-0.032
Token had
Token ID550
Feature activation+1.79e-02

Pos logit contributions
 cheese+0.017
 Some+0.016
 of+0.015
 Their+0.014
 There+0.014
Neg logit contributions
 forth-0.043
irling-0.042
ault-0.042
 salon-0.041
inge-0.039
Token been
Token ID587
Feature activation+2.39e-02

Pos logit contributions
 cheese+0.018
 Some+0.017
 of+0.015
 Their+0.014
 There+0.014
Neg logit contributions
 forth-0.045
irling-0.044
 salon-0.042
ault-0.042
inge-0.040
Token made
Token ID925
Feature activation+1.17e-02

Pos logit contributions
 cheese+0.036
 Some+0.035
oke+0.033
 pizz+0.032
 Their+0.031
Neg logit contributions
 forth-0.045
irling-0.045
 salon-0.042
ault-0.042
icycle-0.040
Token many
Token ID867
Feature activation-1.93e-04

Pos logit contributions
 Some+0.008
 cheese+0.008
oke+0.007
 pizz+0.007
 Their+0.006
Neg logit contributions
 forth-0.031
irling-0.030
ault-0.029
 salon-0.028
icycle-0.028
Token years
Token ID812
Feature activation+7.92e-02

Pos logit contributions
 forth+0.000
irling+0.000
ault+0.000
 salon+0.000
icycle+0.000
Neg logit contributions
 cheese-0.000
 Some-0.000
oke-0.000
 Their-0.000
 There-0.000
Token ago
Token ID2084
Feature activation+1.15e-01

Pos logit contributions
 cheese+0.089
 Some+0.086
 pizz+0.075
 Their+0.073
 mushrooms+0.071
Neg logit contributions
irling-0.173
 salon-0.171
 forth-0.166
ault-0.160
 wrist-0.160
Token,
Token ID11
Feature activation+7.82e-03

Pos logit contributions
 Some+0.121
 cheese+0.115
oke+0.108
 Their+0.097
 There+0.095
Neg logit contributions
 forth-0.264
irling-0.262
 wrist-0.253
 salon-0.252
ault-0.249
Token but
Token ID475
Feature activation-2.19e-02

Pos logit contributions
 cheese+0.010
 Some+0.010
 of+0.009
oke+0.009
 pizz+0.009
Neg logit contributions
 forth-0.016
irling-0.016
ault-0.015
 salon-0.015
 wrist-0.014
Token it
Token ID340
Feature activation-1.72e-03

Pos logit contributions
 forth+0.045
irling+0.045
ault+0.044
 salon+0.043
icycle+0.041
Neg logit contributions
 cheese-0.030
 Some-0.028
 of-0.026
 Their-0.025
 wine-0.025
Token still
Token ID991
Feature activation-2.25e-03

Pos logit contributions
 forth+0.005
ault+0.005
irling+0.005
 salon+0.004
 sidelines+0.004
Neg logit contributions
 of-0.001
 cheese-0.001
 time-0.001
 can-0.001
 Some-0.001
Token looked
Token ID3114
Feature activation+9.05e-03

Pos logit contributions
 forth+0.005
irling+0.005
ault+0.005
 salon+0.005
inge+0.004
Neg logit contributions
 cheese-0.003
 Some-0.003
 of-0.003
oke-0.002
 pizz-0.002
Token this
Token ID428
Feature activation+7.88e-03

Pos logit contributions
 cheese+0.018
 Some+0.018
oke+0.017
 pizz+0.016
 Their+0.016
Neg logit contributions
 forth-0.031
irling-0.030
 salon-0.029
ault-0.029
 wrist-0.028
Token house
Token ID2156
Feature activation+3.04e-03

Pos logit contributions
 cheese+0.013
 Some+0.012
 of+0.011
 pizz+0.011
 wine+0.011
Neg logit contributions
 forth-0.015
irling-0.014
ault-0.014
 salon-0.013
inge-0.013
Token a
Token ID257
Feature activation+1.11e-02

Pos logit contributions
 cheese+0.003
 Some+0.003
oke+0.003
 pizz+0.003
 Their+0.003
Neg logit contributions
 forth-0.007
irling-0.007
 salon-0.007
ault-0.006
 wrist-0.006
Token long
Token ID890
Feature activation+2.50e-02

Pos logit contributions
 cheese+0.015
 Some+0.015
 of+0.014
 pizz+0.013
oke+0.013
Neg logit contributions
 forth-0.022
irling-0.022
ault-0.021
 salon-0.021
inge-0.020
Token time
Token ID640
Feature activation+3.80e-02

Pos logit contributions
 Some+0.026
 cheese+0.026
oke+0.023
 pizz+0.022
 Their+0.022
Neg logit contributions
 forth-0.058
irling-0.057
 salon-0.056
ault-0.055
 wrist-0.053
Token ago
Token ID2084
Feature activation+1.15e-01

Pos logit contributions
 cheese+0.018
 Some+0.016
 of+0.011
 pizz+0.011
oke+0.011
Neg logit contributions
 forth-0.111
irling-0.109
 salon-0.106
ault-0.106
 wrist-0.102
Token."
Token ID526
Feature activation+7.93e-04

Pos logit contributions
 Some+0.113
 cheese+0.110
oke+0.093
 Their+0.092
 wine+0.088
Neg logit contributions
 forth-0.276
irling-0.267
 salon-0.265
ault-0.258
 wrist-0.257
Token
Token ID198
Feature activation+9.61e-03

Pos logit contributions
 cheese+0.001
 pizz+0.001
 Some+0.001
oke+0.001
ocol+0.001
Neg logit contributions
 forth-0.002
irling-0.002
 salon-0.002
 wrist-0.002
ault-0.002
Token
Token ID198
Feature activation+7.75e-03

Pos logit contributions
 cheese+0.011
 pizz+0.010
 Some+0.010
 peppers+0.009
 wine+0.009
Neg logit contributions
irling-0.021
 forth-0.021
 salon-0.020
liv-0.020
icycle-0.019
TokenL
Token ID43
Feature activation-6.12e-03

Pos logit contributions
 Some+0.009
 cheese+0.008
 of+0.008
 Their+0.008
 wine+0.007
Neg logit contributions
 forth-0.019
ault-0.017
irling-0.017
 salon-0.016
inge-0.016
Tokenily
Token ID813
Feature activation+1.04e-02

Pos logit contributions
irling+0.015
 forth+0.014
 salon+0.014
ault+0.014
inge+0.013
Neg logit contributions
 cheese-0.006
 Some-0.006
 pizz-0.005
 There-0.005
 Their-0.005
Token flyer
Token ID42464
Feature activation-6.30e-03

Pos logit contributions
 forth+0.039
irling+0.038
 salon+0.037
ault+0.037
 wrist+0.035
Neg logit contributions
 Some-0.023
 cheese-0.023
oke-0.020
 of-0.020
 Their-0.020
Token posted
Token ID4481
Feature activation+1.24e-02

Pos logit contributions
 forth+0.015
irling+0.014
 salon+0.014
ault+0.014
icycle+0.013
Neg logit contributions
 cheese-0.007
 Some-0.006
 of-0.006
oke-0.006
 pizz-0.006
Token a
Token ID257
Feature activation+1.47e-04

Pos logit contributions
 Some+0.016
 cheese+0.016
oke+0.015
 pizz+0.014
 Their+0.014
Neg logit contributions
 forth-0.025
ault-0.024
irling-0.024
 salon-0.023
 wrist-0.022
Token few
Token ID1178
Feature activation+1.16e-03

Pos logit contributions
 cheese+0.000
 Some+0.000
 of+0.000
oke+0.000
 pizz+0.000
Neg logit contributions
 forth-0.000
irling-0.000
ault-0.000
 salon-0.000
 wrist-0.000
Token days
Token ID1528
Feature activation+3.68e-02

Pos logit contributions
 Some+0.002
 Their+0.001
 cheese+0.001
oke+0.001
izza+0.001
Neg logit contributions
 forth-0.002
irling-0.002
ault-0.002
 salon-0.002
 wrist-0.002
Token ago
Token ID2084
Feature activation+1.14e-01

Pos logit contributions
 cheese+0.035
 Some+0.033
 pizz+0.027
 Their+0.027
oke+0.027
Neg logit contributions
 forth-0.091
irling-0.089
 salon-0.086
ault-0.086
 wrist-0.082
Token,
Token ID11
Feature activation+3.46e-03

Pos logit contributions
 Some+0.103
 cheese+0.102
oke+0.083
 Their+0.081
 pizz+0.080
Neg logit contributions
 forth-0.284
irling-0.278
 salon-0.269
ault-0.269
 wrist-0.261
Token looking
Token ID2045
Feature activation+3.10e-02

Pos logit contributions
 cheese+0.004
 Some+0.004
 of+0.003
 pizz+0.003
oke+0.003
Neg logit contributions
 forth-0.008
irling-0.008
 salon-0.007
ault-0.007
inge-0.007
Token for
Token ID329
Feature activation+1.84e-02

Pos logit contributions
 cheese+0.046
 Some+0.044
 pizz+0.041
oke+0.040
 Their+0.040
Neg logit contributions
 forth-0.060
irling-0.056
ault-0.055
 salon-0.054
icycle-0.050
Token help
Token ID1037
Feature activation+3.95e-03

Pos logit contributions
 Some+0.024
oke+0.024
 cheese+0.024
izza+0.022
 Their+0.022
Neg logit contributions
 forth-0.036
irling-0.035
ault-0.034
 salon-0.033
 wrist-0.032
Token around
Token ID1088
Feature activation-1.71e-02

Pos logit contributions
 Some+0.005
 cheese+0.005
oke+0.004
 Their+0.004
 pizz+0.004
Neg logit contributions
 forth-0.009
ault-0.008
irling-0.008
 salon-0.008
 wrist-0.008
Token says
Token ID1139
Feature activation+2.63e-02

Pos logit contributions
 cheese+0.032
 Some+0.032
 pizz+0.029
 Their+0.029
oke+0.028
Neg logit contributions
 forth-0.042
irling-0.040
ault-0.038
 salon-0.038
 wrist-0.036
Token that
Token ID326
Feature activation+2.50e-02

Pos logit contributions
 Some+0.031
 cheese+0.030
 pizz+0.027
oke+0.027
 Their+0.026
Neg logit contributions
 forth-0.054
ault-0.054
irling-0.053
 salon-0.052
 wrist-0.051
Token a
Token ID257
Feature activation+1.88e-02

Pos logit contributions
 Some+0.037
 cheese+0.035
oke+0.033
 Their+0.033
 There+0.032
Neg logit contributions
 forth-0.047
 salon-0.044
irling-0.043
ault-0.043
 wrist-0.041
Token long
Token ID890
Feature activation+2.33e-02

Pos logit contributions
 Some+0.026
 cheese+0.025
 Their+0.024
oke+0.023
 There+0.023
Neg logit contributions
 forth-0.036
 salon-0.035
irling-0.035
ault-0.035
 wrist-0.033
Token time
Token ID640
Feature activation+3.32e-02

Pos logit contributions
 Some+0.033
 Their+0.030
oke+0.029
 cheese+0.029
 pizz+0.027
Neg logit contributions
 forth-0.046
 salon-0.043
 wrist-0.042
irling-0.042
ault-0.042
Token ago
Token ID2084
Feature activation+1.14e-01

Pos logit contributions
 cheese+0.034
 Some+0.033
oke+0.029
 pizz+0.029
 Their+0.028
Neg logit contributions
 forth-0.077
irling-0.075
 salon-0.073
ault-0.072
 wrist-0.070
Token,
Token ID11
Feature activation+9.78e-03

Pos logit contributions
 Some+0.122
 cheese+0.115
 Their+0.101
oke+0.100
 There+0.095
Neg logit contributions
 forth-0.264
 salon-0.252
irling-0.252
 wrist-0.249
ault-0.246
Token a
Token ID257
Feature activation+1.13e-02

Pos logit contributions
 cheese+0.013
 Some+0.012
 pizz+0.011
oke+0.011
 of+0.011
Neg logit contributions
 forth-0.020
irling-0.020
 salon-0.019
ault-0.019
 wrist-0.018
Token dragon
Token ID10441
Feature activation+2.55e-02

Pos logit contributions
 Some+0.016
 cheese+0.014
 Their+0.014
oke+0.014
 There+0.013
Neg logit contributions
 forth-0.022
 salon-0.021
ault-0.021
irling-0.021
 wrist-0.020
Token used
Token ID973
Feature activation+1.34e-02

Pos logit contributions
 cheese+0.037
 Some+0.036
 pizz+0.032
 of+0.032
 Their+0.032
Neg logit contributions
 forth-0.050
irling-0.048
ault-0.046
 salon-0.046
 wrist-0.043
Token to
Token ID284
Feature activation+1.32e-02

Pos logit contributions
 Some+0.015
oke+0.015
 cheese+0.014
 Their+0.013
 pizz+0.013
Neg logit contributions
 forth-0.029
irling-0.027
ault-0.027
 salon-0.026
 wrist-0.026
Token me
Token ID502
Feature activation+1.21e-02

Pos logit contributions
 forth+0.054
irling+0.046
ault+0.046
 salon+0.044
 wrist+0.044
Neg logit contributions
 Some-0.044
oke-0.043
 cheese-0.040
 pizz-0.039
 There-0.039
Token here
Token ID994
Feature activation+1.26e-02

Pos logit contributions
 Some+0.017
 cheese+0.017
oke+0.016
 pizz+0.015
 There+0.015
Neg logit contributions
 forth-0.024
irling-0.023
ault-0.022
 salon-0.022
 wrist-0.021
Token a
Token ID257
Feature activation-1.80e-03

Pos logit contributions
 Some+0.014
 cheese+0.013
oke+0.012
 pizz+0.012
 There+0.012
Neg logit contributions
 forth-0.029
irling-0.028
ault-0.027
 salon-0.027
 wrist-0.026
Token long
Token ID890
Feature activation+1.48e-02

Pos logit contributions
 forth+0.003
 salon+0.003
irling+0.003
ault+0.003
 wrist+0.003
Neg logit contributions
 Some-0.003
 cheese-0.003
oke-0.003
 There-0.003
 Their-0.003
Token time
Token ID640
Feature activation+4.09e-02

Pos logit contributions
 Some+0.026
oke+0.025
 cheese+0.025
 pizz+0.024
 Their+0.024
Neg logit contributions
 forth-0.024
 salon-0.023
irling-0.022
ault-0.022
 wrist-0.021
Token ago
Token ID2084
Feature activation+1.13e-01

Pos logit contributions
 cheese+0.036
 Some+0.035
 pizz+0.029
 Their+0.029
oke+0.028
Neg logit contributions
 forth-0.103
irling-0.100
ault-0.097
 salon-0.097
 wrist-0.093
Token.
Token ID13
Feature activation+1.84e-02

Pos logit contributions
 Some+0.123
 cheese+0.114
 Their+0.099
oke+0.098
 wine+0.095
Neg logit contributions
 forth-0.266
irling-0.254
 salon-0.251
 wrist-0.245
ault-0.245
Token They
Token ID1119
Feature activation-1.85e-03

Pos logit contributions
 time+0.024
 pizz+0.023
 cheese+0.023
oke+0.022
 happened+0.022
Neg logit contributions
 wrist-0.034
 salon-0.032
 forth-0.032
ault-0.030
irling-0.029
Token forgot
Token ID16453
Feature activation-8.56e-03

Pos logit contributions
irling+0.005
 forth+0.005
 salon+0.004
liv+0.004
icycle+0.004
Neg logit contributions
 cheese-0.002
 Some-0.001
 of-0.001
 can-0.001
 There-0.001
Token about
Token ID546
Feature activation-1.85e-02

Pos logit contributions
 forth+0.021
 salon+0.020
irling+0.019
ault+0.019
 wrist+0.018
Neg logit contributions
 Some-0.008
 cheese-0.007
oke-0.007
 pizz-0.006
 There-0.006
Token me
Token ID502
Feature activation+5.44e-03

Pos logit contributions
 forth+0.036
irling+0.034
 salon+0.034
ault+0.033
 wrist+0.032
Neg logit contributions
 Some-0.027
oke-0.025
 of-0.024
 cheese-0.024
 There-0.023
Token I
Token ID314
Feature activation-2.34e-02

Pos logit contributions
 forth+0.010
irling+0.010
 salon+0.010
 wrist+0.010
icycle+0.010
Neg logit contributions
 cheese-0.008
 pizz-0.008
 time-0.007
 wine-0.007
 Some-0.007
Token built
Token ID3170
Feature activation+2.41e-03

Pos logit contributions
 forth+0.049
irling+0.048
 salon+0.046
ault+0.046
inge+0.044
Neg logit contributions
 cheese-0.031
 Some-0.029
 of-0.026
 pizz-0.026
oke-0.026
Token it
Token ID340
Feature activation-1.82e-03

Pos logit contributions
 Some+0.003
oke+0.003
 cheese+0.003
 Their+0.003
 There+0.002
Neg logit contributions
 forth-0.005
irling-0.005
ault-0.005
 salon-0.005
 wrist-0.005
Token many
Token ID867
Feature activation+4.83e-04

Pos logit contributions
 forth+0.004
irling+0.004
 salon+0.004
ault+0.004
inge+0.004
Neg logit contributions
 cheese-0.002
 Some-0.002
 of-0.002
 pizz-0.002
oke-0.002
Token years
Token ID812
Feature activation+7.17e-02

Pos logit contributions
 Some+0.001
 cheese+0.001
 Their+0.001
 There+0.001
oke+0.001
Neg logit contributions
 forth-0.001
irling-0.001
ault-0.001
 salon-0.001
 wrist-0.001
Token ago
Token ID2084
Feature activation+1.12e-01

Pos logit contributions
 cheese+0.071
 Some+0.070
 Their+0.060
 pizz+0.060
oke+0.056
Neg logit contributions
 forth-0.168
irling-0.167
 salon-0.165
ault-0.160
 wrist-0.154
Token and
Token ID290
Feature activation+8.85e-03

Pos logit contributions
 Some+0.115
 cheese+0.112
oke+0.097
 Their+0.094
 pizz+0.091
Neg logit contributions
 forth-0.264
irling-0.258
 salon-0.249
ault-0.247
 wrist-0.245
Token I
Token ID314
Feature activation-1.84e-02

Pos logit contributions
 cheese+0.013
 Some+0.012
 of+0.011
 pizz+0.011
oke+0.011
Neg logit contributions
 forth-0.017
irling-0.017
 salon-0.016
ault-0.016
inge-0.015
Token am
Token ID716
Feature activation-2.59e-02

Pos logit contributions
 forth+0.040
irling+0.039
ault+0.037
 salon+0.037
 wrist+0.035
Neg logit contributions
 cheese-0.023
 Some-0.022
 of-0.021
oke-0.020
 ago-0.019
Token very
Token ID845
Feature activation-5.48e-03

Pos logit contributions
 forth+0.052
irling+0.051
ault+0.048
 salon+0.048
inge+0.045
Neg logit contributions
 cheese-0.037
 Some-0.035
 of-0.032
 pizz-0.032
oke-0.032
Token proud
Token ID6613
Feature activation-2.20e-02

Pos logit contributions
 forth+0.010
irling+0.010
 salon+0.010
ault+0.010
icycle+0.009
Neg logit contributions
 cheese-0.008
 Some-0.008
 of-0.008
oke-0.007
 pizz-0.007
Token found
Token ID1043
Feature activation+3.13e-02

Pos logit contributions
 cheese+0.029
 Some+0.028
 of+0.024
oke+0.024
 pizz+0.024
Neg logit contributions
 forth-0.051
irling-0.050
ault-0.048
 salon-0.048
 wrist-0.045
Token the
Token ID262
Feature activation-1.89e-02

Pos logit contributions
 Some+0.038
oke+0.038
 cheese+0.034
 pizz+0.033
 Their+0.033
Neg logit contributions
 forth-0.063
ault-0.059
irling-0.058
 salon-0.058
 wrist-0.056
Token truck
Token ID7779
Feature activation-1.18e-02

Pos logit contributions
 forth+0.038
irling+0.037
 salon+0.036
ault+0.036
 wrist+0.034
Neg logit contributions
 cheese-0.026
 Some-0.025
oke-0.023
 of-0.023
 pizz-0.022
Token many
Token ID867
Feature activation+1.38e-02

Pos logit contributions
 forth+0.026
irling+0.025
 salon+0.025
ault+0.024
 wrist+0.023
Neg logit contributions
 Some-0.014
 cheese-0.014
 pizz-0.012
oke-0.012
 Their-0.012
Token years
Token ID812
Feature activation+7.41e-02

Pos logit contributions
 Some+0.020
 Their+0.019
 There+0.018
oke+0.018
 cheese+0.018
Neg logit contributions
 forth-0.027
irling-0.026
ault-0.023
 salon-0.023
icycle-0.023
Token ago
Token ID2084
Feature activation+1.12e-01

Pos logit contributions
 Some+0.079
 cheese+0.073
 Their+0.064
 pizz+0.062
 There+0.059
Neg logit contributions
 salon-0.164
irling-0.164
 forth-0.162
ault-0.153
icycle-0.152
Token and
Token ID290
Feature activation-9.68e-04

Pos logit contributions
 Some+0.112
 cheese+0.106
oke+0.092
 Their+0.088
 There+0.085
Neg logit contributions
 forth-0.267
irling-0.261
 salon-0.254
ault-0.251
 wrist-0.250
Token worked
Token ID3111
Feature activation-1.27e-02

Pos logit contributions
 forth+0.002
irling+0.002
 salon+0.002
ault+0.002
 wrist+0.002
Neg logit contributions
 cheese-0.001
 Some-0.001
oke-0.001
 pizz-0.001
 of-0.001
Token hard
Token ID1327
Feature activation+3.11e-02

Pos logit contributions
 forth+0.027
irling+0.026
ault+0.025
 salon+0.024
icycle+0.023
Neg logit contributions
 Some-0.017
 cheese-0.016
oke-0.015
 There-0.014
 pizz-0.014
Token to
Token ID284
Feature activation-1.69e-03

Pos logit contributions
 cheese+0.031
 Some+0.030
oke+0.026
 pizz+0.026
 Their+0.026
Neg logit contributions
 forth-0.075
irling-0.072
ault-0.068
 salon-0.068
icycle-0.066
Token fix
Token ID4259
Feature activation+9.65e-04

Pos logit contributions
irling+0.003
 forth+0.003
 salon+0.003
ault+0.003
icycle+0.003
Neg logit contributions
 cheese-0.003
 Some-0.002
 of-0.002
 time-0.002
 Their-0.002
Token They
Token ID1119
Feature activation+1.40e-02

Pos logit contributions
 time+0.045
 happened+0.042
 cheese+0.042
 wine+0.038
 pizz+0.038
Neg logit contributions
 wrist-0.066
 forth-0.064
ault-0.062
 myself-0.060
icycle-0.059
Token lived
Token ID5615
Feature activation+5.00e-03

Pos logit contributions
 cheese+0.015
 Some+0.013
 of+0.012
 pizz+0.012
 wine+0.011
Neg logit contributions
irling-0.034
 forth-0.034
 salon-0.032
ault-0.032
icycle-0.031
Token a
Token ID257
Feature activation+1.37e-02

Pos logit contributions
 Some+0.007
 cheese+0.007
oke+0.007
 There+0.006
 Their+0.006
Neg logit contributions
 forth-0.010
irling-0.010
ault-0.009
 salon-0.009
 wrist-0.009
Token long
Token ID890
Feature activation+1.80e-02

Pos logit contributions
 cheese+0.018
 Some+0.018
 of+0.016
oke+0.015
 pizz+0.015
Neg logit contributions
 forth-0.028
irling-0.028
ault-0.027
 salon-0.027
 wrist-0.025
Token time
Token ID640
Feature activation+3.75e-02

Pos logit contributions
 Some+0.022
 cheese+0.022
oke+0.020
 Their+0.020
 pizz+0.019
Neg logit contributions
 forth-0.038
irling-0.037
 salon-0.036
ault-0.036
 wrist-0.035
Token ago
Token ID2084
Feature activation+1.12e-01

Pos logit contributions
 cheese+0.032
 Some+0.030
 of+0.025
 pizz+0.024
oke+0.024
Neg logit contributions
 forth-0.096
irling-0.095
 salon-0.092
ault-0.091
inge-0.088
Token.
Token ID13
Feature activation+2.03e-02

Pos logit contributions
 Some+0.120
 cheese+0.110
oke+0.102
 Their+0.097
 There+0.093
Neg logit contributions
 forth-0.260
irling-0.249
 wrist-0.246
 salon-0.246
ault-0.239
Token They
Token ID1119
Feature activation-1.37e-03

Pos logit contributions
 cheese+0.023
 happened+0.023
 pizz+0.022
oke+0.021
 time+0.021
Neg logit contributions
 wrist-0.037
 forth-0.037
ault-0.035
 myself-0.035
irling-0.035
Token had
Token ID550
Feature activation+1.41e-02

Pos logit contributions
irling+0.003
 forth+0.003
 salon+0.003
ault+0.003
liv+0.003
Neg logit contributions
 cheese-0.001
 Some-0.001
 of-0.001
 can-0.001
 pizz-0.001
Token big
Token ID1263
Feature activation-1.45e-03

Pos logit contributions
 Some+0.017
oke+0.016
 cheese+0.016
 There+0.014
 of+0.014
Neg logit contributions
 forth-0.030
irling-0.029
ault-0.028
 salon-0.028
 wrist-0.027
Token bones
Token ID11945
Feature activation+2.51e-02

Pos logit contributions
 forth+0.003
irling+0.003
 salon+0.003
 wrist+0.003
ault+0.003
Neg logit contributions
 Their-0.002
 Some-0.002
oke-0.002
 cheese-0.002
lic-0.002
TokenThey
Token ID2990
Feature activation-1.34e-02

Pos logit contributions
 forth+0.006
irling+0.005
ault+0.005
icycle+0.005
 salon+0.005
Neg logit contributions
 Some-0.005
 cheese-0.005
 of-0.005
 Their-0.005
oke-0.005
Token were
Token ID547
Feature activation-5.63e-03

Pos logit contributions
irling+0.034
 forth+0.034
 salon+0.032
ault+0.032
 wrist+0.032
Neg logit contributions
 cheese-0.013
 of-0.011
 can-0.010
 Some-0.010
 wine-0.010
Token here
Token ID994
Feature activation+7.90e-03

Pos logit contributions
 forth+0.010
irling+0.010
ault+0.010
 salon+0.010
inge+0.009
Neg logit contributions
 Some-0.009
 cheese-0.009
oke-0.008
 of-0.008
 Their-0.008
Token a
Token ID257
Feature activation+6.24e-03

Pos logit contributions
 Some+0.008
 cheese+0.008
oke+0.007
 pizz+0.007
 Their+0.007
Neg logit contributions
 forth-0.018
irling-0.017
ault-0.017
 salon-0.017
 wrist-0.016
Token minute
Token ID5664
Feature activation+5.26e-03

Pos logit contributions
 cheese+0.009
 Some+0.009
 of+0.008
oke+0.008
 pizz+0.008
Neg logit contributions
 forth-0.012
irling-0.011
 salon-0.011
ault-0.011
 wrist-0.010
Token ago
Token ID2084
Feature activation+1.12e-01

Pos logit contributions
 cheese+0.006
 Some+0.006
 Their+0.005
 pizz+0.005
 wine+0.005
Neg logit contributions
 forth-0.012
irling-0.011
 salon-0.011
ault-0.011
 wrist-0.010
Token."
Token ID526
Feature activation+6.67e-03

Pos logit contributions
 Some+0.128
 cheese+0.119
 Their+0.104
oke+0.103
 There+0.098
Neg logit contributions
 forth-0.253
irling-0.242
 salon-0.239
 wrist-0.236
ault-0.234
Token
Token ID198
Feature activation+1.68e-02

Pos logit contributions
 cheese+0.009
 pizz+0.008
izza+0.008
ocol+0.008
oke+0.008
Neg logit contributions
irling-0.012
 salon-0.012
 wrist-0.011
 forth-0.011
ault-0.011
Token
Token ID198
Feature activation+1.49e-02

Pos logit contributions
 cheese+0.020
 pizz+0.018
 Some+0.017
 wine+0.016
 mushrooms+0.016
Neg logit contributions
irling-0.037
 forth-0.035
 salon-0.034
 wrist-0.033
ault-0.033
Token"
Token ID1
Feature activation-2.48e-02

Pos logit contributions
 Some+0.018
 cheese+0.018
 of+0.017
 Their+0.016
oke+0.016
Neg logit contributions
 forth-0.034
irling-0.032
ault-0.031
 salon-0.031
inge-0.030
TokenMaybe
Token ID13300
Feature activation+1.82e-03

Pos logit contributions
 forth+0.041
irling+0.039
ault+0.036
 salon+0.035
inge+0.034
Neg logit contributions
 Some-0.046
 cheese-0.046
 of-0.042
 Their-0.042
oke-0.041
Token started
Token ID2067
Feature activation-1.56e-02

Pos logit contributions
 forth+0.015
irling+0.015
ault+0.014
 salon+0.014
inge+0.013
Neg logit contributions
 cheese-0.011
 Some-0.010
 of-0.009
 pizz-0.009
oke-0.009
Token smoking
Token ID9216
Feature activation+5.22e-02

Pos logit contributions
 forth+0.037
irling+0.036
ault+0.034
 salon+0.034
inge+0.032
Neg logit contributions
 Some-0.014
 cheese-0.014
oke-0.014
 There-0.013
 pizz-0.012
Token a
Token ID257
Feature activation-1.13e-02

Pos logit contributions
oke+0.071
 Some+0.067
 There+0.067
 ago+0.061
 Their+0.060
Neg logit contributions
 forth-0.103
irling-0.096
 salon-0.095
ault-0.092
 wrist-0.088
Token long
Token ID890
Feature activation+1.37e-04

Pos logit contributions
 forth+0.022
 salon+0.021
ault+0.021
irling+0.020
ich+0.019
Neg logit contributions
 Some-0.015
 There-0.015
 Their-0.014
oke-0.013
 ago-0.013
Token time
Token ID640
Feature activation+2.74e-02

Pos logit contributions
 Some+0.000
oke+0.000
 There+0.000
 Their+0.000
aly+0.000
Neg logit contributions
 forth-0.000
irling-0.000
 salon-0.000
ault-0.000
 wrist-0.000
Token ago
Token ID2084
Feature activation+1.12e-01

Pos logit contributions
 Some+0.030
 cheese+0.030
 Their+0.026
 pizz+0.025
oke+0.025
Neg logit contributions
 forth-0.062
irling-0.061
 salon-0.058
ault-0.058
 wrist-0.055
Token and
Token ID290
Feature activation-6.36e-03

Pos logit contributions
 Some+0.106
 cheese+0.103
oke+0.086
 Their+0.085
 pizz+0.083
Neg logit contributions
 forth-0.272
irling-0.265
 salon-0.261
ault-0.256
 wrist-0.253
Token now
Token ID783
Feature activation+1.52e-02

Pos logit contributions
 forth+0.012
irling+0.012
 salon+0.011
ault+0.011
 wrist+0.010
Neg logit contributions
 Some-0.009
 cheese-0.009
oke-0.008
 pizz-0.008
 Their-0.008
Token it
Token ID340
Feature activation+1.68e-02

Pos logit contributions
 cheese+0.019
 Some+0.018
 of+0.016
oke+0.016
 pizz+0.015
Neg logit contributions
 forth-0.033
irling-0.033
ault-0.031
 salon-0.031
inge-0.030
Token's
Token ID338
Feature activation-2.96e-03

Pos logit contributions
 Some+0.023
 cheese+0.023
 ago+0.020
 pizz+0.020
 Their+0.020
Neg logit contributions
 forth-0.034
irling-0.032
 salon-0.031
ault-0.030
inge-0.029
Token hard
Token ID1327
Feature activation+3.28e-02

Pos logit contributions
 forth+0.006
irling+0.005
ault+0.005
 salon+0.005
pping+0.004
Neg logit contributions
oke-0.005
 Some-0.005
 There-0.004
 Their-0.004
izza-0.004
Token She
Token ID1375
Feature activation-5.22e-03

Pos logit contributions
 cheese+0.007
oke+0.007
 pizz+0.007
 Some+0.007
 of+0.006
Neg logit contributions
 forth-0.013
 salon-0.013
irling-0.013
ault-0.012
 wrist-0.012
Token told
Token ID1297
Feature activation+1.50e-02

Pos logit contributions
 forth+0.011
irling+0.011
 salon+0.010
ault+0.010
inge+0.009
Neg logit contributions
 cheese-0.007
 Some-0.007
 of-0.006
 pizz-0.006
oke-0.006
Token her
Token ID607
Feature activation+2.07e-02

Pos logit contributions
 Some+0.024
 cheese+0.024
oke+0.023
 ago+0.022
 pizz+0.022
Neg logit contributions
 forth-0.026
irling-0.025
 salon-0.025
ault-0.024
liv-0.023
Token three
Token ID1115
Feature activation+5.44e-02

Pos logit contributions
 cheese+0.029
 Some+0.028
 pizz+0.026
oke+0.025
 Their+0.024
Neg logit contributions
 forth-0.041
irling-0.040
 salon-0.039
ault-0.039
 wrist-0.037
Token-
Token ID12
Feature activation+7.36e-02

Pos logit contributions
 cheese+0.079
 Some+0.077
 There+0.071
 wine+0.068
 Their+0.068
Neg logit contributions
irling-0.099
 salon-0.096
 forth-0.096
 wrist-0.090
ault-0.090
Tokenyear
Token ID1941
Feature activation+1.11e-01

Pos logit contributions
 cheese+0.082
 Some+0.071
 There+0.070
oke+0.069
 pizz+0.068
Neg logit contributions
irling-0.159
 salon-0.158
 forth-0.156
ault-0.151
liv-0.150
Token-
Token ID12
Feature activation+7.53e-02

Pos logit contributions
 cheese+0.128
 Some+0.126
 There+0.117
 wine+0.108
 Their+0.107
Neg logit contributions
irling-0.237
 salon-0.229
 forth-0.227
ault-0.222
inge-0.220
Tokenold
Token ID727
Feature activation+1.75e-02

Pos logit contributions
 cheese+0.107
 Some+0.099
 There+0.096
oke+0.093
 wine+0.092
Neg logit contributions
irling-0.140
 salon-0.138
 forth-0.135
ault-0.131
liv-0.129
Token daughter
Token ID4957
Feature activation+2.39e-02

Pos logit contributions
 cheese+0.030
 Some+0.029
oke+0.027
 pizz+0.026
 wine+0.026
Neg logit contributions
 forth-0.029
 salon-0.027
irling-0.027
ault-0.027
 wrist-0.025
Token to
Token ID284
Feature activation+2.11e-02

Pos logit contributions
 cheese+0.020
 Some+0.019
 pizz+0.016
oke+0.016
 wine+0.015
Neg logit contributions
 forth-0.060
 salon-0.058
irling-0.058
ault-0.057
 wrist-0.055
Token attach
Token ID10199
Feature activation+1.03e-02

Pos logit contributions
 cheese+0.028
 Some+0.026
 of+0.026
 time+0.024
 Their+0.024
Neg logit contributions
irling-0.044
 forth-0.044
ault-0.041
 salon-0.041
icycle-0.040
Token bracelet
Token ID42893
Feature activation-6.42e-03

Pos logit contributions
 forth+0.033
irling+0.031
 salon+0.031
 wrist+0.030
ault+0.030
Neg logit contributions
 Some-0.030
oke-0.028
 cheese-0.028
 There-0.027
 Their-0.027
Token for
Token ID329
Feature activation+4.55e-02

Pos logit contributions
 forth+0.018
irling+0.018
ault+0.017
 salon+0.017
inge+0.016
Neg logit contributions
 cheese-0.005
 Some-0.004
 of-0.004
 wine-0.003
 pizz-0.003
Token her
Token ID607
Feature activation-3.68e-03

Pos logit contributions
 Some+0.063
 cheese+0.061
oke+0.060
 of+0.056
 There+0.055
Neg logit contributions
 forth-0.090
irling-0.089
ault-0.084
 salon-0.083
 wrist-0.078
Token three
Token ID1115
Feature activation+4.03e-02

Pos logit contributions
 forth+0.008
 wrist+0.008
 salon+0.008
ault+0.008
irling+0.008
Neg logit contributions
 Some-0.004
 cheese-0.004
oke-0.004
 pizz-0.004
 Their-0.004
Token-
Token ID12
Feature activation+6.48e-02

Pos logit contributions
 Some+0.050
 cheese+0.046
 There+0.044
oke+0.043
 Their+0.043
Neg logit contributions
irling-0.085
 forth-0.085
ault-0.081
 wrist-0.080
 salon-0.080
Tokenyear
Token ID1941
Feature activation+1.11e-01

Pos logit contributions
 cheese+0.086
 Some+0.082
 There+0.079
oke+0.079
 Their+0.077
Neg logit contributions
irling-0.123
 salon-0.121
 forth-0.120
ault-0.119
liv-0.114
Token-
Token ID12
Feature activation+6.71e-02

Pos logit contributions
 Some+0.126
 cheese+0.120
 There+0.111
oke+0.105
 Their+0.104
Neg logit contributions
irling-0.243
 forth-0.238
ault-0.233
 salon-0.232
 wrist-0.229
Tokenold
Token ID727
Feature activation+6.63e-03

Pos logit contributions
 cheese+0.093
 Some+0.091
 There+0.087
oke+0.085
 Their+0.083
Neg logit contributions
irling-0.123
 salon-0.121
ault-0.118
 forth-0.117
liv-0.115
Token child
Token ID1200
Feature activation+3.07e-02

Pos logit contributions
 Some+0.010
 cheese+0.010
oke+0.009
 There+0.008
 pizz+0.008
Neg logit contributions
 forth-0.012
 salon-0.012
ault-0.011
irling-0.011
 wrist-0.011
Token.
Token ID13
Feature activation+6.25e-03

Pos logit contributions
 Some+0.027
 cheese+0.027
oke+0.023
 pizz+0.022
 There+0.021
Neg logit contributions
 forth-0.075
irling-0.073
 salon-0.072
ault-0.072
 wrist-0.070
Token The
Token ID383
Feature activation+2.34e-02

Pos logit contributions
 cheese+0.005
oke+0.005
 pizz+0.005
 Some+0.005
 of+0.004
Neg logit contributions
 forth-0.015
irling-0.015
 salon-0.014
 wrist-0.014
ault-0.014
TokenOne
Token ID3198
Feature activation+1.04e-02

Pos logit contributions
 Some+0.004
 cheese+0.003
 of+0.003
 time+0.003
 Their+0.003
Neg logit contributions
 forth-0.005
irling-0.004
ault-0.004
 salon-0.004
inge-0.004
Token day
Token ID1110
Feature activation+5.75e-03

Pos logit contributions
 Some+0.017
 cheese+0.017
 pizz+0.017
oke+0.016
izza+0.016
Neg logit contributions
 forth-0.018
 salon-0.016
irling-0.016
ault-0.015
inge-0.015
Token,
Token ID11
Feature activation+9.20e-03

Pos logit contributions
 cheese+0.006
 Some+0.006
oke+0.005
 pizz+0.005
izza+0.005
Neg logit contributions
 forth-0.014
irling-0.013
 salon-0.013
ault-0.013
liv-0.012
Token three
Token ID1115
Feature activation+5.09e-02

Pos logit contributions
 cheese+0.014
 Some+0.014
 of+0.013
oke+0.012
 pizz+0.012
Neg logit contributions
 forth-0.017
irling-0.017
 salon-0.016
ault-0.016
inge-0.015
Token-
Token ID12
Feature activation+7.00e-02

Pos logit contributions
 cheese+0.064
 Some+0.062
 pizz+0.055
izza+0.055
 Their+0.055
Neg logit contributions
 forth-0.109
irling-0.107
 salon-0.100
ault-0.098
inge-0.095
Tokenyear
Token ID1941
Feature activation+1.11e-01

Pos logit contributions
 cheese+0.071
 Some+0.062
 pizz+0.058
 wine+0.057
 There+0.055
Neg logit contributions
 forth-0.166
irling-0.163
 salon-0.161
ault-0.157
inge-0.151
Token-
Token ID12
Feature activation+7.19e-02

Pos logit contributions
 cheese+0.128
 Some+0.125
 There+0.116
oke+0.111
 wine+0.109
Neg logit contributions
irling-0.238
 forth-0.235
 salon-0.221
ault-0.221
inge-0.217
Tokenold
Token ID727
Feature activation+1.40e-02

Pos logit contributions
 cheese+0.094
 Some+0.088
 pizz+0.080
 wine+0.080
 There+0.079
Neg logit contributions
 forth-0.148
irling-0.147
 salon-0.144
ault-0.139
inge-0.134
Token Billy
Token ID15890
Feature activation+2.20e-02

Pos logit contributions
 cheese+0.020
 Some+0.020
 pizz+0.018
oke+0.018
 wine+0.018
Neg logit contributions
 forth-0.027
 salon-0.025
irling-0.024
ault-0.024
 wrist-0.023
Token saw
Token ID2497
Feature activation+2.74e-02

Pos logit contributions
 cheese+0.031
 Some+0.029
 of+0.027
oke+0.026
 pizz+0.026
Neg logit contributions
 forth-0.045
irling-0.044
ault-0.042
 salon-0.042
 wrist-0.040
Token his
Token ID465
Feature activation-2.23e-02

Pos logit contributions
 cheese+0.027
 Some+0.027
oke+0.026
 pizz+0.024
 of+0.023
Neg logit contributions
 forth-0.064
irling-0.062
 salon-0.061
ault-0.059
 wrist-0.057
Token ac
Token ID936
Feature activation-8.40e-03

Pos logit contributions
 forth+0.005
irling+0.005
 salon+0.005
ault+0.005
 wrist+0.005
Neg logit contributions
 Some-0.003
 cheese-0.003
 Their-0.003
oke-0.003
 pizz-0.003
Tokenorn
Token ID1211
Feature activation+4.55e-03

Pos logit contributions
 forth+0.013
irling+0.013
 salon+0.012
ault+0.012
icycle+0.011
Neg logit contributions
 cheese-0.016
 Some-0.015
 pizz-0.014
 Their-0.014
oke-0.014
Token a
Token ID257
Feature activation-3.73e-03

Pos logit contributions
 cheese+0.005
 Some+0.005
oke+0.004
 pizz+0.004
 Their+0.004
Neg logit contributions
 forth-0.010
irling-0.010
ault-0.010
 salon-0.010
 wrist-0.009
Token few
Token ID1178
Feature activation-3.23e-03

Pos logit contributions
 forth+0.008
irling+0.008
ault+0.007
 salon+0.007
 wrist+0.007
Neg logit contributions
 Some-0.005
 cheese-0.005
oke-0.004
 Their-0.004
 pizz-0.004
Token days
Token ID1528
Feature activation+3.56e-02

Pos logit contributions
 forth+0.007
irling+0.006
 salon+0.006
 wrist+0.006
ault+0.006
Neg logit contributions
 Their-0.004
 Some-0.004
oke-0.004
 There-0.004
 cheese-0.004
Token ago
Token ID2084
Feature activation+1.11e-01

Pos logit contributions
 cheese+0.038
 Some+0.036
 of+0.031
 pizz+0.031
oke+0.031
Neg logit contributions
 forth-0.084
irling-0.082
 salon-0.079
ault-0.079
 wrist-0.075
Token so
Token ID523
Feature activation+1.25e-02

Pos logit contributions
 cheese+0.107
 Some+0.107
oke+0.088
 Their+0.087
 pizz+0.087
Neg logit contributions
 forth-0.268
irling-0.262
 salon-0.254
ault-0.252
 wrist-0.247
Token I
Token ID314
Feature activation-1.90e-02

Pos logit contributions
 cheese+0.019
 Some+0.019
 pizz+0.017
oke+0.017
 Their+0.017
Neg logit contributions
 forth-0.024
irling-0.023
ault-0.022
 salon-0.022
 wrist-0.021
Token could
Token ID714
Feature activation-1.16e-02

Pos logit contributions
 forth+0.047
irling+0.046
 salon+0.044
ault+0.044
inge+0.042
Neg logit contributions
 cheese-0.018
 Some-0.017
 of-0.015
 pizz-0.014
oke-0.014
Token have
Token ID423
Feature activation-3.15e-02

Pos logit contributions
 forth+0.024
irling+0.022
icycle+0.022
ault+0.021
 salon+0.021
Neg logit contributions
 cheese-0.017
 of-0.016
 Some-0.015
 time-0.014
 wine-0.014
Token some
Token ID617
Feature activation-3.83e-04

Pos logit contributions
 forth+0.069
irling+0.068
ault+0.065
 salon+0.065
inge+0.062
Neg logit contributions
 cheese-0.039
 Some-0.037
 of-0.033
 pizz-0.033
oke-0.032
Token the
Token ID262
Feature activation-2.15e-02

Pos logit contributions
 cheese+0.001
 Some+0.001
 of+0.001
 time+0.001
 wine+0.001
Neg logit contributions
irling-0.002
 forth-0.002
ault-0.002
 salon-0.002
inge-0.002
Token wardrobe
Token ID35593
Feature activation-2.53e-02

Pos logit contributions
irling+0.043
 forth+0.040
ault+0.039
inge+0.037
 salon+0.036
Neg logit contributions
 cheese-0.035
 Some-0.032
 of-0.031
 time-0.030
 wine-0.030
Token a
Token ID257
Feature activation-1.25e-02

Pos logit contributions
irling+0.064
 forth+0.063
ault+0.061
 salon+0.059
inge+0.059
Neg logit contributions
 of-0.022
 cheese-0.022
 Some-0.019
 ago-0.018
oke-0.017
Token few
Token ID1178
Feature activation-4.10e-04

Pos logit contributions
 forth+0.026
irling+0.025
ault+0.024
 salon+0.024
inge+0.023
Neg logit contributions
 cheese-0.017
 Some-0.016
 of-0.014
 pizz-0.014
oke-0.014
Token days
Token ID1528
Feature activation+3.29e-02

Pos logit contributions
 forth+0.001
irling+0.001
 salon+0.001
ault+0.001
 wrist+0.001
Neg logit contributions
 Some-0.001
 cheese-0.001
oke-0.001
 Their-0.001
izza-0.001
Token ago
Token ID2084
Feature activation+1.11e-01

Pos logit contributions
 cheese+0.029
 Some+0.028
 pizz+0.023
 of+0.023
oke+0.023
Neg logit contributions
 forth-0.083
irling-0.082
 salon-0.079
ault-0.079
 wrist-0.075
Token,
Token ID11
Feature activation+4.53e-03

Pos logit contributions
 Some+0.104
 cheese+0.102
oke+0.085
 pizz+0.082
 Their+0.081
Neg logit contributions
 forth-0.270
irling-0.265
 salon-0.257
ault-0.256
 wrist-0.251
Token so
Token ID523
Feature activation+1.82e-03

Pos logit contributions
 cheese+0.005
 Some+0.005
 of+0.005
oke+0.005
 pizz+0.005
Neg logit contributions
 forth-0.010
irling-0.010
 salon-0.009
ault-0.009
 wrist-0.009
Token she
Token ID673
Feature activation-2.32e-02

Pos logit contributions
 cheese+0.003
 Some+0.003
 of+0.003
 wine+0.003
 There+0.003
Neg logit contributions
irling-0.003
 forth-0.003
ault-0.003
 salon-0.003
icycle-0.003
Token opened
Token ID4721
Feature activation-4.52e-03

Pos logit contributions
 forth+0.042
irling+0.042
 salon+0.040
ault+0.040
inge+0.037
Neg logit contributions
 cheese-0.037
 Some-0.035
 of-0.034
oke-0.032
 pizz-0.032
Token it
Token ID340
Feature activation+1.72e-02

Pos logit contributions
irling+0.011
 forth+0.011
 salon+0.011
ault+0.011
inge+0.010
Neg logit contributions
 cheese-0.004
 Some-0.004
 of-0.004
 time-0.004
 There-0.003
Token it
Token ID340
Feature activation+1.99e-02

Pos logit contributions
 cheese+0.005
 Some+0.005
oke+0.005
 pizz+0.005
 There+0.005
Neg logit contributions
 forth-0.006
irling-0.006
ault-0.005
 salon-0.005
 wrist-0.005
Token away
Token ID1497
Feature activation+9.01e-04

Pos logit contributions
 cheese+0.030
 Some+0.028
 of+0.027
 pizz+0.026
oke+0.026
Neg logit contributions
 forth-0.038
irling-0.038
 salon-0.036
ault-0.035
inge-0.034
Token a
Token ID257
Feature activation+3.71e-03

Pos logit contributions
 cheese+0.001
 Some+0.001
oke+0.001
 pizz+0.001
 There+0.001
Neg logit contributions
 forth-0.002
irling-0.002
ault-0.002
 salon-0.002
 wrist-0.002
Token long
Token ID890
Feature activation+1.66e-02

Pos logit contributions
 Some+0.005
 cheese+0.005
oke+0.005
 There+0.005
 Their+0.004
Neg logit contributions
 forth-0.007
irling-0.007
 salon-0.007
ault-0.007
 wrist-0.007
Token time
Token ID640
Feature activation+3.48e-02

Pos logit contributions
 Some+0.011
 cheese+0.010
oke+0.009
 pizz+0.009
 Their+0.008
Neg logit contributions
 forth-0.045
 salon-0.043
irling-0.043
ault-0.043
 wrist-0.042
Token ago
Token ID2084
Feature activation+1.11e-01

Pos logit contributions
 cheese+0.029
 Some+0.028
 pizz+0.023
oke+0.023
 Their+0.023
Neg logit contributions
 forth-0.088
irling-0.087
 salon-0.084
ault-0.084
 wrist-0.081
Token.
Token ID13
Feature activation+8.82e-03

Pos logit contributions
 Some+0.109
 cheese+0.106
oke+0.089
 Their+0.088
 pizz+0.086
Neg logit contributions
 forth-0.266
irling-0.258
 salon-0.255
ault-0.250
 wrist-0.248
Token It
Token ID632
Feature activation+1.93e-02

Pos logit contributions
 cheese+0.012
 pizz+0.012
oke+0.011
 of+0.011
 time+0.011
Neg logit contributions
 wrist-0.016
 forth-0.016
irling-0.015
 salon-0.015
liv-0.015
Token is
Token ID318
Feature activation-2.36e-03

Pos logit contributions
 cheese+0.022
 Some+0.022
 pizz+0.019
oke+0.019
 of+0.019
Neg logit contributions
 forth-0.043
irling-0.041
 salon-0.040
ault-0.040
inge-0.038
Token not
Token ID407
Feature activation-5.10e-03

Pos logit contributions
 forth+0.004
irling+0.004
 salon+0.003
ault+0.003
liv+0.003
Neg logit contributions
 Some-0.004
oke-0.004
 There-0.004
izza-0.004
 pizz-0.003
Token good
Token ID922
Feature activation-3.30e-02

Pos logit contributions
 forth+0.010
irling+0.009
ault+0.009
 salon+0.009
 wrist+0.009
Neg logit contributions
 Some-0.007
oke-0.007
 There-0.006
 pizz-0.006
 cheese-0.006
Token in
Token ID287
Feature activation-4.35e-03

Pos logit contributions
 cheese+0.009
 Some+0.009
oke+0.008
 pizz+0.007
 of+0.007
Neg logit contributions
 forth-0.024
irling-0.023
ault-0.022
 salon-0.022
 wrist-0.021
Token the
Token ID262
Feature activation-1.40e-02

Pos logit contributions
 forth+0.009
irling+0.008
 salon+0.008
ault+0.008
 wrist+0.008
Neg logit contributions
 cheese-0.006
 Some-0.006
oke-0.005
 pizz-0.005
 Their-0.005
Token park
Token ID3952
Feature activation-2.15e-02

Pos logit contributions
irling+0.025
 forth+0.024
ault+0.023
inge+0.022
 salon+0.021
Neg logit contributions
 cheese-0.024
 Some-0.023
 time-0.023
 of-0.022
 There-0.022
Token many
Token ID867
Feature activation+6.39e-03

Pos logit contributions
 forth+0.055
irling+0.054
ault+0.052
 salon+0.052
inge+0.050
Neg logit contributions
 cheese-0.018
 Some-0.017
 of-0.015
 pizz-0.014
oke-0.014
Token years
Token ID812
Feature activation+7.13e-02

Pos logit contributions
 cheese+0.010
 Some+0.009
oke+0.009
 Their+0.009
 There+0.008
Neg logit contributions
 forth-0.012
irling-0.012
 salon-0.011
ault-0.011
 wrist-0.010
Token ago
Token ID2084
Feature activation+1.11e-01

Pos logit contributions
 cheese+0.069
 Some+0.067
 pizz+0.057
 Their+0.055
 wine+0.052
Neg logit contributions
 forth-0.170
irling-0.169
 salon-0.167
ault-0.162
 wrist-0.156
Token.
Token ID13
Feature activation+3.63e-03

Pos logit contributions
 cheese+0.096
 Some+0.094
oke+0.077
 pizz+0.074
 Their+0.073
Neg logit contributions
 forth-0.278
irling-0.273
 salon-0.265
ault-0.264
 wrist-0.257
Token Toby
Token ID37578
Feature activation+1.14e-03

Pos logit contributions
 cheese+0.005
 Some+0.005
 of+0.004
 pizz+0.004
oke+0.004
Neg logit contributions
 forth-0.007
irling-0.007
 salon-0.007
ault-0.007
 wrist-0.006
Token was
Token ID373
Feature activation-2.88e-03

Pos logit contributions
 cheese+0.001
 of+0.001
 Some+0.001
 Their+0.001
:+0.001
Neg logit contributions
 forth-0.003
irling-0.003
ault-0.003
 salon-0.003
inge-0.003
Token amazed
Token ID24562
Feature activation-1.09e-02

Pos logit contributions
 forth+0.007
irling+0.006
 salon+0.006
ault+0.006
icycle+0.006
Neg logit contributions
 Some-0.003
 cheese-0.003
 of-0.003
 Their-0.003
 time-0.003
Token!
Token ID0
Feature activation-3.04e-03

Pos logit contributions
 forth+0.026
irling+0.025
ault+0.024
 salon+0.024
 wrist+0.023
Neg logit contributions
 cheese-0.012
 Some-0.011
 pizz-0.010
oke-0.010
 Their-0.009
Token mother
Token ID2802
Feature activation+6.96e-03

Pos logit contributions
 Some+0.024
 cheese+0.021
 pizz+0.021
 ago+0.021
oke+0.020
Neg logit contributions
 forth-0.039
ault-0.037
irling-0.037
 salon-0.036
 wrist-0.035
Token took
Token ID1718
Feature activation+5.43e-03

Pos logit contributions
 cheese+0.008
 Some+0.008
 pizz+0.007
oke+0.007
 Their+0.007
Neg logit contributions
 forth-0.015
irling-0.014
 salon-0.014
ault-0.014
icycle-0.013
Token her
Token ID607
Feature activation-2.04e-03

Pos logit contributions
oke+0.010
 ago+0.010
 Some+0.010
 cheese+0.010
 pizz+0.009
Neg logit contributions
 forth-0.008
ault-0.007
irling-0.006
 salon-0.006
handed-0.006
Token 3
Token ID513
Feature activation+3.65e-02

Pos logit contributions
 forth+0.004
 salon+0.003
 wrist+0.003
ault+0.003
ci+0.003
Neg logit contributions
oke-0.003
 Some-0.003
 cheese-0.003
 pizz-0.003
ocol-0.003
Token-
Token ID12
Feature activation+6.52e-02

Pos logit contributions
 Some+0.045
 cheese+0.043
oke+0.040
 Their+0.039
 There+0.039
Neg logit contributions
 forth-0.077
irling-0.075
ault-0.074
inge-0.071
 salon-0.071
Tokenyear
Token ID1941
Feature activation+1.10e-01

Pos logit contributions
 cheese+0.078
 Some+0.070
oke+0.067
 There+0.066
 pizz+0.065
Neg logit contributions
 forth-0.140
irling-0.136
 salon-0.134
ault-0.132
inge-0.128
Token-
Token ID12
Feature activation+6.81e-02

Pos logit contributions
 Some+0.134
 cheese+0.132
 There+0.124
oke+0.117
 Their+0.115
Neg logit contributions
irling-0.224
 forth-0.219
ault-0.213
inge-0.211
 salon-0.208
Tokenold
Token ID727
Feature activation+8.24e-03

Pos logit contributions
 cheese+0.098
 Some+0.092
 There+0.088
oke+0.088
 pizz+0.085
Neg logit contributions
 forth-0.123
irling-0.123
 salon-0.120
ault-0.117
inge-0.113
Token daughter
Token ID4957
Feature activation+1.27e-02

Pos logit contributions
 Some+0.016
 cheese+0.016
oke+0.016
 ago+0.015
izza+0.015
Neg logit contributions
 forth-0.011
 salon-0.010
ault-0.009
 wrist-0.009
irling-0.009
Token to
Token ID284
Feature activation+1.22e-02

Pos logit contributions
 Some+0.016
oke+0.016
 cheese+0.016
 pizz+0.014
 happens+0.014
Neg logit contributions
 forth-0.026
ault-0.024
 salon-0.024
irling-0.023
 wrist-0.023
Token the
Token ID262
Feature activation+5.73e-04

Pos logit contributions
 cheese+0.016
 Some+0.016
oke+0.015
 pizz+0.014
 of+0.014
Neg logit contributions
 forth-0.025
irling-0.024
 salon-0.023
ault-0.023
 wrist-0.023
Token They
Token ID1119
Feature activation-1.01e-02

Pos logit contributions
 cheese+0.006
oke+0.005
 mushrooms+0.005
 wine+0.005
 of+0.005
Neg logit contributions
 salon-0.008
 forth-0.007
irling-0.007
 wrist-0.007
liv-0.007
Token want
Token ID765
Feature activation-1.63e-03

Pos logit contributions
irling+0.024
 forth+0.023
liv+0.023
icycle+0.022
 salon+0.022
Neg logit contributions
 cheese-0.011
 Some-0.011
 of-0.010
 can-0.010
 ago-0.009
Token to
Token ID284
Feature activation-2.43e-02

Pos logit contributions
 salon+0.004
 forth+0.004
irling+0.004
 wrist+0.003
ault+0.003
Neg logit contributions
oke-0.002
 There-0.001
 Some-0.001
ocol-0.001
 cheese-0.001
Token make
Token ID787
Feature activation-1.68e-02

Pos logit contributions
irling+0.056
 forth+0.055
icycle+0.053
liv+0.053
ipping+0.051
Neg logit contributions
 cheese-0.028
 of-0.026
 Some-0.024
 time-0.024
 Their-0.022
Token snow
Token ID6729
Feature activation-2.83e-02

Pos logit contributions
 forth+0.040
irling+0.039
 salon+0.038
ault+0.038
 wrist+0.036
Neg logit contributions
 cheese-0.017
 Some-0.017
oke-0.015
 of-0.014
 There-0.014
Tokenfl
Token ID2704
Feature activation-9.25e-02

Pos logit contributions
 forth+0.055
irling+0.053
 salon+0.051
ault+0.051
 wrist+0.048
Neg logit contributions
 cheese-0.041
 Some-0.041
oke-0.036
 of-0.036
 pizz-0.036
Tokenakes
Token ID1124
Feature activation-3.30e-02

Pos logit contributions
 forth+0.149
irling+0.146
 salon+0.137
ault+0.137
icycle+0.127
Neg logit contributions
 cheese-0.166
 Some-0.162
 of-0.150
oke-0.149
 pizz-0.148
Token for
Token ID329
Feature activation+2.71e-02

Pos logit contributions
 forth+0.076
irling+0.075
 salon+0.072
ault+0.071
icycle+0.070
Neg logit contributions
 cheese-0.037
 Some-0.033
 of-0.032
 pizz-0.030
oke-0.029
Token the
Token ID262
Feature activation-2.86e-03

Pos logit contributions
 Some+0.037
 cheese+0.036
oke+0.033
 of+0.033
 There+0.032
Neg logit contributions
 forth-0.055
irling-0.055
ault-0.052
 salon-0.052
 wrist-0.049
Token window
Token ID4324
Feature activation+8.64e-03

Pos logit contributions
 forth+0.005
 salon+0.005
irling+0.005
ault+0.005
 wrist+0.005
Neg logit contributions
 Some-0.004
 cheese-0.004
oke-0.004
 Their-0.004
 There-0.004
Token.
Token ID13
Feature activation-1.00e-04

Pos logit contributions
 cheese+0.009
 Some+0.009
oke+0.007
 wine+0.007
 Their+0.007
Neg logit contributions
 forth-0.021
 salon-0.020
irling-0.019
ault-0.019
 wrist-0.019
Token and
Token ID290
Feature activation+1.58e-03

Pos logit contributions
 cheese+0.004
 Some+0.004
 of+0.003
 pizz+0.003
oke+0.003
Neg logit contributions
 forth-0.012
irling-0.011
 salon-0.011
ault-0.011
inge-0.010
Token see
Token ID766
Feature activation+1.55e-02

Pos logit contributions
 cheese+0.002
 Some+0.002
 of+0.002
 There+0.002
 Their+0.002
Neg logit contributions
irling-0.003
ault-0.003
 forth-0.003
icycle-0.003
 salon-0.003
Token Tom
Token ID4186
Feature activation-3.49e-02

Pos logit contributions
oke+0.021
 Some+0.021
 cheese+0.020
 There+0.020
 ago+0.020
Neg logit contributions
 forth-0.029
 salon-0.026
irling-0.026
ault-0.025
 wrist-0.024
Token's
Token ID338
Feature activation-3.52e-02

Pos logit contributions
 forth+0.079
irling+0.078
 salon+0.075
ault+0.075
 wrist+0.071
Neg logit contributions
 cheese-0.040
 Some-0.038
 of-0.034
 pizz-0.033
oke-0.033
Token sun
Token ID4252
Feature activation-1.67e-02

Pos logit contributions
 forth+0.059
irling+0.057
ault+0.054
 salon+0.054
 wrist+0.051
Neg logit contributions
 cheese-0.060
 Some-0.060
oke-0.056
 of-0.054
 pizz-0.054
Tokenfl
Token ID2704
Feature activation-9.01e-02

Pos logit contributions
 forth+0.019
irling+0.017
ault+0.016
 salon+0.015
 wrist+0.014
Neg logit contributions
 Some-0.039
 cheese-0.038
oke-0.037
 pizz-0.036
 Their-0.035
Tokenowers
Token ID3618
Feature activation-3.56e-03

Pos logit contributions
 forth+0.144
irling+0.134
 salon+0.124
icycle+0.124
ipping+0.123
Neg logit contributions
 Some-0.165
 cheese-0.162
oke-0.152
 Their-0.151
 pizz-0.148
Token.
Token ID13
Feature activation-7.61e-03

Pos logit contributions
 forth+0.008
irling+0.008
ault+0.008
 salon+0.008
 wrist+0.007
Neg logit contributions
 Some-0.004
 cheese-0.004
 pizz-0.003
oke-0.003
 Their-0.003
Token They
Token ID1119
Feature activation-1.97e-02

Pos logit contributions
 salon+0.015
 sandbox+0.014
 wrist+0.014
liv+0.014
 forth+0.014
Neg logit contributions
 cheese-0.008
ocol-0.008
 pizz-0.008
oke-0.007
 of-0.007
Token are
Token ID389
Feature activation-3.11e-02

Pos logit contributions
irling+0.044
 forth+0.042
icycle+0.041
liv+0.041
ault+0.040
Neg logit contributions
 cheese-0.025
 Some-0.023
 can-0.022
 of-0.022
 There-0.021
Token very
Token ID845
Feature activation-2.57e-03

Pos logit contributions
 forth+0.058
irling+0.057
ault+0.054
 salon+0.053
inge+0.051
Neg logit contributions
 cheese-0.047
 Some-0.047
oke-0.043
 pizz-0.042
 of-0.041
Token beautiful
Token ID4950
Feature activation+7.40e-03

Pos logit contributions
 forth+0.006
irling+0.006
ault+0.005
 salon+0.005
 wrist+0.005
Neg logit contributions
 Some-0.005
 cheese-0.005
oke-0.005
 Their-0.005
 There-0.005
Token--
Token ID438
Feature activation-1.60e-02

Pos logit contributions
 Some+0.013
 cheese+0.012
oke+0.012
 Their+0.012
 There+0.011
Neg logit contributions
 forth-0.013
irling-0.012
ault-0.011
 salon-0.011
 wrist-0.011
Tokenbut
Token ID4360
Feature activation-3.93e-02

Pos logit contributions
 forth+0.029
irling+0.028
ault+0.027
 salon+0.027
inge+0.025
Neg logit contributions
 cheese-0.026
 Some-0.025
 of-0.023
 pizz-0.023
oke-0.023
Token different
Token ID1180
Feature activation-1.37e-02

Pos logit contributions
irling+0.083
 forth+0.082
ault+0.079
 salon+0.079
icycle+0.077
Neg logit contributions
 cheese-0.051
 Some-0.048
 of-0.046
 wine-0.042
 There-0.042
Token--
Token ID438
Feature activation-1.76e-02

Pos logit contributions
 forth+0.027
irling+0.026
 salon+0.025
ault+0.025
 wrist+0.024
Neg logit contributions
 cheese-0.019
 Some-0.019
oke-0.018
 Their-0.017
 There-0.017
Tokenfl
Token ID2704
Feature activation-8.93e-02

Pos logit contributions
 forth+0.033
irling+0.032
 salon+0.031
ault+0.031
inge+0.029
Neg logit contributions
 cheese-0.027
 Some-0.026
 pizz-0.023
oke-0.023
 of-0.023
Tokenowers
Token ID3618
Feature activation-7.98e-03

Pos logit contributions
 forth+0.187
irling+0.182
ault+0.177
 salon+0.176
 wrist+0.168
Neg logit contributions
 cheese-0.117
 Some-0.113
 of-0.105
oke-0.101
 pizz-0.099
Token.
Token ID13
Feature activation+1.07e-03

Pos logit contributions
 forth+0.019
irling+0.018
ault+0.017
 salon+0.017
 wrist+0.017
Neg logit contributions
 cheese-0.009
 Some-0.008
 of-0.007
 pizz-0.007
oke-0.007
Token Each
Token ID5501
Feature activation-3.19e-02

Pos logit contributions
 cheese+0.001
oke+0.001
 pizz+0.001
ocol+0.001
 happens+0.001
Neg logit contributions
 forth-0.002
 salon-0.002
 wrist-0.002
irling-0.002
icycle-0.002
Token morning
Token ID3329
Feature activation-7.53e-03

Pos logit contributions
 forth+0.054
 salon+0.050
irling+0.049
ault+0.046
 wrist+0.045
Neg logit contributions
oke-0.051
 Some-0.050
 cheese-0.049
izza-0.048
 pizz-0.046
Token,
Token ID11
Feature activation+4.00e-03

Pos logit contributions
 forth+0.015
 salon+0.013
irling+0.013
ault+0.013
 wrist+0.012
Neg logit contributions
 Some-0.010
oke-0.010
 cheese-0.009
aly-0.009
izza-0.009
Token window
Token ID4324
Feature activation+1.55e-02

Pos logit contributions
 forth+0.032
irling+0.032
ault+0.030
 salon+0.030
inge+0.028
Neg logit contributions
 cheese-0.026
 Some-0.025
 of-0.023
 pizz-0.023
oke-0.022
Token and
Token ID290
Feature activation-8.81e-03

Pos logit contributions
 cheese+0.017
 Some+0.016
 pizz+0.015
oke+0.015
 wine+0.014
Neg logit contributions
 forth-0.036
 salon-0.034
irling-0.034
ault-0.033
 wrist-0.032
Token saw
Token ID2497
Feature activation+2.32e-02

Pos logit contributions
irling+0.017
 forth+0.017
ault+0.017
 salon+0.016
icycle+0.016
Neg logit contributions
 cheese-0.013
 Some-0.012
 Their-0.011
 of-0.011
 pizz-0.011
Token the
Token ID262
Feature activation-2.63e-02

Pos logit contributions
 cheese+0.032
 Some+0.030
oke+0.029
 pizz+0.029
izza+0.028
Neg logit contributions
 forth-0.045
irling-0.044
 salon-0.044
ault-0.042
 wrist-0.040
Token snow
Token ID6729
Feature activation-3.21e-02

Pos logit contributions
 forth+0.051
irling+0.050
ault+0.047
 salon+0.047
inge+0.044
Neg logit contributions
 cheese-0.039
 Some-0.038
 of-0.035
 pizz-0.034
oke-0.034
Tokenfl
Token ID2704
Feature activation-8.84e-02

Pos logit contributions
 forth+0.066
irling+0.063
 salon+0.061
ault+0.061
 wrist+0.057
Neg logit contributions
 cheese-0.044
 Some-0.044
oke-0.039
 of-0.038
 pizz-0.038
Tokenakes
Token ID1124
Feature activation-2.97e-02

Pos logit contributions
 forth+0.154
irling+0.144
 salon+0.139
icycle+0.134
ault+0.134
Neg logit contributions
 cheese-0.149
 Some-0.147
 Their-0.134
oke-0.133
 pizz-0.133
Token falling
Token ID7463
Feature activation+1.79e-02

Pos logit contributions
 forth+0.069
irling+0.068
 salon+0.066
ault+0.065
icycle+0.063
Neg logit contributions
 cheese-0.032
 Some-0.029
 of-0.028
oke-0.025
 pizz-0.025
Token.
Token ID13
Feature activation-1.48e-03

Pos logit contributions
oke+0.035
 Some+0.035
 cheese+0.035
 pizz+0.034
izza+0.033
Neg logit contributions
 forth-0.028
ault-0.022
irling-0.021
 salon-0.020
itating-0.019
Token She
Token ID1375
Feature activation-2.19e-02

Pos logit contributions
 salon+0.002
 wrist+0.002
irling+0.002
 forth+0.002
icycle+0.002
Neg logit contributions
 pizz-0.003
oke-0.002
 cheese-0.002
 of-0.002
ocol-0.002
Token thought
Token ID1807
Feature activation-6.98e-03

Pos logit contributions
 forth+0.042
irling+0.041
ault+0.040
 salon+0.039
icycle+0.037
Neg logit contributions
 cheese-0.033
 Some-0.032
 of-0.030
 Their-0.029
oke-0.029
Token'm
Token ID1101
Feature activation-3.32e-02

Pos logit contributions
 forth+0.065
irling+0.064
 salon+0.061
ault+0.061
inge+0.058
Neg logit contributions
 cheese-0.038
 Some-0.037
 pizz-0.033
 of-0.032
oke-0.032
Token afraid
Token ID7787
Feature activation-1.26e-02

Pos logit contributions
 forth+0.062
irling+0.061
 salon+0.058
ault+0.058
inge+0.055
Neg logit contributions
 cheese-0.050
 Some-0.048
 pizz-0.044
oke-0.044
 of-0.043
Token I
Token ID314
Feature activation-5.20e-02

Pos logit contributions
 forth+0.024
irling+0.023
 salon+0.022
ault+0.022
 wrist+0.020
Neg logit contributions
 cheese-0.018
 Some-0.017
 pizz-0.017
 Their-0.016
oke-0.016
Token can
Token ID460
Feature activation-3.68e-02

Pos logit contributions
 forth+0.117
irling+0.115
 salon+0.111
ault+0.110
inge+0.105
Neg logit contributions
 cheese-0.059
 Some-0.057
 pizz-0.050
 of-0.049
oke-0.049
Token't
Token ID470
Feature activation-3.21e-02

Pos logit contributions
 forth+0.079
irling+0.079
liv+0.071
ault+0.070
 salon+0.069
Neg logit contributions
 of-0.049
 cheese-0.047
 Some-0.045
 can-0.042
 time-0.041
Token let
Token ID1309
Feature activation-8.72e-02

Pos logit contributions
irling+0.065
 forth+0.063
 salon+0.059
liv+0.059
icycle+0.058
Neg logit contributions
 cheese-0.046
 of-0.046
 Some-0.041
 time-0.040
 wine-0.038
Token it
Token ID340
Feature activation+1.67e-03

Pos logit contributions
 forth+0.152
ault+0.141
 salon+0.140
irling+0.139
 wrist+0.125
Neg logit contributions
 Some-0.141
 cheese-0.141
oke-0.131
 pizz-0.130
 ago-0.128
Token go
Token ID467
Feature activation-8.76e-03

Pos logit contributions
 cheese+0.002
 Some+0.002
 pizz+0.002
oke+0.002
 of+0.002
Neg logit contributions
 forth-0.003
irling-0.003
ault-0.003
 salon-0.003
 wrist-0.003
Token for
Token ID329
Feature activation+2.37e-02

Pos logit contributions
 forth+0.019
irling+0.018
 salon+0.018
ault+0.018
icycle+0.017
Neg logit contributions
 cheese-0.011
 Some-0.011
oke-0.010
 pizz-0.010
 Their-0.009
Token any
Token ID597
Feature activation-7.44e-03

Pos logit contributions
oke+0.031
 Some+0.030
 cheese+0.028
 Their+0.026
 of+0.026
Neg logit contributions
 forth-0.049
irling-0.048
ault-0.046
 salon-0.045
 wrist-0.043
Token less
Token ID1342
Feature activation-4.61e-03

Pos logit contributions
 forth+0.016
 salon+0.014
ault+0.014
irling+0.014
 wrist+0.012
Neg logit contributions
oke-0.010
 Some-0.010
 Their-0.010
izza-0.009
 cheese-0.009
Token and
Token ID290
Feature activation-3.53e-03

Pos logit contributions
 cheese+0.002
 of+0.002
 time+0.001
 Some+0.001
 about+0.001
Neg logit contributions
irling-0.003
 forth-0.003
icycle-0.002
 salon-0.002
inge-0.002
Token Lib
Token ID7980
Feature activation-2.37e-02

Pos logit contributions
irling+0.007
icycle+0.007
 forth+0.006
inge+0.006
 salon+0.006
Neg logit contributions
 of-0.005
 cheese-0.005
 time-0.005
 Some-0.005
 about-0.005
Tokenby
Token ID1525
Feature activation+1.74e-02

Pos logit contributions
 forth+0.046
irling+0.045
ault+0.043
 salon+0.043
 wrist+0.040
Neg logit contributions
 cheese-0.035
 Some-0.034
 of-0.031
 pizz-0.031
oke-0.031
Token couldn
Token ID3521
Feature activation+3.32e-03

Pos logit contributions
 cheese+0.024
 of+0.024
 Some+0.023
 pizz+0.022
oke+0.021
Neg logit contributions
 forth-0.035
irling-0.034
 salon-0.033
ault-0.033
icycle-0.031
Token't
Token ID470
Feature activation-2.66e-02

Pos logit contributions
 Some+0.005
 cheese+0.005
 of+0.005
 There+0.005
 time+0.005
Neg logit contributions
 forth-0.006
irling-0.006
ault-0.006
 salon-0.006
 wrist-0.005
Token WA
Token ID16400
Feature activation-8.56e-02

Pos logit contributions
irling+0.044
 forth+0.043
icycle+0.041
 salon+0.040
liv+0.039
Neg logit contributions
 cheese-0.047
 of-0.046
 Some-0.045
 time-0.044
 Their-0.041
TokenIT
Token ID2043
Feature activation-3.42e-02

Pos logit contributions
 forth+0.111
irling+0.104
inge+0.096
 salon+0.096
ault+0.095
Neg logit contributions
 cheese-0.173
 Some-0.170
 time-0.166
 pizz-0.165
oke-0.161
Token to
Token ID284
Feature activation-4.33e-02

Pos logit contributions
 forth+0.076
irling+0.075
 salon+0.072
inge+0.071
 wrist+0.069
Neg logit contributions
 cheese-0.038
 of-0.038
 Some-0.035
 time-0.032
oke-0.032
Token plan
Token ID1410
Feature activation-1.26e-02

Pos logit contributions
irling+0.090
 forth+0.087
 salon+0.084
icycle+0.084
liv+0.083
Neg logit contributions
 cheese-0.057
 time-0.056
 of-0.055
 Some-0.049
 pizz-0.049
Token the
Token ID262
Feature activation-4.20e-03

Pos logit contributions
 forth+0.027
irling+0.026
ault+0.025
 salon+0.025
inge+0.024
Neg logit contributions
 cheese-0.016
 Some-0.015
 of-0.015
 pizz-0.014
 wine-0.013
Token next
Token ID1306
Feature activation+1.41e-02

Pos logit contributions
irling+0.007
 forth+0.007
liv+0.007
inge+0.007
 salon+0.006
Neg logit contributions
 cheese-0.007
 time-0.007
 of-0.007
 pizz-0.007
 wine-0.006
Token much
Token ID881
Feature activation+1.05e-03

Pos logit contributions
 forth+0.040
irling+0.040
ault+0.038
 salon+0.038
inge+0.036
Neg logit contributions
 cheese-0.019
 Some-0.018
oke-0.017
 pizz-0.017
izza-0.016
Token lighter
Token ID14871
Feature activation+3.08e-02

Pos logit contributions
 cheese+0.001
 Some+0.001
 of+0.001
oke+0.001
 pizz+0.001
Neg logit contributions
 forth-0.002
irling-0.002
ault-0.002
 salon-0.002
inge-0.002
Token and
Token ID290
Feature activation-5.77e-04

Pos logit contributions
 cheese+0.031
 Some+0.031
 pizz+0.026
oke+0.025
 Their+0.025
Neg logit contributions
 forth-0.074
irling-0.072
ault-0.069
 salon-0.069
 wrist-0.066
Token it
Token ID340
Feature activation-7.03e-03

Pos logit contributions
 forth+0.001
irling+0.001
ault+0.001
 salon+0.001
icycle+0.001
Neg logit contributions
 cheese-0.001
 Some-0.001
 of-0.001
 pizz-0.001
oke-0.001
Token made
Token ID925
Feature activation-1.11e-02

Pos logit contributions
 forth+0.016
irling+0.016
ault+0.016
 wrist+0.016
 salon+0.015
Neg logit contributions
 of-0.008
 cheese-0.007
 Some-0.007
 time-0.007
 can-0.007
Token Br
Token ID1709
Feature activation-8.49e-02

Pos logit contributions
 forth+0.020
irling+0.019
ault+0.018
 salon+0.017
liv+0.017
Neg logit contributions
 cheese-0.018
 Some-0.017
oke-0.017
 pizz-0.016
 ago-0.016
Tokenandy
Token ID10757
Feature activation-4.31e-02

Pos logit contributions
 forth+0.129
irling+0.125
 salon+0.119
ault+0.119
 wrist+0.111
Neg logit contributions
 cheese-0.157
 Some-0.154
 of-0.147
oke-0.146
 pizz-0.140
Token feel
Token ID1254
Feature activation-1.49e-02

Pos logit contributions
 forth+0.093
irling+0.090
icycle+0.088
 salon+0.087
liv+0.087
Neg logit contributions
 of-0.056
 cheese-0.052
 Some-0.050
 time-0.046
 Their-0.044
Token so
Token ID523
Feature activation-1.63e-02

Pos logit contributions
 forth+0.030
irling+0.030
ault+0.028
 salon+0.028
inge+0.027
Neg logit contributions
 cheese-0.021
 Some-0.020
oke-0.018
 pizz-0.018
 of-0.017
Token happy
Token ID3772
Feature activation-1.05e-02

Pos logit contributions
 forth+0.035
 salon+0.034
irling+0.033
icycle+0.033
ault+0.033
Neg logit contributions
 of-0.021
 cheese-0.020
 Some-0.020
 time-0.018
 There-0.018
Token.
Token ID13
Feature activation-9.33e-03

Pos logit contributions
 forth+0.030
irling+0.029
ault+0.029
 salon+0.029
inge+0.028
Neg logit contributions
 cheese-0.006
 of-0.006
 Some-0.005
 wine-0.004
 time-0.004
Token naughty
Token ID45128
Feature activation+2.20e-03

Pos logit contributions
 forth+0.033
irling+0.033
 salon+0.031
ault+0.031
inge+0.029
Neg logit contributions
 cheese-0.025
 Some-0.024
 of-0.022
 pizz-0.022
oke-0.022
Token.
Token ID13
Feature activation-2.40e-03

Pos logit contributions
 cheese+0.002
 Some+0.002
 pizz+0.002
 Their+0.002
izza+0.002
Neg logit contributions
 forth-0.005
irling-0.005
 salon-0.005
ault-0.005
icycle-0.005
Token He
Token ID679
Feature activation-9.80e-03

Pos logit contributions
 salon+0.004
 wrist+0.004
 forth+0.004
liv+0.004
icycle+0.004
Neg logit contributions
 cheese-0.003
 facts-0.003
 happened-0.003
 mushrooms-0.003
 wine-0.003
Token does
Token ID857
Feature activation-1.59e-02

Pos logit contributions
 forth+0.022
irling+0.022
ault+0.021
 salon+0.021
 wrist+0.020
Neg logit contributions
 cheese-0.012
 Some-0.011
 of-0.010
oke-0.010
 pizz-0.010
Token not
Token ID407
Feature activation-2.68e-02

Pos logit contributions
 forth+0.036
icycle+0.033
irling+0.033
 salon+0.032
ault+0.032
Neg logit contributions
 cheese-0.019
 Some-0.018
 time-0.018
 of-0.018
 Their-0.017
Token let
Token ID1309
Feature activation-8.45e-02

Pos logit contributions
irling+0.068
 forth+0.067
 salon+0.064
icycle+0.064
liv+0.063
Neg logit contributions
 cheese-0.024
 of-0.023
 Some-0.021
 time-0.020
oke-0.018
Token anyone
Token ID2687
Feature activation-1.08e-02

Pos logit contributions
 forth+0.144
 salon+0.137
ault+0.137
irling+0.122
liv+0.119
Neg logit contributions
 cheese-0.128
 ago-0.127
 Some-0.126
oke-0.123
lic-0.116
Token go
Token ID467
Feature activation-3.03e-02

Pos logit contributions
 forth+0.021
irling+0.020
ault+0.019
 salon+0.019
 wrist+0.018
Neg logit contributions
 cheese-0.017
 Some-0.016
 pizz-0.015
oke-0.014
 wine-0.014
Token on
Token ID319
Feature activation-2.15e-02

Pos logit contributions
irling+0.077
 forth+0.076
ault+0.074
 salon+0.073
inge+0.072
Neg logit contributions
 cheese-0.024
 of-0.024
 Some-0.024
oke-0.019
 time-0.019
Token the
Token ID262
Feature activation-1.62e-02

Pos logit contributions
 forth+0.053
irling+0.053
ault+0.051
inge+0.051
 salon+0.050
Neg logit contributions
 cheese-0.020
 Some-0.018
 of-0.017
 time-0.016
 pizz-0.015
Token slide
Token ID10649
Feature activation-5.43e-02

Pos logit contributions
irling+0.022
ica+0.021
fer+0.020
inge+0.020
ault+0.020
Neg logit contributions
 time-0.034
 of-0.031
 can-0.030
 cheese-0.030
 words-0.029
Token was
Token ID373
Feature activation-7.07e-03

Pos logit contributions
 cheese+0.009
 Some+0.009
 of+0.008
 pizz+0.008
oke+0.007
Neg logit contributions
 forth-0.014
irling-0.014
ault-0.013
 salon-0.013
 wrist-0.013
Token tough
Token ID5802
Feature activation+3.00e-03

Pos logit contributions
 forth+0.015
irling+0.015
 salon+0.014
ault+0.014
inge+0.014
Neg logit contributions
 cheese-0.009
 Some-0.008
 of-0.007
oke-0.007
 pizz-0.007
Token and
Token ID290
Feature activation-1.99e-02

Pos logit contributions
 cheese+0.003
 Some+0.003
 of+0.002
 pizz+0.002
oke+0.002
Neg logit contributions
 forth-0.007
irling-0.007
ault-0.007
 salon-0.007
inge-0.007
Token didn
Token ID1422
Feature activation-1.04e-02

Pos logit contributions
 forth+0.040
irling+0.039
 salon+0.036
ault+0.036
inge+0.035
Neg logit contributions
 cheese-0.028
 Some-0.027
oke-0.026
 pizz-0.025
 wine-0.024
Token't
Token ID470
Feature activation-1.90e-02

Pos logit contributions
 forth+0.019
irling+0.018
 salon+0.017
ault+0.017
 wrist+0.016
Neg logit contributions
 Some-0.017
 cheese-0.017
 of-0.016
 Their-0.015
 There-0.015
Token let
Token ID1309
Feature activation-8.41e-02

Pos logit contributions
irling+0.047
 forth+0.046
 salon+0.044
icycle+0.044
liv+0.043
Neg logit contributions
 cheese-0.018
 of-0.017
 Some-0.017
 time-0.016
oke-0.014
Token anything
Token ID1997
Feature activation-2.72e-02

Pos logit contributions
 forth+0.156
ault+0.149
 salon+0.142
irling+0.141
icycle+0.129
Neg logit contributions
 cheese-0.126
 Some-0.124
oke-0.117
 ago-0.115
 pizz-0.113
Token stop
Token ID2245
Feature activation-3.12e-02

Pos logit contributions
 forth+0.063
irling+0.061
ault+0.059
 salon+0.058
 wrist+0.056
Neg logit contributions
 cheese-0.030
 Some-0.030
 pizz-0.026
oke-0.025
 Their-0.024
Token him
Token ID683
Feature activation+2.71e-02

Pos logit contributions
irling+0.078
 forth+0.078
 salon+0.077
ault+0.075
inge+0.073
Neg logit contributions
 cheese-0.026
 Some-0.024
 of-0.022
oke-0.020
 pizz-0.020
Token.
Token ID13
Feature activation-8.85e-03

Pos logit contributions
 cheese+0.026
 Some+0.025
 pizz+0.021
oke+0.021
 of+0.020
Neg logit contributions
 forth-0.067
irling-0.065
ault-0.064
 salon-0.063
 wrist-0.060
Token Every
Token ID3887
Feature activation-1.86e-02

Pos logit contributions
 forth+0.018
icycle+0.018
 wrist+0.017
 salon+0.017
liv+0.016
Neg logit contributions
 cheese-0.010
ocol-0.010
oke-0.010
 wine-0.009
 mushrooms-0.009
Token strong
Token ID1913
Feature activation+4.84e-05

Pos logit contributions
 forth+0.053
irling+0.047
 salon+0.047
ault+0.045
 wrist+0.043
Neg logit contributions
oke-0.036
 Some-0.035
 pizz-0.034
 cheese-0.033
izza-0.032
Token like
Token ID588
Feature activation-1.92e-02

Pos logit contributions
oke+0.000
izza+0.000
 Some+0.000
 Their+0.000
 pizz+0.000
Neg logit contributions
 forth-0.000
ault-0.000
irling-0.000
 salon-0.000
 wrist-0.000
Token the
Token ID262
Feature activation-1.90e-02

Pos logit contributions
 forth+0.035
 salon+0.033
irling+0.033
ault+0.032
 wrist+0.030
Neg logit contributions
oke-0.029
 Some-0.027
 cheese-0.025
 pizz-0.024
izza-0.024
Token other
Token ID584
Feature activation-3.35e-02

Pos logit contributions
 forth+0.039
irling+0.035
 salon+0.035
ault+0.035
 wrist+0.033
Neg logit contributions
 Some-0.026
oke-0.026
 cheese-0.025
 Their-0.024
 pizz-0.023
Token sun
Token ID4252
Feature activation-1.96e-02

Pos logit contributions
 forth+0.066
irling+0.056
 salon+0.054
 sandbox+0.053
ault+0.053
Neg logit contributions
oke-0.048
 Some-0.048
 cheese-0.048
izza-0.046
 Their-0.046
Tokenfl
Token ID2704
Feature activation-8.41e-02

Pos logit contributions
 forth+0.032
 salon+0.028
irling+0.028
ault+0.027
 wrist+0.025
Neg logit contributions
 Some-0.036
 cheese-0.036
 pizz-0.034
oke-0.033
 Their-0.033
Tokenowers
Token ID3618
Feature activation-3.74e-03

Pos logit contributions
 forth+0.135
irling+0.130
 salon+0.122
icycle+0.117
ipping+0.116
Neg logit contributions
 cheese-0.147
 Some-0.145
 Their-0.136
oke-0.135
 pizz-0.134
Token.
Token ID13
Feature activation-6.20e-03

Pos logit contributions
 forth+0.008
irling+0.008
ault+0.008
 salon+0.007
 wrist+0.007
Neg logit contributions
 Some-0.005
 cheese-0.004
 pizz-0.004
oke-0.004
izza-0.004
Token The
Token ID383
Feature activation+1.18e-02

Pos logit contributions
 wrist+0.011
 forth+0.011
irling+0.010
 swing+0.010
 salon+0.010
Neg logit contributions
ocol-0.009
oke-0.009
 ago-0.008
 pizz-0.008
 facts-0.007
Token weak
Token ID4939
Feature activation-1.46e-02

Pos logit contributions
 Some+0.017
oke+0.016
 cheese+0.015
 Their+0.015
 pizz+0.015
Neg logit contributions
 forth-0.023
irling-0.021
ault-0.020
 salon-0.020
 sandbox-0.020
Token sun
Token ID4252
Feature activation-1.88e-02

Pos logit contributions
 forth+0.028
irling+0.024
 salon+0.024
inge+0.023
ault+0.023
Neg logit contributions
 Some-0.021
oke-0.021
 cheese-0.020
 pizz-0.020
 Their-0.020
Token saw
Token ID2497
Feature activation+1.77e-02

Pos logit contributions
irling+0.055
icycle+0.051
 salon+0.051
ault+0.051
 forth+0.051
Neg logit contributions
 of-0.024
 Some-0.023
 cheese-0.022
 Their-0.022
 can-0.021
Token the
Token ID262
Feature activation-1.99e-02

Pos logit contributions
 Some+0.025
 cheese+0.025
oke+0.025
 pizz+0.024
 ago+0.023
Neg logit contributions
 forth-0.034
irling-0.031
 salon-0.031
ault-0.030
 wrist-0.028
Token veil
Token ID30615
Feature activation-3.03e-02

Pos logit contributions
irling+0.038
 forth+0.037
liv+0.036
icycle+0.036
fer+0.035
Neg logit contributions
 time-0.033
 cheese-0.032
 words-0.030
 can-0.028
 of-0.028
Token and
Token ID290
Feature activation-3.00e-02

Pos logit contributions
 forth+0.076
irling+0.076
ault+0.073
 salon+0.073
icycle+0.070
Neg logit contributions
 cheese-0.027
 Some-0.024
 of-0.023
 wine-0.020
oke-0.020
Token couldn
Token ID3521
Feature activation-1.51e-02

Pos logit contributions
irling+0.063
 forth+0.062
ault+0.060
icycle+0.059
 salon+0.059
Neg logit contributions
 cheese-0.040
 Some-0.039
 of-0.037
 Their-0.036
 wine-0.034
Tokenâ
Token ID22940
Feature activation-8.40e-02

Pos logit contributions
 forth+0.026
irling+0.025
ault+0.024
 salon+0.024
 wrist+0.023
Neg logit contributions
 cheese-0.025
 Some-0.025
 of-0.024
 There-0.023
 Their-0.022
Token€
Token ID26391
Feature activation-5.25e-02

Pos logit contributions
 forth+0.147
irling+0.144
 salon+0.137
ault+0.134
icycle+0.130
Neg logit contributions
 cheese-0.136
 Some-0.131
 time-0.125
 Their-0.124
 of-0.123
Tokenâ„¢
Token ID8151
Feature activation-2.51e-02

Pos logit contributions
 forth+0.105
irling+0.097
 salon+0.094
ault+0.091
inge+0.090
Neg logit contributions
 cheese-0.077
 Some-0.075
 There-0.072
 of-0.071
 Their-0.069
Tokent
Token ID83
Feature activation-1.57e-02

Pos logit contributions
 forth+0.058
irling+0.057
 salon+0.056
ault+0.056
icycle+0.053
Neg logit contributions
 cheese-0.027
 Some-0.024
 pizz-0.022
 wine-0.021
 mushrooms-0.021
Token wait
Token ID4043
Feature activation-2.49e-02

Pos logit contributions
irling+0.032
 forth+0.032
 salon+0.030
icycle+0.029
ault+0.029
Neg logit contributions
 cheese-0.022
 Some-0.022
 of-0.021
 Their-0.019
 There-0.019
Token to
Token ID284
Feature activation+4.19e-03

Pos logit contributions
 forth+0.070
irling+0.069
ault+0.067
 salon+0.067
 wrist+0.064
Neg logit contributions
 cheese-0.015
 Some-0.014
 of-0.010
oke-0.010
 pizz-0.010
Token was
Token ID373
Feature activation+1.78e-04

Pos logit contributions
 cheese+0.013
 Some+0.011
 of+0.011
oke+0.010
 pizz+0.010
Neg logit contributions
irling-0.023
 forth-0.022
ault-0.022
 salon-0.022
icycle-0.021
Token scared
Token ID12008
Feature activation-8.43e-03

Pos logit contributions
 cheese+0.000
 Some+0.000
 of+0.000
 pizz+0.000
 Their+0.000
Neg logit contributions
 forth-0.000
irling-0.000
 salon-0.000
ault-0.000
icycle-0.000
Token and
Token ID290
Feature activation-2.82e-02

Pos logit contributions
 forth+0.017
ault+0.014
irling+0.014
 salon+0.013
itating+0.013
Neg logit contributions
izza-0.013
 pizz-0.013
 cheese-0.012
emon-0.011
engu-0.011
Token wouldn
Token ID3636
Feature activation-2.48e-02

Pos logit contributions
 forth+0.052
irling+0.048
 salon+0.046
ault+0.045
inge+0.043
Neg logit contributions
 cheese-0.046
 Some-0.046
oke-0.042
 pizz-0.042
 of-0.041
Token't
Token ID470
Feature activation-2.04e-02

Pos logit contributions
 forth+0.048
irling+0.046
 salon+0.044
 wrist+0.042
ault+0.042
Neg logit contributions
 of-0.037
 Some-0.036
 cheese-0.036
 There-0.033
oke-0.032
Token let
Token ID1309
Feature activation-8.40e-02

Pos logit contributions
irling+0.042
 forth+0.042
 salon+0.040
ault+0.039
icycle+0.038
Neg logit contributions
 cheese-0.028
 Some-0.026
 of-0.025
oke-0.023
 pizz-0.023
Token them
Token ID606
Feature activation+7.43e-04

Pos logit contributions
 forth+0.140
ault+0.132
 salon+0.127
irling+0.114
 wrist+0.111
Neg logit contributions
 Some-0.139
oke-0.137
 cheese-0.134
 ago-0.132
 pizz-0.128
Token near
Token ID1474
Feature activation+5.54e-03

Pos logit contributions
 cheese+0.001
 Some+0.001
 pizz+0.001
oke+0.001
 of+0.001
Neg logit contributions
 forth-0.001
irling-0.001
ault-0.001
 salon-0.001
 wrist-0.001
Token.
Token ID13
Feature activation-1.37e-02

Pos logit contributions
oke+0.008
 Some+0.008
 cheese+0.008
izza+0.007
 pizz+0.007
Neg logit contributions
 forth-0.011
irling-0.010
ault-0.010
 salon-0.010
 wrist-0.010
Token But
Token ID887
Feature activation-3.36e-02

Pos logit contributions
 forth+0.032
 salon+0.031
irling+0.031
 wrist+0.030
ault+0.030
Neg logit contributions
 cheese-0.013
oke-0.012
 Some-0.012
 of-0.011
 pizz-0.011
Token the
Token ID262
Feature activation+1.23e-03

Pos logit contributions
 forth+0.056
irling+0.053
 salon+0.051
ault+0.050
 wrist+0.047
Neg logit contributions
 cheese-0.059
 Some-0.058
oke-0.054
 pizz-0.054
 of-0.053
Token Daisy
Token ID40355
Feature activation-2.91e-02

Pos logit contributions
irling+0.009
 forth+0.009
liv+0.009
 salon+0.009
 wrist+0.008
Neg logit contributions
 cheese-0.006
 pizz-0.006
oke-0.005
ocol-0.005
 facts-0.005
Token was
Token ID373
Feature activation-1.22e-02

Pos logit contributions
 forth+0.067
ault+0.067
 salon+0.066
irling+0.066
liv+0.063
Neg logit contributions
 cheese-0.030
 of-0.028
 Some-0.027
 can-0.026
:-0.023
Token amazed
Token ID24562
Feature activation-1.90e-02

Pos logit contributions
 forth+0.030
 salon+0.029
irling+0.028
icycle+0.028
ault+0.028
Neg logit contributions
 of-0.012
 cheese-0.011
 Some-0.011
 about-0.011
 time-0.010
Token and
Token ID290
Feature activation-2.65e-02

Pos logit contributions
 forth+0.043
irling+0.041
ault+0.040
 salon+0.039
 wrist+0.037
Neg logit contributions
 cheese-0.023
 Some-0.022
 pizz-0.020
oke-0.019
 Their-0.019
Token couldn
Token ID3521
Feature activation-1.51e-02

Pos logit contributions
icycle+0.060
 salon+0.059
ault+0.058
irling+0.057
 forth+0.055
Neg logit contributions
 of-0.031
 cheese-0.028
 Their-0.027
 Some-0.027
 There-0.027
Tokenâ
Token ID22940
Feature activation-8.39e-02

Pos logit contributions
 forth+0.024
irling+0.023
ault+0.022
 salon+0.022
inge+0.020
Neg logit contributions
 cheese-0.027
 Some-0.027
 of-0.025
 pizz-0.025
oke-0.025
Token€
Token ID26391
Feature activation-5.42e-02

Pos logit contributions
 forth+0.141
irling+0.137
 salon+0.131
ault+0.128
icycle+0.122
Neg logit contributions
 cheese-0.141
 Some-0.136
 time-0.132
 Their-0.129
 of-0.129
Tokenâ„¢
Token ID8151
Feature activation-2.58e-02

Pos logit contributions
 forth+0.118
irling+0.104
 salon+0.103
inge+0.101
ault+0.101
Neg logit contributions
 There-0.069
 Some-0.068
 cheese-0.066
 of-0.064
 time-0.064
Tokent
Token ID83
Feature activation-2.45e-02

Pos logit contributions
 forth+0.059
irling+0.058
 salon+0.056
ault+0.056
icycle+0.054
Neg logit contributions
 cheese-0.029
 Some-0.027
 pizz-0.024
 wine-0.023
oke-0.022
Token take
Token ID1011
Feature activation-3.55e-02

Pos logit contributions
 forth+0.044
irling+0.043
ault+0.041
 salon+0.041
inge+0.038
Neg logit contributions
 cheese-0.040
 Some-0.039
 of-0.035
 pizz-0.035
oke-0.035
Token her
Token ID607
Feature activation-2.18e-02

Pos logit contributions
 forth+0.076
irling+0.074
ault+0.072
 salon+0.071
 wrist+0.067
Neg logit contributions
 cheese-0.045
 Some-0.043
oke-0.040
 pizz-0.039
 of-0.038
Token lots
Token ID6041
Feature activation-2.33e-02

Pos logit contributions
oke+0.019
 cheese+0.019
 Some+0.018
 ago+0.017
 pizz+0.017
Neg logit contributions
 forth-0.033
irling-0.032
 salon-0.031
ault-0.031
 wrist-0.029
Token of
Token ID286
Feature activation+1.50e-02

Pos logit contributions
 forth+0.055
irling+0.055
ault+0.052
 salon+0.052
ipping+0.050
Neg logit contributions
izza-0.018
 Their-0.017
 Some-0.016
 cheese-0.015
 ago-0.015
Token trees
Token ID7150
Feature activation+1.19e-02

Pos logit contributions
izza+0.022
oke+0.022
 Their+0.022
 cheese+0.021
 Some+0.021
Neg logit contributions
 forth-0.026
irling-0.025
 sandbox-0.023
ault-0.022
 salon-0.022
Token and
Token ID290
Feature activation-1.47e-02

Pos logit contributions
 cheese+0.010
 Some+0.010
 pizz+0.008
 of+0.008
oke+0.008
Neg logit contributions
 forth-0.030
irling-0.030
ault-0.028
 salon-0.028
 wrist-0.027
Token wild
Token ID4295
Feature activation+1.44e-02

Pos logit contributions
 forth+0.028
irling+0.026
ault+0.025
 salon+0.025
 sandbox+0.023
Neg logit contributions
oke-0.021
 cheese-0.020
 Some-0.020
 Their-0.020
izza-0.019
Tokenfl
Token ID2704
Feature activation-8.39e-02

Pos logit contributions
oke+0.026
izza+0.026
 Their+0.025
 Some+0.025
 cheese+0.024
Neg logit contributions
 forth-0.022
irling-0.018
 sandbox-0.017
 playground-0.015
 believing-0.015
Tokenowers
Token ID3618
Feature activation-5.46e-03

Pos logit contributions
 forth+0.138
irling+0.138
icycle+0.125
ault+0.124
 salon+0.122
Neg logit contributions
 cheese-0.145
 Some-0.141
 wine-0.129
 pizz-0.129
 Their-0.128
Token.
Token ID13
Feature activation-6.17e-03

Pos logit contributions
 forth+0.013
irling+0.013
ault+0.012
 salon+0.012
 wrist+0.012
Neg logit contributions
 Some-0.005
 cheese-0.005
 pizz-0.004
 Their-0.004
oke-0.004
Token As
Token ID1081
Feature activation-1.15e-02

Pos logit contributions
 forth+0.012
icycle+0.011
 salon+0.011
 wrist+0.011
 sandbox+0.011
Neg logit contributions
 cheese-0.007
oke-0.007
ocol-0.007
 pizz-0.006
 happens-0.006
Token he
Token ID339
Feature activation+1.09e-02

Pos logit contributions
 forth+0.025
irling+0.025
 salon+0.024
ault+0.024
 wrist+0.023
Neg logit contributions
 cheese-0.014
 Some-0.013
 of-0.012
 pizz-0.012
oke-0.012
Token stepped
Token ID10764
Feature activation-1.93e-02

Pos logit contributions
 cheese+0.019
 Some+0.018
oke+0.017
 pizz+0.017
 wine+0.017
Neg logit contributions
 forth-0.019
irling-0.018
ault-0.017
 salon-0.017
inge-0.016
Token'
Token ID6
Feature activation+2.24e-03

Pos logit contributions
 forth+0.003
irling+0.003
ault+0.003
 salon+0.003
inge+0.003
Neg logit contributions
 cheese-0.001
 Some-0.001
 of-0.001
 pizz-0.001
oke-0.001
Token things
Token ID1243
Feature activation+4.47e-03

Pos logit contributions
oke+0.003
 Some+0.003
ocol+0.003
 cheese+0.003
 happens+0.003
Neg logit contributions
 forth-0.004
 wrist-0.004
 salon-0.004
icycle-0.004
ault-0.003
Token and
Token ID290
Feature activation-5.56e-03

Pos logit contributions
 cheese+0.005
 Some+0.005
oke+0.004
 pizz+0.004
 Their+0.004
Neg logit contributions
 forth-0.010
irling-0.010
ault-0.010
 salon-0.009
 wrist-0.009
Token didn
Token ID1422
Feature activation-1.29e-02

Pos logit contributions
 forth+0.010
irling+0.010
 salon+0.010
ault+0.010
 wrist+0.009
Neg logit contributions
 cheese-0.009
 Some-0.008
oke-0.008
 of-0.008
 pizz-0.008
Token't
Token ID470
Feature activation-2.38e-02

Pos logit contributions
 forth+0.021
irling+0.021
ault+0.019
 salon+0.019
 wrist+0.018
Neg logit contributions
 cheese-0.023
 Some-0.022
 of-0.021
 pizz-0.020
oke-0.020
Token let
Token ID1309
Feature activation-8.39e-02

Pos logit contributions
irling+0.058
 forth+0.055
liv+0.054
icycle+0.053
 salon+0.053
Neg logit contributions
 cheese-0.026
 of-0.025
 Some-0.025
 time-0.022
 Their-0.021
Token them
Token ID606
Feature activation-1.74e-03

Pos logit contributions
 forth+0.150
ault+0.144
 salon+0.135
irling+0.130
pping+0.121
Neg logit contributions
 cheese-0.126
 Some-0.124
oke-0.121
 ago-0.121
 pizz-0.114
Token play
Token ID711
Feature activation-4.21e-02

Pos logit contributions
 forth+0.003
irling+0.003
 salon+0.003
ault+0.003
icycle+0.003
Neg logit contributions
 cheese-0.003
 Some-0.003
 of-0.002
 pizz-0.002
 Their-0.002
Token with
Token ID351
Feature activation-2.11e-02

Pos logit contributions
 forth+0.077
irling+0.075
ault+0.073
 salon+0.072
 wrist+0.070
Neg logit contributions
 cheese-0.063
 Some-0.062
oke-0.060
izza-0.056
 pizz-0.056
Token him
Token ID683
Feature activation+3.02e-02

Pos logit contributions
 forth+0.041
irling+0.039
ault+0.038
 salon+0.038
 wrist+0.036
Neg logit contributions
oke-0.029
 Some-0.027
 There-0.026
 cheese-0.026
 ago-0.025
Token.
Token ID13
Feature activation-3.32e-03

Pos logit contributions
 Some+0.030
 cheese+0.029
oke+0.025
 pizz+0.025
 Their+0.024
Neg logit contributions
 forth-0.073
irling-0.070
ault-0.069
 salon-0.068
 wrist-0.066
Token,
Token ID11
Feature activation-6.28e-03

Pos logit contributions
 cheese+0.051
 Some+0.051
oke+0.045
izza+0.044
 wine+0.043
Neg logit contributions
 forth-0.116
 salon-0.108
irling-0.105
ault-0.105
 wrist-0.105
Token but
Token ID475
Feature activation-3.61e-02

Pos logit contributions
 forth+0.014
irling+0.014
ault+0.013
 salon+0.013
inge+0.012
Neg logit contributions
 cheese-0.007
 Some-0.007
 of-0.006
 pizz-0.006
oke-0.006
Token he
Token ID339
Feature activation-1.82e-02

Pos logit contributions
 forth+0.078
irling+0.077
 salon+0.073
ault+0.073
inge+0.070
Neg logit contributions
 cheese-0.046
 Some-0.044
 of-0.040
oke-0.039
 pizz-0.039
Token did
Token ID750
Feature activation-1.48e-02

Pos logit contributions
 forth+0.040
irling+0.039
ault+0.038
 salon+0.037
 wrist+0.036
Neg logit contributions
 cheese-0.022
 Some-0.021
 of-0.020
oke-0.019
 pizz-0.019
Token not
Token ID407
Feature activation-1.86e-02

Pos logit contributions
 forth+0.033
 salon+0.032
irling+0.031
icycle+0.031
ault+0.031
Neg logit contributions
 cheese-0.016
 time-0.016
 of-0.015
 about-0.015
 Some-0.015
Token let
Token ID1309
Feature activation-8.37e-02

Pos logit contributions
irling+0.043
 forth+0.042
 salon+0.041
icycle+0.040
ault+0.039
Neg logit contributions
 cheese-0.021
 Some-0.019
 of-0.019
 time-0.018
oke-0.017
Token that
Token ID326
Feature activation-2.13e-02

Pos logit contributions
 forth+0.150
ault+0.145
 salon+0.136
irling+0.129
inge+0.121
Neg logit contributions
 Some-0.126
 cheese-0.126
oke-0.123
 ago-0.120
 wine-0.115
Token stop
Token ID2245
Feature activation-2.06e-02

Pos logit contributions
 forth+0.045
irling+0.043
ault+0.042
 salon+0.041
 wrist+0.039
Neg logit contributions
 cheese-0.028
 Some-0.028
oke-0.025
 pizz-0.025
 of-0.024
Token him
Token ID683
Feature activation+3.60e-02

Pos logit contributions
 forth+0.050
irling+0.049
 salon+0.048
ault+0.047
inge+0.046
Neg logit contributions
 cheese-0.020
 Some-0.019
 of-0.017
 pizz-0.016
oke-0.016
Token.
Token ID13
Feature activation-8.09e-03

Pos logit contributions
 Some+0.037
 cheese+0.037
oke+0.032
 pizz+0.031
 wine+0.030
Neg logit contributions
 forth-0.086
irling-0.082
ault-0.081
 salon-0.080
 wrist-0.076
Token He
Token ID679
Feature activation+7.56e-03

Pos logit contributions
 forth+0.017
icycle+0.016
 salon+0.016
 wrist+0.015
irling+0.015
Neg logit contributions
 cheese-0.010
 wine-0.009
ocol-0.009
oke-0.009
 pizz-0.009
Token on
Token ID319
Feature activation-9.87e-03

Pos logit contributions
 forth+0.003
irling+0.003
ault+0.003
 salon+0.003
icycle+0.003
Neg logit contributions
 cheese-0.002
 Some-0.001
 pizz-0.001
oke-0.001
 of-0.001
Token the
Token ID262
Feature activation-1.02e-02

Pos logit contributions
 forth+0.019
irling+0.019
ault+0.018
 salon+0.018
 wrist+0.018
Neg logit contributions
oke-0.013
 Some-0.013
 cheese-0.012
 pizz-0.011
 There-0.011
Token fence
Token ID13990
Feature activation-1.79e-02

Pos logit contributions
 forth+0.018
irling+0.017
ault+0.016
 salon+0.016
 wrist+0.016
Neg logit contributions
 Some-0.017
 cheese-0.017
oke-0.016
 pizz-0.015
 of-0.015
Token and
Token ID290
Feature activation-2.70e-02

Pos logit contributions
 forth+0.042
irling+0.041
ault+0.040
 salon+0.040
 wrist+0.038
Neg logit contributions
 cheese-0.018
 Some-0.018
 pizz-0.015
oke-0.015
 Their-0.015
Token couldn
Token ID3521
Feature activation-1.67e-02

Pos logit contributions
irling+0.056
 forth+0.055
ault+0.054
 salon+0.053
icycle+0.051
Neg logit contributions
 cheese-0.036
 Some-0.033
 of-0.033
 wine-0.031
 There-0.030
Tokenâ
Token ID22940
Feature activation-8.36e-02

Pos logit contributions
 forth+0.029
irling+0.028
ault+0.026
 salon+0.026
 wrist+0.025
Neg logit contributions
 cheese-0.028
 Some-0.028
 of-0.026
 There-0.025
oke-0.025
Token€
Token ID26391
Feature activation-5.07e-02

Pos logit contributions
 forth+0.141
irling+0.138
 salon+0.131
ault+0.129
icycle+0.122
Neg logit contributions
 cheese-0.140
 Some-0.134
 time-0.130
oke-0.127
 Their-0.126
Tokenâ„¢
Token ID8151
Feature activation-2.11e-02

Pos logit contributions
 forth+0.106
irling+0.096
 salon+0.094
ault+0.090
inge+0.089
Neg logit contributions
 cheese-0.069
 Some-0.068
 There-0.066
 of-0.065
 time-0.063
Tokent
Token ID83
Feature activation-1.11e-02

Pos logit contributions
 forth+0.046
irling+0.046
 salon+0.045
ault+0.044
icycle+0.042
Neg logit contributions
 cheese-0.026
 Some-0.023
 pizz-0.021
 wine-0.021
 mushrooms-0.020
Token get
Token ID651
Feature activation-3.55e-02

Pos logit contributions
irling+0.023
 forth+0.023
 salon+0.022
icycle+0.022
ault+0.021
Neg logit contributions
 cheese-0.015
 of-0.014
 Some-0.014
oke-0.012
 There-0.012
Token out
Token ID503
Feature activation+7.36e-03

Pos logit contributions
 forth+0.066
irling+0.064
ault+0.061
 salon+0.061
inge+0.058
Neg logit contributions
 cheese-0.055
 Some-0.054
oke-0.049
 pizz-0.049
 of-0.048
Token,
Token ID11
Feature activation-2.51e-02

Pos logit contributions
 cheese+0.031
 Some+0.028
 pizz+0.028
izza+0.026
oke+0.025
Neg logit contributions
 forth-0.059
irling-0.056
 salon-0.054
ault-0.053
inge-0.051
Token but
Token ID475
Feature activation-5.61e-02

Pos logit contributions
irling+0.060
 forth+0.059
ault+0.058
 salon+0.057
icycle+0.057
Neg logit contributions
 cheese-0.026
 Some-0.025
 of-0.022
 wine-0.021
 Their-0.021
Token she
Token ID673
Feature activation-4.11e-02

Pos logit contributions
 forth+0.092
irling+0.087
 salon+0.081
ault+0.081
 wrist+0.076
Neg logit contributions
 cheese-0.102
 Some-0.100
 pizz-0.093
oke-0.092
 of-0.090
Token didn
Token ID1422
Feature activation-5.57e-03

Pos logit contributions
 forth+0.080
irling+0.079
ault+0.076
 salon+0.076
icycle+0.073
Neg logit contributions
 cheese-0.060
 Some-0.055
 of-0.053
 Their-0.052
 time-0.051
Token't
Token ID470
Feature activation-1.84e-02

Pos logit contributions
 forth+0.009
irling+0.009
 salon+0.008
ault+0.008
 wrist+0.008
Neg logit contributions
 cheese-0.010
 Some-0.010
 of-0.009
oke-0.009
 pizz-0.009
Token let
Token ID1309
Feature activation-8.35e-02

Pos logit contributions
 forth+0.041
irling+0.040
ault+0.038
 salon+0.038
inge+0.036
Neg logit contributions
 cheese-0.022
 Some-0.021
 of-0.019
 pizz-0.019
oke-0.019
Token the
Token ID262
Feature activation-1.52e-02

Pos logit contributions
 forth+0.119
ault+0.112
 salon+0.109
irling+0.100
 wrist+0.091
Neg logit contributions
 cheese-0.158
 Some-0.158
 ago-0.153
oke-0.153
 pizz-0.151
Token ducks
Token ID39694
Feature activation-1.88e-02

Pos logit contributions
 forth+0.031
irling+0.030
ault+0.029
 salon+0.029
inge+0.027
Neg logit contributions
 cheese-0.021
 Some-0.020
oke-0.018
 pizz-0.018
 of-0.018
Token bring
Token ID2222
Feature activation-2.60e-02

Pos logit contributions
 forth+0.037
irling+0.036
ault+0.034
 salon+0.034
 wrist+0.032
Neg logit contributions
 cheese-0.027
 Some-0.026
oke-0.024
 of-0.024
 pizz-0.024
Token her
Token ID607
Feature activation-2.04e-02

Pos logit contributions
 forth+0.040
ault+0.036
irling+0.034
 salon+0.033
 wrist+0.032
Neg logit contributions
oke-0.049
 Some-0.047
 cheese-0.045
 ago-0.044
izza-0.044
Token down
Token ID866
Feature activation-3.23e-02

Pos logit contributions
 forth+0.043
irling+0.042
ault+0.040
 salon+0.040
 wrist+0.038
Neg logit contributions
 cheese-0.026
 Some-0.026
oke-0.023
 pizz-0.023
 of-0.023
Token with
Token ID351
Feature activation-2.38e-02

Pos logit contributions
 cheese+0.025
 Some+0.024
 pizz+0.021
oke+0.021
 Their+0.020
Neg logit contributions
 forth-0.059
irling-0.057
 salon-0.056
ault-0.055
 wrist-0.053
Token it
Token ID340
Feature activation-2.43e-03

Pos logit contributions
 forth+0.040
irling+0.039
 salon+0.037
ault+0.037
 wrist+0.035
Neg logit contributions
 cheese-0.040
 Some-0.039
oke-0.037
 pizz-0.037
 of-0.036
Token and
Token ID290
Feature activation-3.28e-02

Pos logit contributions
 forth+0.005
irling+0.005
 salon+0.005
ault+0.005
 wrist+0.005
Neg logit contributions
 cheese-0.003
 Some-0.003
 pizz-0.003
oke-0.003
 Their-0.002
Token wouldn
Token ID3636
Feature activation-2.41e-02

Pos logit contributions
irling+0.068
 forth+0.066
ault+0.065
icycle+0.063
 salon+0.062
Neg logit contributions
 cheese-0.044
 Some-0.042
 of-0.039
 Their-0.038
 wine-0.038
Token't
Token ID470
Feature activation-1.91e-02

Pos logit contributions
 forth+0.049
irling+0.047
 wrist+0.044
 salon+0.044
ault+0.044
Neg logit contributions
 of-0.034
 Some-0.033
 cheese-0.032
 There-0.029
oke-0.029
Token let
Token ID1309
Feature activation-8.33e-02

Pos logit contributions
irling+0.042
liv+0.041
icycle+0.041
 forth+0.039
 salon+0.038
Neg logit contributions
 of-0.024
 cheese-0.023
 Some-0.022
 time-0.021
 can-0.020
Token anyone
Token ID2687
Feature activation-8.35e-03

Pos logit contributions
 forth+0.151
irling+0.144
ault+0.142
 salon+0.141
 wrist+0.131
Neg logit contributions
 cheese-0.130
 Some-0.128
oke-0.119
 pizz-0.117
 ago-0.114
Token else
Token ID2073
Feature activation-1.79e-02

Pos logit contributions
 forth+0.015
irling+0.014
ault+0.014
 salon+0.014
 wrist+0.013
Neg logit contributions
 cheese-0.014
 Some-0.013
 pizz-0.012
oke-0.012
 Their-0.012
Token play
Token ID711
Feature activation-4.72e-02

Pos logit contributions
 forth+0.035
irling+0.035
 salon+0.033
ault+0.033
inge+0.031
Neg logit contributions
 cheese-0.026
 Some-0.025
 of-0.023
 pizz-0.022
oke-0.022
Token with
Token ID351
Feature activation-3.01e-02

Pos logit contributions
 forth+0.096
irling+0.094
ault+0.090
 salon+0.090
inge+0.085
Neg logit contributions
 cheese-0.065
 Some-0.063
 of-0.057
 pizz-0.056
oke-0.056
Token it
Token ID340
Feature activation+1.10e-02

Pos logit contributions
 forth+0.063
irling+0.062
 salon+0.059
ault+0.059
icycle+0.057
Neg logit contributions
 cheese-0.041
 Some-0.039
 of-0.036
 wine-0.034
 pizz-0.034
Token too
Token ID1165
Feature activation-1.24e-02

Pos logit contributions
 forth+0.001
irling+0.001
ault+0.001
 salon+0.001
inge+0.001
Neg logit contributions
 cheese-0.001
 Some-0.001
 of-0.001
 pizz-0.001
oke-0.001
Token full
Token ID1336
Feature activation+1.81e-02

Pos logit contributions
 forth+0.026
irling+0.025
 salon+0.024
ault+0.024
 wrist+0.023
Neg logit contributions
 cheese-0.016
 Some-0.016
 of-0.015
oke-0.014
 pizz-0.014
Token and
Token ID290
Feature activation-1.18e-02

Pos logit contributions
 Some+0.026
 cheese+0.023
ocol+0.022
 pizz+0.022
 Their+0.022
Neg logit contributions
 forth-0.034
 salon-0.032
ault-0.031
irling-0.030
 wrist-0.029
Token could
Token ID714
Feature activation-1.97e-02

Pos logit contributions
 forth+0.023
irling+0.022
 salon+0.021
ault+0.021
inge+0.020
Neg logit contributions
 cheese-0.017
 Some-0.017
 pizz-0.015
oke-0.015
 of-0.015
Token not
Token ID407
Feature activation-2.83e-02

Pos logit contributions
 forth+0.040
irling+0.039
icycle+0.036
ault+0.036
 salon+0.036
Neg logit contributions
 cheese-0.028
 of-0.027
 Some-0.027
 Their-0.024
 time-0.024
Token let
Token ID1309
Feature activation-8.33e-02

Pos logit contributions
irling+0.056
 forth+0.055
icycle+0.053
 salon+0.052
liv+0.052
Neg logit contributions
 cheese-0.041
 of-0.038
 Some-0.037
 time-0.036
 wine-0.034
Token him
Token ID683
Feature activation+1.57e-02

Pos logit contributions
 forth+0.155
ault+0.151
 salon+0.143
irling+0.139
liv+0.128
Neg logit contributions
 Some-0.121
 cheese-0.120
oke-0.115
 ago-0.110
 pizz-0.105
Token stay
Token ID2652
Feature activation-2.56e-02

Pos logit contributions
 cheese+0.021
 Some+0.020
 of+0.020
 pizz+0.018
 Their+0.018
Neg logit contributions
 forth-0.032
irling-0.032
 salon-0.030
ault-0.029
icycle-0.029
Token.
Token ID13
Feature activation-5.12e-03

Pos logit contributions
 forth+0.050
 salon+0.050
irling+0.050
ault+0.048
liv+0.047
Neg logit contributions
 cheese-0.035
 of-0.033
 Some-0.032
 time-0.031
 wine-0.030
Token
Token ID198
Feature activation-1.22e-03

Pos logit contributions
 forth+0.010
irling+0.010
 salon+0.010
liv+0.010
 wrist+0.009
Neg logit contributions
 cheese-0.006
 pizz-0.005
 ago-0.005
 facts-0.005
 wine-0.005
Token
Token ID198
Feature activation-1.68e-03

Pos logit contributions
irling+0.003
 forth+0.002
liv+0.002
icycle+0.002
ault+0.002
Neg logit contributions
 cheese-0.002
 pizz-0.001
 wine-0.001
 Some-0.001
 mushrooms-0.001
Token says
Token ID1139
Feature activation-7.21e-03

Pos logit contributions
 cheese+0.025
 Some+0.024
 ago+0.022
ocol+0.022
 of+0.022
Neg logit contributions
 forth-0.039
 salon-0.037
irling-0.037
ault-0.036
 wrist-0.035
Token.
Token ID13
Feature activation+2.67e-02

Pos logit contributions
 forth+0.013
 wrist+0.012
irling+0.011
ault+0.011
 salon+0.011
Neg logit contributions
 cheese-0.011
 mushrooms-0.010
 Some-0.010
ocol-0.010
iles-0.010
Token "
Token ID366
Feature activation+7.41e-03

Pos logit contributions
ocol+0.041
izza+0.035
 pizz+0.035
 cheese+0.034
 wine+0.033
Neg logit contributions
 forth-0.044
 salon-0.043
 wrist-0.043
irling-0.042
ault-0.039
TokenWe
Token ID1135
Feature activation-5.08e-03

Pos logit contributions
 cheese+0.014
 Some+0.014
 of+0.013
 Their+0.013
 wine+0.013
Neg logit contributions
 forth-0.011
irling-0.011
 salon-0.010
liv-0.010
ault-0.010
Token forgive
Token ID20927
Feature activation+2.21e-02

Pos logit contributions
irling+0.014
 forth+0.014
ault+0.013
 salon+0.013
icycle+0.013
Neg logit contributions
 cheese-0.004
 Some-0.004
 of-0.003
 can-0.003
 wine-0.003
Token you
Token ID345
Feature activation+6.30e-02

Pos logit contributions
 Some+0.050
 There+0.047
oke+0.046
 ago+0.046
 cheese+0.046
Neg logit contributions
 forth-0.030
irling-0.024
ault-0.022
 wrist-0.021
 myself-0.020
Token.
Token ID13
Feature activation+2.32e-02

Pos logit contributions
 cheese+0.078
 Some+0.075
ocol+0.074
 There+0.071
 happened+0.070
Neg logit contributions
 forth-0.134
ault-0.118
 salon-0.117
irling-0.116
 wrist-0.113
Token But
Token ID887
Feature activation-2.90e-03

Pos logit contributions
 cheese+0.036
 pizz+0.033
 time+0.032
oke+0.032
 of+0.031
Neg logit contributions
 forth-0.039
 wrist-0.038
irling-0.037
ault-0.034
 salon-0.033
Token you
Token ID345
Feature activation+3.36e-02

Pos logit contributions
 forth+0.005
irling+0.005
 salon+0.004
ault+0.004
 wrist+0.004
Neg logit contributions
 cheese-0.005
 Some-0.005
 pizz-0.005
oke-0.005
 Their-0.004
Token have
Token ID423
Feature activation-1.35e-02

Pos logit contributions
 cheese+0.046
 Some+0.044
 pizz+0.042
 Their+0.040
oke+0.040
Neg logit contributions
 forth-0.066
irling-0.063
 salon-0.062
ault-0.061
inge-0.058
Token to
Token ID284
Feature activation-9.14e-03

Pos logit contributions
 forth+0.035
 salon+0.034
irling+0.034
ault+0.032
 wrist+0.032
Neg logit contributions
 cheese-0.009
oke-0.009
 Some-0.009
 pizz-0.008
 There-0.007
Token Joy
Token ID14087
Feature activation+3.10e-02

Pos logit contributions
 cheese+0.070
 Some+0.070
 pizz+0.064
oke+0.062
 Their+0.061
Neg logit contributions
 forth-0.091
ault-0.087
irling-0.086
 salon-0.085
 wrist-0.081
Token is
Token ID318
Feature activation+2.20e-02

Pos logit contributions
 Some+0.037
 cheese+0.033
 Their+0.031
 pizz+0.030
 There+0.029
Neg logit contributions
 forth-0.070
irling-0.067
ault-0.064
 salon-0.062
 wrist-0.061
Token a
Token ID257
Feature activation+1.56e-02

Pos logit contributions
 cheese+0.025
 Some+0.025
oke+0.021
 of+0.021
 pizz+0.021
Neg logit contributions
 forth-0.050
irling-0.049
ault-0.047
 salon-0.046
 wrist-0.045
Token good
Token ID922
Feature activation-2.80e-02

Pos logit contributions
 cheese+0.018
 Some+0.017
 of+0.015
 pizz+0.015
 time+0.015
Neg logit contributions
 forth-0.036
irling-0.035
 salon-0.033
ault-0.033
inge-0.032
Token name
Token ID1438
Feature activation+3.03e-02

Pos logit contributions
 forth+0.061
irling+0.060
 salon+0.057
ault+0.057
inge+0.054
Neg logit contributions
 cheese-0.036
 Some-0.034
 of-0.031
 pizz-0.030
oke-0.030
Token for
Token ID329
Feature activation+5.97e-02

Pos logit contributions
 Some+0.036
 cheese+0.033
 Their+0.033
 pizz+0.032
oke+0.031
Neg logit contributions
 forth-0.064
ault-0.061
 salon-0.059
irling-0.058
 wrist-0.058
Token that
Token ID326
Feature activation+2.36e-02

Pos logit contributions
 Some+0.098
 cheese+0.095
oke+0.091
 Their+0.087
 There+0.086
Neg logit contributions
 forth-0.105
irling-0.101
ault-0.097
 salon-0.095
 wrist-0.091
Token star
Token ID3491
Feature activation+2.81e-02

Pos logit contributions
 cheese+0.032
 Some+0.030
 of+0.028
 pizz+0.027
oke+0.027
Neg logit contributions
irling-0.049
 forth-0.049
ault-0.046
 salon-0.046
inge-0.044
Token.
Token ID13
Feature activation+3.43e-03

Pos logit contributions
 Some+0.034
 cheese+0.032
 Their+0.029
 There+0.028
 pizz+0.028
Neg logit contributions
 forth-0.062
irling-0.059
 salon-0.057
ault-0.056
 wrist-0.055
Token It
Token ID632
Feature activation+2.27e-02

Pos logit contributions
 cheese+0.004
 pizz+0.004
oke+0.004
 time+0.004
 happened+0.004
Neg logit contributions
 forth-0.007
 wrist-0.007
irling-0.007
 salon-0.006
ault-0.006
Token reminds
Token ID17603
Feature activation+2.30e-02

Pos logit contributions
 cheese+0.026
 Some+0.025
 of+0.021
 pizz+0.021
oke+0.021
Neg logit contributions
 forth-0.052
irling-0.050
 salon-0.048
ault-0.048
 wrist-0.046
Token And
Token ID843
Feature activation-5.04e-04

Pos logit contributions
 cheese+0.002
 Some+0.002
 Their+0.002
 of+0.002
 There+0.002
Neg logit contributions
 forth-0.007
irling-0.007
ault-0.007
 salon-0.006
inge-0.006
Token they
Token ID484
Feature activation-4.11e-04

Pos logit contributions
irling+0.001
 forth+0.001
icycle+0.001
ault+0.001
 salon+0.001
Neg logit contributions
 cheese-0.001
 of-0.001
 Some-0.000
 Their-0.000
 wine-0.000
Token all
Token ID477
Feature activation-1.85e-02

Pos logit contributions
irling+0.001
icycle+0.001
 salon+0.001
 forth+0.001
itating+0.001
Neg logit contributions
 cheese-0.001
 of-0.001
 can-0.001
 Their-0.001
 time-0.001
Token lived
Token ID5615
Feature activation-3.56e-04

Pos logit contributions
irling+0.042
 forth+0.041
 salon+0.041
icycle+0.040
ault+0.040
Neg logit contributions
 cheese-0.021
 of-0.020
 Some-0.019
 Their-0.019
oke-0.018
Token happily
Token ID18177
Feature activation+5.18e-03

Pos logit contributions
 forth+0.001
irling+0.001
 salon+0.001
ault+0.001
icycle+0.001
Neg logit contributions
 cheese-0.001
 of-0.001
 Some-0.001
 pizz-0.000
 Their-0.000
Token ever
Token ID1683
Feature activation+6.44e-02

Pos logit contributions
 cheese+0.007
 Some+0.007
 of+0.006
oke+0.006
 pizz+0.006
Neg logit contributions
 forth-0.011
irling-0.010
ault-0.010
 salon-0.010
 wrist-0.009
Token after
Token ID706
Feature activation+4.39e-03

Pos logit contributions
 cheese+0.096
 Some+0.095
oke+0.086
 of+0.085
 Their+0.084
Neg logit contributions
 forth-0.125
irling-0.120
ault-0.117
 salon-0.113
inge-0.107
Token.
Token ID13
Feature activation+8.98e-03

Pos logit contributions
 cheese+0.003
 of+0.003
 Some+0.002
 wine+0.002
 time+0.002
Neg logit contributions
 forth-0.012
 salon-0.012
ault-0.012
irling-0.012
icycle-0.011
Token The
Token ID383
Feature activation+2.15e-02

Pos logit contributions
 cheese+0.009
 Some+0.008
 pizz+0.007
oke+0.007
 ago+0.007
Neg logit contributions
 forth-0.021
irling-0.021
 salon-0.020
ault-0.020
liv-0.020
Token end
Token ID886
Feature activation-1.24e-02

Pos logit contributions
 cheese+0.030
 Some+0.029
 of+0.027
 pizz+0.026
oke+0.026
Neg logit contributions
 forth-0.043
irling-0.043
ault-0.040
 salon-0.040
 wrist-0.038
Token.
Token ID13
Feature activation+9.78e-03

Pos logit contributions
 forth+0.021
irling+0.020
liv+0.019
icycle+0.019
har+0.017
Neg logit contributions
 Some-0.018
ocol-0.018
 pizz-0.018
 cheese-0.017
 peppers-0.017
Token hugs
Token ID40657
Feature activation+4.07e-03

Pos logit contributions
 cheese+0.011
 Some+0.010
 can+0.010
 of+0.009
 pizz+0.009
Neg logit contributions
 forth-0.025
irling-0.025
ault-0.024
inge-0.024
liv-0.023
Token her
Token ID607
Feature activation+7.07e-03

Pos logit contributions
oke+0.008
 cheese+0.007
izza+0.007
 Some+0.007
 ago+0.007
Neg logit contributions
 forth-0.006
 salon-0.005
irling-0.005
ault-0.005
 wrist-0.005
Token.
Token ID13
Feature activation+1.42e-02

Pos logit contributions
 cheese+0.007
 Some+0.006
 of+0.006
 pizz+0.005
 Their+0.005
Neg logit contributions
irling-0.018
 forth-0.017
 salon-0.017
ault-0.016
inge-0.016
Token "
Token ID366
Feature activation-1.31e-02

Pos logit contributions
 pizz+0.017
ocol+0.017
oke+0.016
 cheese+0.016
izza+0.015
Neg logit contributions
irling-0.025
 wrist-0.024
 salon-0.024
 forth-0.023
 sandbox-0.023
TokenThank
Token ID10449
Feature activation-1.46e-02

Pos logit contributions
 forth+0.022
irling+0.022
 salon+0.021
ault+0.020
icycle+0.019
Neg logit contributions
 Some-0.024
 cheese-0.024
 of-0.022
 There-0.021
 Their-0.021
Token you
Token ID345
Feature activation+6.38e-02

Pos logit contributions
 forth+0.019
irling+0.017
ault+0.016
 salon+0.015
liv+0.014
Neg logit contributions
 Some-0.031
 cheese-0.031
 ago-0.029
 pizz-0.029
 Their-0.028
Token,
Token ID11
Feature activation+2.00e-02

Pos logit contributions
 Some+0.082
 happened+0.081
 ago+0.078
 There+0.076
 cheese+0.074
Neg logit contributions
 forth-0.124
ault-0.107
 myself-0.104
 salon-0.104
irling-0.103
Token Mia
Token ID32189
Feature activation+9.68e-04

Pos logit contributions
 cheese+0.020
 Some+0.019
 pizz+0.017
 Their+0.016
oke+0.016
Neg logit contributions
 forth-0.047
irling-0.046
 salon-0.045
ault-0.044
 wrist-0.043
Token.
Token ID13
Feature activation+1.75e-02

Pos logit contributions
 Some+0.001
 cheese+0.001
 pizz+0.001
 There+0.001
 Their+0.001
Neg logit contributions
 forth-0.002
irling-0.002
 salon-0.002
ault-0.002
 wrist-0.002
Token You
Token ID921
Feature activation+3.13e-02

Pos logit contributions
 cheese+0.028
 pizz+0.026
 Some+0.026
oke+0.025
 wine+0.025
Neg logit contributions
 forth-0.029
irling-0.027
 wrist-0.027
 salon-0.026
ault-0.026
Token are
Token ID389
Feature activation-2.13e-02

Pos logit contributions
 cheese+0.031
 Some+0.027
 of+0.026
 pizz+0.024
oke+0.024
Neg logit contributions
irling-0.078
 forth-0.077
 salon-0.075
ault-0.073
 wrist-0.071
Token,
Token ID11
Feature activation+1.79e-02

Pos logit contributions
 cheese+0.021
 Some+0.020
 wine+0.018
oke+0.018
 pizz+0.017
Neg logit contributions
 forth-0.041
irling-0.041
 salon-0.038
ault-0.037
 wrist-0.037
Token mom
Token ID1995
Feature activation+1.36e-02

Pos logit contributions
 cheese+0.024
 Some+0.023
 of+0.020
oke+0.020
 pizz+0.020
Neg logit contributions
 forth-0.037
irling-0.036
 salon-0.035
ault-0.035
 wrist-0.033
Token.
Token ID13
Feature activation+2.12e-02

Pos logit contributions
 Some+0.014
 cheese+0.014
 Their+0.013
 There+0.012
 wine+0.012
Neg logit contributions
 forth-0.032
 salon-0.030
irling-0.029
ault-0.028
 wrist-0.028
Token Thank
Token ID6952
Feature activation+9.23e-03

Pos logit contributions
 pizz+0.029
 cheese+0.029
oke+0.028
 of+0.027
 happened+0.026
Neg logit contributions
 forth-0.037
 wrist-0.037
irling-0.036
 salon-0.035
liv-0.034
Token you
Token ID345
Feature activation+7.26e-02

Pos logit contributions
 Some+0.019
 cheese+0.019
oke+0.018
 pizz+0.017
 Their+0.017
Neg logit contributions
 forth-0.013
irling-0.012
ault-0.011
 wrist-0.011
 salon-0.010
Token for
Token ID329
Feature activation+6.45e-02

Pos logit contributions
 Some+0.083
 cheese+0.079
 happened+0.076
ocol+0.074
 There+0.072
Neg logit contributions
 forth-0.155
ault-0.142
 salon-0.140
irling-0.138
 wrist-0.134
Token the
Token ID262
Feature activation+1.36e-02

Pos logit contributions
 cheese+0.101
 Some+0.094
 of+0.088
 pizz+0.087
 wine+0.086
Neg logit contributions
 forth-0.121
irling-0.118
 salon-0.114
ault-0.114
icycle-0.110
Token vegetables
Token ID13701
Feature activation+4.20e-02

Pos logit contributions
 Some+0.017
oke+0.017
 Their+0.016
 cheese+0.016
 There+0.015
Neg logit contributions
 forth-0.028
 salon-0.027
irling-0.026
ault-0.026
 wrist-0.025
Token,"
Token ID553
Feature activation+1.93e-02

Pos logit contributions
 Some+0.046
 cheese+0.039
 There+0.039
oke+0.037
 Their+0.037
Neg logit contributions
 forth-0.095
 salon-0.093
irling-0.090
ault-0.090
 wrist-0.088
Token Tommy
Token ID19919
Feature activation+9.41e-03

Pos logit contributions
 cheese+0.021
 Some+0.020
 of+0.018
 pizz+0.017
oke+0.017
Neg logit contributions
 forth-0.045
irling-0.044
ault-0.043
 salon-0.042
inge-0.041
Token said
Token ID531
Feature activation+4.52e-04

Pos logit contributions
 cheese+0.012
 Some+0.011
 of+0.010
 pizz+0.010
oke+0.010
Neg logit contributions
 forth-0.021
irling-0.021
ault-0.020
 salon-0.019
inge-0.019
Token playing
Token ID2712
Feature activation+1.72e-03

Pos logit contributions
 forth+0.090
irling+0.088
ault+0.086
 salon+0.085
inge+0.084
Neg logit contributions
 cheese-0.016
 Some-0.014
 of-0.011
 pizz-0.010
 Their-0.009
Token.
Token ID13
Feature activation+3.49e-03

Pos logit contributions
 cheese+0.002
 Some+0.002
 of+0.002
 time+0.001
 pizz+0.001
Neg logit contributions
 forth-0.004
irling-0.004
 salon-0.004
ault-0.004
liv-0.004
Token When
Token ID1649
Feature activation-8.95e-03

Pos logit contributions
 cheese+0.004
 pizz+0.004
oke+0.004
 Some+0.004
ocol+0.003
Neg logit contributions
 forth-0.008
irling-0.007
 salon-0.007
icycle-0.007
 wrist-0.007
Token it
Token ID340
Feature activation+1.72e-02

Pos logit contributions
irling+0.023
 salon+0.022
ault+0.022
 wrist+0.022
 forth+0.022
Neg logit contributions
 cheese-0.009
 Some-0.008
 of-0.008
 time-0.007
 There-0.007
Token was
Token ID373
Feature activation+1.15e-02

Pos logit contributions
 cheese+0.021
 Some+0.020
 pizz+0.018
 of+0.018
oke+0.018
Neg logit contributions
 forth-0.038
irling-0.037
 salon-0.035
ault-0.035
inge-0.034
Token time
Token ID640
Feature activation+3.19e-02

Pos logit contributions
 cheese+0.013
 Some+0.012
oke+0.011
 pizz+0.011
 of+0.011
Neg logit contributions
 forth-0.027
irling-0.026
ault-0.025
 salon-0.025
inge-0.024
Token to
Token ID284
Feature activation-7.16e-03

Pos logit contributions
 cheese+0.017
 Some+0.015
 of+0.011
oke+0.010
 pizz+0.010
Neg logit contributions
 forth-0.092
irling-0.091
ault-0.088
 salon-0.088
inge-0.085
Token go
Token ID467
Feature activation+6.86e-03

Pos logit contributions
irling+0.019
 salon+0.018
 forth+0.018
icycle+0.018
liv+0.018
Neg logit contributions
 time-0.005
 cheese-0.005
 of-0.004
 wine-0.004
 Their-0.004
Token home
Token ID1363
Feature activation+2.09e-02

Pos logit contributions
 of+0.011
 cheese+0.011
 Some+0.010
 There+0.009
 time+0.009
Neg logit contributions
irling-0.013
ault-0.012
 forth-0.012
 salon-0.012
inge-0.012
Token,
Token ID11
Feature activation-4.98e-03

Pos logit contributions
 cheese+0.008
 of+0.008
 Some+0.006
oke+0.004
 Their+0.004
Neg logit contributions
irling-0.063
 forth-0.063
ault-0.061
 salon-0.060
icycle-0.059
Token Tim
Token ID5045
Feature activation-1.72e-02

Pos logit contributions
irling+0.014
 salon+0.014
ault+0.014
 forth+0.014
icycle+0.013
Neg logit contributions
 cheese-0.003
 Some-0.003
 of-0.002
 Their-0.002
 wine-0.002
Token else
Token ID2073
Feature activation+1.40e-02

Pos logit contributions
 Some+0.021
 cheese+0.020
 pizz+0.018
oke+0.018
 There+0.018
Neg logit contributions
 forth-0.034
irling-0.032
 salon-0.032
ault-0.031
 wrist-0.030
Token instead
Token ID2427
Feature activation+1.53e-02

Pos logit contributions
 Some+0.015
 cheese+0.014
oke+0.014
 pizz+0.013
 There+0.013
Neg logit contributions
 forth-0.032
irling-0.029
 salon-0.029
 wrist-0.029
ault-0.028
Token of
Token ID286
Feature activation+8.95e-03

Pos logit contributions
 Some+0.016
 cheese+0.015
 pizz+0.014
oke+0.013
 Their+0.013
Neg logit contributions
 forth-0.035
irling-0.033
 salon-0.033
ault-0.031
 wrist-0.031
Token scissors
Token ID41786
Feature activation+2.04e-02

Pos logit contributions
 Some+0.013
oke+0.013
 cheese+0.012
 There+0.012
 Their+0.011
Neg logit contributions
 forth-0.017
irling-0.016
 salon-0.016
ault-0.016
 wrist-0.015
Token.
Token ID13
Feature activation+1.04e-02

Pos logit contributions
 Some+0.020
 cheese+0.020
 pizz+0.017
 Their+0.017
 There+0.016
Neg logit contributions
 forth-0.049
 salon-0.047
irling-0.047
ault-0.045
 wrist-0.043
Token How
Token ID1374
Feature activation+6.80e-03

Pos logit contributions
 cheese+0.012
 happened+0.012
 pizz+0.012
 of+0.011
 time+0.011
Neg logit contributions
 salon-0.020
 wrist-0.020
 forth-0.020
irling-0.019
ault-0.019
Token about
Token ID546
Feature activation-1.76e-02

Pos logit contributions
ocol+0.009
 pizz+0.008
 peppers+0.008
 cheese+0.008
 wine+0.007
Neg logit contributions
 salon-0.014
 swing-0.012
irling-0.012
ault-0.011
 wrist-0.011
Token some
Token ID617
Feature activation+6.75e-03

Pos logit contributions
 forth+0.035
irling+0.035
 salon+0.033
ault+0.032
 wrist+0.031
Neg logit contributions
 cheese-0.023
 Some-0.023
oke-0.022
 of-0.021
 pizz-0.021
Token string
Token ID4731
Feature activation+1.86e-02

Pos logit contributions
 Some+0.009
 Their+0.009
oke+0.008
 There+0.008
 cheese+0.008
Neg logit contributions
 forth-0.014
 salon-0.013
irling-0.012
ault-0.012
 wrist-0.011
Token or
Token ID393
Feature activation+1.74e-02

Pos logit contributions
 Some+0.022
 cheese+0.021
 pizz+0.019
 Their+0.019
oke+0.019
Neg logit contributions
 forth-0.042
 salon-0.039
irling-0.039
ault-0.037
 wrist-0.036
Token some
Token ID617
Feature activation+5.52e-04

Pos logit contributions
oke+0.027
 Some+0.025
 Their+0.023
 There+0.023
 cheese+0.023
Neg logit contributions
 forth-0.034
 salon-0.031
ault-0.029
irling-0.029
 wrist-0.029
Token Sam
Token ID3409
Feature activation+2.09e-03

Pos logit contributions
 cheese+0.002
 Some+0.002
 of+0.001
 pizz+0.001
oke+0.001
Neg logit contributions
 forth-0.004
irling-0.004
 salon-0.003
ault-0.003
inge-0.003
Token had
Token ID550
Feature activation+1.06e-02

Pos logit contributions
 cheese+0.002
 of+0.002
 Some+0.002
 time+0.002
oke+0.002
Neg logit contributions
 forth-0.005
irling-0.005
ault-0.005
 salon-0.005
inge-0.005
Token learned
Token ID4499
Feature activation+3.21e-02

Pos logit contributions
 cheese+0.012
 Some+0.011
 of+0.010
 pizz+0.009
 Their+0.009
Neg logit contributions
 forth-0.025
irling-0.025
 salon-0.024
ault-0.024
inge-0.023
Token an
Token ID281
Feature activation+1.96e-02

Pos logit contributions
 cheese+0.032
 Some+0.030
 of+0.027
 pizz+0.025
 Their+0.025
Neg logit contributions
 forth-0.079
irling-0.077
 salon-0.074
ault-0.074
inge-0.071
Token important
Token ID1593
Feature activation+2.12e-02

Pos logit contributions
 Some+0.023
 cheese+0.023
 There+0.021
oke+0.020
 pizz+0.020
Neg logit contributions
 forth-0.042
irling-0.041
ault-0.040
 salon-0.038
inge-0.038
Token lesson
Token ID11483
Feature activation+2.07e-02

Pos logit contributions
 cheese+0.024
 Some+0.023
oke+0.021
 pizz+0.020
 of+0.020
Neg logit contributions
 forth-0.046
irling-0.046
ault-0.045
 salon-0.044
 wrist-0.043
Token:
Token ID25
Feature activation+2.93e-02

Pos logit contributions
 cheese+0.026
 Some+0.025
 pizz+0.021
 wine+0.021
oke+0.021
Neg logit contributions
 forth-0.043
irling-0.043
ault-0.041
 salon-0.041
liv-0.040
Token it
Token ID340
Feature activation+3.07e-02

Pos logit contributions
 cheese+0.046
 Some+0.044
 pizz+0.041
oke+0.041
 of+0.040
Neg logit contributions
 forth-0.053
irling-0.052
 salon-0.049
ault-0.049
 wrist-0.046
Token's
Token ID338
Feature activation+9.44e-03

Pos logit contributions
 cheese+0.040
 Some+0.038
 pizz+0.034
 of+0.033
oke+0.033
Neg logit contributions
 forth-0.065
irling-0.063
ault-0.060
 salon-0.060
inge-0.057
Token always
Token ID1464
Feature activation+1.39e-02

Pos logit contributions
 Some+0.012
 cheese+0.012
oke+0.011
 pizz+0.011
 There+0.011
Neg logit contributions
 forth-0.020
irling-0.019
ault-0.019
 salon-0.018
inge-0.017
Token a
Token ID257
Feature activation+2.11e-02

Pos logit contributions
 Some+0.019
 cheese+0.018
oke+0.017
 pizz+0.017
 There+0.016
Neg logit contributions
 forth-0.029
irling-0.027
ault-0.025
 salon-0.024
 wrist-0.024
Token day
Token ID1110
Feature activation-7.35e-03

Pos logit contributions
 cheese+0.007
 Some+0.007
 of+0.007
 time+0.006
 pizz+0.006
Neg logit contributions
 forth-0.009
irling-0.009
ault-0.008
 salon-0.008
inge-0.008
Token of
Token ID286
Feature activation+1.73e-02

Pos logit contributions
 forth+0.017
 salon+0.017
irling+0.016
icycle+0.016
ault+0.016
Neg logit contributions
 cheese-0.006
 Some-0.006
 peppers-0.005
 mushrooms-0.005
 wine-0.005
Token the
Token ID262
Feature activation+3.01e-03

Pos logit contributions
 cheese+0.024
 Some+0.023
oke+0.023
izza+0.022
 pizz+0.021
Neg logit contributions
 forth-0.036
irling-0.033
 salon-0.032
ault-0.031
icycle-0.031
Token test
Token ID1332
Feature activation-9.46e-03

Pos logit contributions
 cheese+0.004
 Some+0.004
 of+0.004
 time+0.004
 pizz+0.004
Neg logit contributions
irling-0.006
 forth-0.006
ault-0.005
inge-0.005
 wrist-0.005
Token,
Token ID11
Feature activation-2.13e-03

Pos logit contributions
 forth+0.024
 salon+0.023
irling+0.023
ault+0.022
icycle+0.021
Neg logit contributions
 cheese-0.009
 Some-0.008
 wine-0.007
 pizz-0.007
oke-0.006
Token the
Token ID262
Feature activation+6.00e-03

Pos logit contributions
 forth+0.004
ault+0.004
 salon+0.004
irling+0.003
 sandbox+0.003
Neg logit contributions
oke-0.003
 Some-0.003
 ago-0.003
 cheese-0.003
izza-0.003
Token little
Token ID1310
Feature activation-7.09e-03

Pos logit contributions
 cheese+0.008
 Some+0.007
 of+0.007
 pizz+0.006
 time+0.006
Neg logit contributions
 forth-0.013
irling-0.013
ault-0.012
 salon-0.012
liv-0.012
Token car
Token ID1097
Feature activation-4.22e-03

Pos logit contributions
irling+0.015
 forth+0.014
ault+0.014
liv+0.013
 salon+0.013
Neg logit contributions
 cheese-0.010
 Some-0.009
 of-0.009
 pizz-0.008
 time-0.008
Token woke
Token ID19092
Feature activation-7.11e-03

Pos logit contributions
irling+0.009
 forth+0.009
ault+0.008
 salon+0.008
inge+0.008
Neg logit contributions
 cheese-0.005
 Some-0.005
 of-0.005
oke-0.005
 pizz-0.005
Token up
Token ID510
Feature activation-2.21e-02

Pos logit contributions
 forth+0.010
irling+0.010
 salon+0.009
ault+0.009
inge+0.008
Neg logit contributions
 cheese-0.014
 Some-0.014
 of-0.013
 pizz-0.013
oke-0.013
Token early
Token ID1903
Feature activation+1.40e-02

Pos logit contributions
 forth+0.058
irling+0.057
 salon+0.055
ault+0.055
liv+0.054
Neg logit contributions
 cheese-0.017
 Some-0.016
 of-0.015
 time-0.013
 pizz-0.013
Token there
Token ID612
Feature activation+1.31e-03

Pos logit contributions
 cheese+0.035
 Some+0.032
 peppers+0.030
 meat+0.030
 pizz+0.030
Neg logit contributions
irling-0.047
 forth-0.046
 salon-0.045
liv-0.044
icycle-0.043
Token was
Token ID373
Feature activation+1.55e-02

Pos logit contributions
 cheese+0.002
 Some+0.002
 pizz+0.002
oke+0.002
izza+0.002
Neg logit contributions
 forth-0.002
irling-0.002
 salon-0.002
liv-0.002
icycle-0.002
Token a
Token ID257
Feature activation+4.78e-03

Pos logit contributions
oke+0.023
 pizz+0.017
 Some+0.017
izza+0.017
 cheese+0.016
Neg logit contributions
irling-0.031
 forth-0.030
ault-0.029
liv-0.028
 salon-0.027
Token cow
Token ID9875
Feature activation+1.57e-03

Pos logit contributions
 cheese+0.004
 Some+0.004
 of+0.004
 pizz+0.004
oke+0.004
Neg logit contributions
 forth-0.012
irling-0.012
ault-0.011
 salon-0.011
 wrist-0.011
Token.
Token ID13
Feature activation+1.13e-02

Pos logit contributions
 cheese+0.002
 Some+0.002
 of+0.001
 pizz+0.001
oke+0.001
Neg logit contributions
 forth-0.004
irling-0.004
ault-0.003
 salon-0.003
inge-0.003
Token The
Token ID383
Feature activation+2.30e-02

Pos logit contributions
oke+0.014
 pizz+0.012
 happens+0.011
 cheese+0.011
izza+0.011
Neg logit contributions
 wrist-0.022
 forth-0.021
 salon-0.021
irling-0.020
liv-0.020
Token cow
Token ID9875
Feature activation+1.49e-03

Pos logit contributions
oke+0.029
 Some+0.028
 cheese+0.028
izza+0.028
 pizz+0.028
Neg logit contributions
 forth-0.045
irling-0.043
 salon-0.043
ault-0.041
inge-0.041
Token was
Token ID373
Feature activation-3.17e-03

Pos logit contributions
 cheese+0.002
 Some+0.002
 pizz+0.002
oke+0.002
 of+0.002
Neg logit contributions
 forth-0.003
irling-0.003
 salon-0.003
ault-0.003
 wrist-0.003
Token lost
Token ID2626
Feature activation-8.32e-03

Pos logit contributions
irling+0.006
 forth+0.006
 salon+0.005
ault+0.005
inge+0.005
Neg logit contributions
oke-0.005
izza-0.004
 Some-0.004
 pizz-0.004
 happens-0.004
Token in
Token ID287
Feature activation-2.46e-02

Pos logit contributions
 forth+0.019
irling+0.018
ault+0.017
 salon+0.017
 wrist+0.016
Neg logit contributions
 Some-0.010
 cheese-0.009
oke-0.009
 pizz-0.009
 There-0.008
Token a
Token ID257
Feature activation-2.06e-02

Pos logit contributions
 forth+0.052
irling+0.050
 salon+0.049
ault+0.048
 wrist+0.045
Neg logit contributions
 Some-0.030
oke-0.030
 cheese-0.029
izza-0.026
 pizz-0.026
Token time
Token ID640
Feature activation+2.97e-02

Pos logit contributions
 Some+0.023
 cheese+0.023
 pizz+0.019
oke+0.019
 peppers+0.018
Neg logit contributions
irling-0.096
 forth-0.092
ault-0.091
liv-0.089
 salon-0.088
Token,
Token ID11
Feature activation+1.27e-02

Pos logit contributions
 cheese+0.042
 Some+0.038
 pizz+0.035
 peppers+0.035
 meat+0.034
Neg logit contributions
irling-0.058
 forth-0.058
 salon-0.056
liv-0.054
ault-0.053
Token there
Token ID612
Feature activation+1.20e-03

Pos logit contributions
 cheese+0.025
 pizz+0.024
 Some+0.023
oke+0.022
 facts+0.022
Neg logit contributions
 forth-0.019
irling-0.018
ault-0.016
 salon-0.016
liv-0.015
Token lived
Token ID5615
Feature activation+9.72e-03

Pos logit contributions
 cheese+0.002
 Some+0.002
 pizz+0.002
oke+0.002
 wine+0.001
Neg logit contributions
 forth-0.002
irling-0.002
 salon-0.002
liv-0.002
ault-0.002
Token a
Token ID257
Feature activation+9.72e-03

Pos logit contributions
 cheese+0.009
oke+0.009
 Some+0.009
 pizz+0.008
 ago+0.008
Neg logit contributions
irling-0.023
 forth-0.022
ault-0.022
 salon-0.021
 wrist-0.021
Token little
Token ID1310
Feature activation-4.47e-03

Pos logit contributions
 cheese+0.009
 Some+0.009
 of+0.008
 pizz+0.008
oke+0.008
Neg logit contributions
 forth-0.024
irling-0.023
ault-0.022
 salon-0.022
 wrist-0.021
Token girl
Token ID2576
Feature activation+2.50e-03

Pos logit contributions
 forth+0.008
irling+0.008
 salon+0.007
ault+0.007
 wrist+0.007
Neg logit contributions
 Some-0.007
 cheese-0.007
 pizz-0.006
oke-0.006
 Their-0.006
Token.
Token ID13
Feature activation+1.62e-02

Pos logit contributions
 cheese+0.004
 Some+0.004
 pizz+0.003
oke+0.003
izza+0.003
Neg logit contributions
 forth-0.005
irling-0.005
 salon-0.004
 wrist-0.004
ault-0.004
Token She
Token ID1375
Feature activation+4.03e-03

Pos logit contributions
oke+0.026
 pizz+0.026
 cheese+0.026
 peppers+0.024
izza+0.023
Neg logit contributions
 wrist-0.026
 salon-0.025
 forth-0.025
irling-0.024
ault-0.022
Token had
Token ID550
Feature activation+6.67e-03

Pos logit contributions
 cheese+0.006
 Some+0.005
oke+0.005
 of+0.005
 pizz+0.005
Neg logit contributions
 forth-0.008
irling-0.008
 salon-0.008
ault-0.008
 wrist-0.007
Token beautiful
Token ID4950
Feature activation-1.54e-03

Pos logit contributions
 cheese+0.005
 Some+0.005
 of+0.004
 pizz+0.004
oke+0.004
Neg logit contributions
 forth-0.018
irling-0.018
ault-0.017
 salon-0.017
inge-0.016
Token a
Token ID257
Feature activation-2.26e-02

Pos logit contributions
 forth+0.003
ault+0.003
irling+0.003
 salon+0.002
 wrist+0.002
Neg logit contributions
 Some-0.002
 cheese-0.002
oke-0.002
 pizz-0.002
 ago-0.002
Token hole
Token ID7604
Feature activation-5.00e-02

Pos logit contributions
 forth+0.041
irling+0.039
ault+0.039
 salon+0.038
 wrist+0.036
Neg logit contributions
 Some-0.035
 cheese-0.034
oke-0.032
 Their-0.031
 There-0.031
Token for
Token ID329
Feature activation+2.10e-02

Pos logit contributions
 forth+0.122
irling+0.120
ault+0.115
 salon+0.115
inge+0.110
Neg logit contributions
 cheese-0.049
 Some-0.046
 of-0.040
 pizz-0.039
oke-0.039
Token the
Token ID262
Feature activation-2.15e-02

Pos logit contributions
 Some+0.028
oke+0.027
 cheese+0.027
 of+0.025
 pizz+0.024
Neg logit contributions
 forth-0.042
irling-0.041
ault-0.040
 salon-0.040
 wrist-0.038
Token door
Token ID3420
Feature activation+1.25e-02

Pos logit contributions
irling+0.038
 forth+0.038
 salon+0.035
ault+0.035
icycle+0.033
Neg logit contributions
 cheese-0.036
 Some-0.034
 of-0.032
 wine-0.032
 pizz-0.031
Token.
Token ID13
Feature activation-4.99e-04

Pos logit contributions
 cheese+0.012
 Some+0.011
 pizz+0.009
oke+0.009
 wine+0.009
Neg logit contributions
 forth-0.031
irling-0.030
 salon-0.030
ault-0.029
 wrist-0.028
Token She
Token ID1375
Feature activation-1.24e-02

Pos logit contributions
irling+0.001
 forth+0.001
 salon+0.001
 wrist+0.001
ault+0.001
Neg logit contributions
 cheese-0.001
 pizz-0.001
oke-0.000
 wine-0.000
 Some-0.000
Token drew
Token ID9859
Feature activation-1.52e-03

Pos logit contributions
 forth+0.025
irling+0.025
ault+0.024
 salon+0.023
inge+0.022
Neg logit contributions
 cheese-0.018
 Some-0.016
 of-0.016
 pizz-0.015
 Their-0.014
Token windows
Token ID9168
Feature activation+2.07e-02

Pos logit contributions
 forth+0.003
irling+0.003
ault+0.003
 salon+0.003
 wrist+0.003
Neg logit contributions
oke-0.002
 Some-0.002
 cheese-0.002
 Their-0.001
 pizz-0.001
Token and
Token ID290
Feature activation-1.24e-04

Pos logit contributions
 cheese+0.019
 Some+0.018
 of+0.015
oke+0.015
 pizz+0.015
Neg logit contributions
 forth-0.051
irling-0.051
 salon-0.049
ault-0.049
 wrist-0.047
Token wings
Token ID12098
Feature activation+1.79e-02

Pos logit contributions
 forth+0.000
irling+0.000
 salon+0.000
ault+0.000
 wrist+0.000
Neg logit contributions
 Some-0.000
 cheese-0.000
oke-0.000
 Their-0.000
 pizz-0.000
Token my
Token ID616
Feature activation-3.73e-03

Pos logit contributions
 cheese+0.006
 Some+0.006
 of+0.006
 wine+0.005
 pizz+0.005
Neg logit contributions
irling-0.009
 forth-0.009
ault-0.009
 salon-0.009
inge-0.008
Token hoop
Token ID44792
Feature activation-1.60e-02

Pos logit contributions
irling+0.006
 salon+0.006
 forth+0.006
ault+0.006
inge+0.006
Neg logit contributions
 cheese-0.006
 Some-0.006
 of-0.006
 wine-0.006
 time-0.005
Token?"
Token ID1701
Feature activation-4.97e-03

Pos logit contributions
 forth+0.037
irling+0.036
ault+0.035
 salon+0.034
inge+0.033
Neg logit contributions
 cheese-0.018
 Some-0.017
 of-0.015
 pizz-0.015
oke-0.015
Token His
Token ID2399
Feature activation+1.92e-02

Pos logit contributions
 forth+0.012
irling+0.011
 salon+0.011
 wrist+0.011
icycle+0.011
Neg logit contributions
 cheese-0.005
oke-0.004
 Some-0.004
 pizz-0.004
 ago-0.004
Token mom
Token ID1995
Feature activation-1.41e-02

Pos logit contributions
 cheese+0.031
 Some+0.030
oke+0.029
 of+0.028
 pizz+0.028
Neg logit contributions
 forth-0.035
irling-0.033
 salon-0.032
ault-0.031
 wrist-0.031
Token said
Token ID531
Feature activation-9.36e-03

Pos logit contributions
 forth+0.028
irling+0.028
ault+0.026
 salon+0.026
inge+0.025
Neg logit contributions
 cheese-0.020
 Some-0.019
 of-0.018
oke-0.017
 pizz-0.017
Token,
Token ID11
Feature activation+8.33e-03

Pos logit contributions
irling+0.018
 forth+0.018
 wrist+0.018
 salon+0.018
ault+0.017
Neg logit contributions
 cheese-0.012
 Some-0.012
 pizz-0.011
 mushrooms-0.011
iles-0.011
Token "
Token ID366
Feature activation+8.78e-03

Pos logit contributions
 cheese+0.008
 Some+0.007
 pizz+0.007
ocol+0.007
 ago+0.007
Neg logit contributions
 forth-0.019
irling-0.019
 salon-0.019
 wrist-0.018
ault-0.018
TokenYes
Token ID5297
Feature activation+7.48e-03

Pos logit contributions
 Some+0.016
 cheese+0.015
 of+0.015
 can+0.014
 There+0.013
Neg logit contributions
irling-0.015
 forth-0.014
ault-0.013
 salon-0.013
inge-0.013
Token you
Token ID345
Feature activation+7.88e-02

Pos logit contributions
 cheese+0.006
 Some+0.006
 pizz+0.005
oke+0.005
 wine+0.005
Neg logit contributions
 forth-0.019
irling-0.019
ault-0.018
 salon-0.018
 wrist-0.017
Token can
Token ID460
Feature activation+3.08e-02

Pos logit contributions
 cheese+0.059
 Some+0.059
 pizz+0.057
oke+0.051
 Their+0.051
Neg logit contributions
 forth-0.198
ault-0.195
irling-0.185
 salon-0.181
icycle-0.180
Token says
Token ID1139
Feature activation-7.14e-03

Pos logit contributions
 cheese+0.005
 Some+0.004
 wine+0.004
 Their+0.004
 pizz+0.004
Neg logit contributions
 forth-0.007
irling-0.007
 salon-0.007
ault-0.006
icycle-0.006
Token.
Token ID13
Feature activation+1.75e-02

Pos logit contributions
 forth+0.013
 wrist+0.013
irling+0.012
 salon+0.012
ault+0.012
Neg logit contributions
 cheese-0.011
 Some-0.010
 mushrooms-0.009
 meat-0.009
 pizz-0.009
Token
Token ID198
Feature activation+1.42e-02

Pos logit contributions
ocol+0.023
 cheese+0.022
 pizz+0.020
 wine+0.020
 mushrooms+0.019
Neg logit contributions
 salon-0.031
 forth-0.031
icycle-0.030
irling-0.030
 wrist-0.030
Token
Token ID198
Feature activation+1.14e-02

Pos logit contributions
 cheese+0.015
 Some+0.013
 pizz+0.013
 wine+0.012
 mushrooms+0.012
Neg logit contributions
irling-0.033
 forth-0.032
 salon-0.031
ault-0.030
icycle-0.030
TokenThey
Token ID2990
Feature activation-1.17e-02

Pos logit contributions
 Some+0.015
 cheese+0.015
 of+0.015
oke+0.014
 Their+0.013
Neg logit contributions
 forth-0.024
irling-0.023
ault-0.023
 salon-0.023
 wrist-0.022
Token follow
Token ID1061
Feature activation-6.32e-03

Pos logit contributions
irling+0.025
 forth+0.024
 salon+0.023
liv+0.023
icycle+0.022
Neg logit contributions
 cheese-0.015
 of-0.014
 Some-0.014
 can-0.014
 There-0.013
Token the
Token ID262
Feature activation+3.14e-02

Pos logit contributions
 forth+0.013
ault+0.012
irling+0.012
 salon+0.012
 wrist+0.012
Neg logit contributions
 cheese-0.008
 Some-0.008
oke-0.008
 pizz-0.007
 ago-0.007
Token trail
Token ID8025
Feature activation-4.88e-03

Pos logit contributions
 cheese+0.050
 words+0.047
 of+0.046
 Some+0.045
 can+0.043
Neg logit contributions
irling-0.063
 forth-0.059
ault-0.055
liv-0.055
inge-0.055
Token and
Token ID290
Feature activation-1.38e-03

Pos logit contributions
 forth+0.011
irling+0.011
 salon+0.011
ault+0.011
 wrist+0.010
Neg logit contributions
 cheese-0.005
 Some-0.005
 pizz-0.004
oke-0.004
 wine-0.004
Token find
Token ID1064
Feature activation+6.99e-03

Pos logit contributions
irling+0.003
 forth+0.003
icycle+0.002
 salon+0.002
ault+0.002
Neg logit contributions
 cheese-0.002
 Some-0.002
 of-0.002
 There-0.002
 Their-0.002
Token Tom
Token ID4186
Feature activation-2.29e-02

Pos logit contributions
oke+0.009
 ago+0.009
 cheese+0.009
 Some+0.008
 pizz+0.008
Neg logit contributions
 forth-0.013
ault-0.012
irling-0.012
 wrist-0.012
 salon-0.011
Token house
Token ID2156
Feature activation+3.54e-03

Pos logit contributions
 forth+0.012
irling+0.012
ault+0.011
 salon+0.011
inge+0.010
Neg logit contributions
 cheese-0.016
 Some-0.015
 of-0.014
 pizz-0.014
 wine-0.014
Token."
Token ID526
Feature activation+5.98e-03

Pos logit contributions
 cheese+0.004
 Some+0.004
 of+0.004
oke+0.004
 pizz+0.004
Neg logit contributions
 forth-0.008
irling-0.008
 salon-0.007
ault-0.007
 wrist-0.007
Token The
Token ID383
Feature activation+3.02e-02

Pos logit contributions
 cheese+0.006
 Some+0.005
 pizz+0.005
oke+0.004
 of+0.004
Neg logit contributions
 forth-0.014
irling-0.014
 salon-0.014
ault-0.013
 wrist-0.013
Token lion
Token ID18744
Feature activation+2.75e-02

Pos logit contributions
 Their+0.042
 Some+0.042
 of+0.040
 There+0.040
oke+0.040
Neg logit contributions
 forth-0.058
irling-0.051
 salon-0.050
ault-0.049
 wrist-0.047
Token was
Token ID373
Feature activation-4.08e-03

Pos logit contributions
 cheese+0.035
 of+0.031
 Some+0.030
oke+0.027
 pizz+0.027
Neg logit contributions
irling-0.060
 forth-0.060
ault-0.059
 salon-0.057
icycle-0.055
Token very
Token ID845
Feature activation-6.10e-03

Pos logit contributions
 forth+0.010
 salon+0.009
irling+0.009
ault+0.009
icycle+0.009
Neg logit contributions
 of-0.004
 cheese-0.004
 Some-0.004
 about-0.004
 time-0.004
Token proud
Token ID6613
Feature activation-2.12e-02

Pos logit contributions
 forth+0.011
irling+0.011
 salon+0.011
ault+0.010
icycle+0.010
Neg logit contributions
 cheese-0.010
 Some-0.009
 of-0.009
oke-0.009
 Their-0.008
Token of
Token ID286
Feature activation+5.44e-03

Pos logit contributions
 forth+0.059
irling+0.057
 salon+0.056
ault+0.055
 wrist+0.053
Neg logit contributions
 cheese-0.012
 Some-0.012
 pizz-0.009
 Their-0.009
oke-0.009
Token himself
Token ID2241
Feature activation+1.18e-02

Pos logit contributions
 cheese+0.008
 Some+0.008
oke+0.007
 pizz+0.007
 of+0.007
Neg logit contributions
 forth-0.010
irling-0.010
 salon-0.010
ault-0.010
inge-0.009
Token.
Token ID13
Feature activation-5.46e-04

Pos logit contributions
 Some+0.011
 cheese+0.011
 pizz+0.009
 Their+0.009
oke+0.009
Neg logit contributions
 forth-0.029
irling-0.028
ault-0.028
 salon-0.027
 wrist-0.026
Token From
Token ID3574
Feature activation+1.82e-02

Pos logit contributions
 forth+0.001
irling+0.001
 salon+0.001
ault+0.001
icycle+0.001
Neg logit contributions
 cheese-0.001
 Some-0.000
 pizz-0.000
 wine-0.000
oke-0.000
Token crying
Token ID13774
Feature activation+2.36e-02

Pos logit contributions
 forth+0.012
irling+0.012
 salon+0.011
ault+0.011
 wrist+0.011
Neg logit contributions
 cheese-0.007
 Some-0.007
 of-0.006
 pizz-0.006
oke-0.006
Token because
Token ID780
Feature activation-3.41e-02

Pos logit contributions
 Some+0.027
 cheese+0.026
 pizz+0.024
oke+0.024
 ago+0.023
Neg logit contributions
 forth-0.056
irling-0.051
ault-0.049
 salon-0.049
 wrist-0.047
Token he
Token ID339
Feature activation-2.74e-02

Pos logit contributions
 forth+0.068
irling+0.066
 salon+0.063
ault+0.063
inge+0.059
Neg logit contributions
 cheese-0.048
 Some-0.046
oke-0.042
 pizz-0.042
 of-0.041
Token lost
Token ID2626
Feature activation-1.45e-02

Pos logit contributions
 forth+0.057
irling+0.056
ault+0.053
 salon+0.053
 wrist+0.050
Neg logit contributions
 cheese-0.037
 Some-0.035
 of-0.032
oke-0.031
 pizz-0.031
Token his
Token ID465
Feature activation-3.16e-02

Pos logit contributions
 forth+0.028
ault+0.025
 salon+0.025
irling+0.025
 wrist+0.025
Neg logit contributions
oke-0.022
 Some-0.021
 There-0.019
izza-0.019
 ago-0.018
Token toy
Token ID13373
Feature activation-6.17e-02

Pos logit contributions
 forth+0.063
 salon+0.058
irling+0.058
 wrist+0.057
ault+0.056
Neg logit contributions
 Some-0.045
oke-0.045
 cheese-0.041
 Their-0.040
 There-0.040
Token.
Token ID13
Feature activation-1.02e-02

Pos logit contributions
 forth+0.149
irling+0.144
 salon+0.141
ault+0.140
 wrist+0.135
Neg logit contributions
 cheese-0.059
 Some-0.059
oke-0.052
 pizz-0.050
 Their-0.049
Token
Token ID220
Feature activation-3.06e-02

Pos logit contributions
 forth+0.022
irling+0.021
 salon+0.021
liv+0.020
icycle+0.020
Neg logit contributions
 cheese-0.012
 pizz-0.011
 Some-0.011
ocol-0.010
oke-0.010
Token
Token ID198
Feature activation-8.85e-03

Pos logit contributions
irling+0.062
 forth+0.061
icycle+0.059
liv+0.059
 salon+0.058
Neg logit contributions
 cheese-0.039
 pizz-0.035
 wine-0.033
 peppers-0.033
 Some-0.033
Token
Token ID198
Feature activation-7.15e-03

Pos logit contributions
irling+0.019
 forth+0.019
 salon+0.018
liv+0.018
icycle+0.018
Neg logit contributions
 cheese-0.010
 pizz-0.009
 Some-0.009
 wine-0.009
 mushrooms-0.008
TokenL
Token ID43
Feature activation-1.83e-02

Pos logit contributions
 forth+0.015
irling+0.015
ault+0.014
 salon+0.014
 wrist+0.014
Neg logit contributions
 cheese-0.009
 Some-0.009
 of-0.009
 Their-0.008
oke-0.008
Token understand
Token ID1833
Feature activation-1.15e-02

Pos logit contributions
 forth+0.059
ault+0.055
irling+0.055
 salon+0.053
inge+0.051
Neg logit contributions
 cheese-0.038
 Some-0.038
 pizz-0.034
oke-0.034
 Their-0.033
Token why
Token ID1521
Feature activation-2.49e-02

Pos logit contributions
 forth+0.021
 salon+0.019
irling+0.018
ault+0.017
 wrist+0.017
Neg logit contributions
 Some-0.018
izza-0.018
 ago-0.017
oke-0.017
lic-0.017
Token she
Token ID673
Feature activation-4.70e-02

Pos logit contributions
 forth+0.044
 salon+0.043
irling+0.042
ault+0.039
 wrist+0.037
Neg logit contributions
 Some-0.038
oke-0.037
 cheese-0.036
 pizz-0.035
izza-0.034
Token could
Token ID714
Feature activation-3.16e-02

Pos logit contributions
 forth+0.094
irling+0.089
 salon+0.085
ault+0.084
 wrist+0.080
Neg logit contributions
 Some-0.068
 cheese-0.068
 pizz-0.062
 of-0.060
oke-0.059
Token not
Token ID407
Feature activation-3.07e-02

Pos logit contributions
 forth+0.057
irling+0.055
 salon+0.053
ault+0.053
 wrist+0.050
Neg logit contributions
 cheese-0.051
 Some-0.050
oke-0.046
 pizz-0.045
 of-0.045
Token have
Token ID423
Feature activation-6.43e-02

Pos logit contributions
 forth+0.057
irling+0.056
ault+0.053
 salon+0.053
 wrist+0.050
Neg logit contributions
 cheese-0.047
 Some-0.046
 of-0.042
oke-0.042
 pizz-0.042
Token the
Token ID262
Feature activation-3.42e-02

Pos logit contributions
 forth+0.123
irling+0.121
 salon+0.113
ault+0.112
 wrist+0.109
Neg logit contributions
oke-0.086
 Some-0.079
izza-0.075
 There-0.075
 ago-0.073
Token wine
Token ID8237
Feature activation-2.68e-02

Pos logit contributions
 salon+0.068
 forth+0.068
 wrist+0.065
irling+0.064
ault+0.062
Neg logit contributions
 Some-0.040
oke-0.040
 cheese-0.039
izza-0.038
 Their-0.038
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
 forth+0.058
 salon+0.057
ault+0.054
 wrist+0.052
irling+0.051
Neg logit contributions
 Some-0.032
oke-0.027
ocol-0.027
 cheese-0.027
 Their-0.026
Token
Token ID198
Feature activation-3.51e-03

Pos logit contributions
 forth+0.019
 salon+0.018
irling+0.018
liv+0.018
 wrist+0.018
Neg logit contributions
 cheese-0.014
 pizz-0.014
ocol-0.013
oke-0.013
 Some-0.013
Token
Token ID198
Feature activation-1.25e-03

Pos logit contributions
irling+0.007
liv+0.006
 forth+0.006
 salon+0.006
icycle+0.006
Neg logit contributions
 cheese-0.005
 pizz-0.004
ocol-0.004
 peppers-0.004
 ago-0.004
Token The
Token ID383
Feature activation+1.49e-02

Pos logit contributions
 forth+0.009
 salon+0.009
irling+0.009
 wrist+0.009
liv+0.008
Neg logit contributions
 cheese-0.004
ocol-0.004
 pizz-0.004
oke-0.004
 ago-0.004
Token bird
Token ID6512
Feature activation-4.10e-03

Pos logit contributions
 Some+0.022
oke+0.022
 Their+0.021
 pizz+0.021
ocol+0.021
Neg logit contributions
 forth-0.028
irling-0.025
ault-0.024
 salon-0.024
 swing-0.023
Token was
Token ID373
Feature activation-1.15e-02

Pos logit contributions
 forth+0.008
irling+0.008
 salon+0.008
ault+0.008
icycle+0.008
Neg logit contributions
 cheese-0.005
 Some-0.005
 of-0.005
oke-0.005
 pizz-0.005
Token sad
Token ID6507
Feature activation+1.64e-02

Pos logit contributions
 forth+0.025
irling+0.025
 salon+0.025
ault+0.024
icycle+0.024
Neg logit contributions
 cheese-0.014
 Some-0.013
 of-0.013
 Their-0.012
 wine-0.011
Token,
Token ID11
Feature activation-2.81e-02

Pos logit contributions
 cheese+0.017
 Some+0.016
 pizz+0.015
oke+0.014
 wine+0.014
Neg logit contributions
 forth-0.039
irling-0.038
 salon-0.036
ault-0.036
 wrist-0.034
Token but
Token ID475
Feature activation-5.76e-02

Pos logit contributions
irling+0.071
 forth+0.069
icycle+0.069
 salon+0.068
ault+0.068
Neg logit contributions
 cheese-0.026
 Some-0.024
 of-0.022
 time-0.020
 Their-0.019
Token it
Token ID340
Feature activation-1.49e-02

Pos logit contributions
irling+0.116
 forth+0.115
 salon+0.112
ault+0.111
icycle+0.107
Neg logit contributions
 cheese-0.082
 Some-0.077
 of-0.073
 Their-0.069
 wine-0.069
Token did
Token ID750
Feature activation-1.32e-02

Pos logit contributions
 forth+0.031
irling+0.030
 salon+0.030
ault+0.029
icycle+0.028
Neg logit contributions
 cheese-0.020
 Some-0.019
 of-0.018
 Their-0.017
 pizz-0.017
Token not
Token ID407
Feature activation-7.25e-03

Pos logit contributions
 forth+0.026
 salon+0.026
irling+0.025
icycle+0.025
ault+0.025
Neg logit contributions
 cheese-0.019
 Some-0.018
 of-0.017
 time-0.017
 Their-0.016
Token give
Token ID1577
Feature activation-3.13e-02

Pos logit contributions
 forth+0.014
irling+0.013
ault+0.013
 salon+0.013
inge+0.012
Neg logit contributions
 cheese-0.011
 Some-0.011
oke-0.010
 pizz-0.010
 Their-0.009
Token up
Token ID510
Feature activation-3.06e-02

Pos logit contributions
 forth+0.038
ault+0.030
irling+0.025
aults+0.022
 wrist+0.021
Neg logit contributions
oke-0.075
 Some-0.073
 ago-0.071
lic-0.067
 pizz-0.067
Token that
Token ID326
Feature activation-1.56e-02

Pos logit contributions
 cheese+0.014
 Some+0.013
 of+0.013
 wine+0.012
 Their+0.012
Neg logit contributions
 forth-0.023
irling-0.023
 salon-0.022
ault-0.022
icycle-0.021
Token he
Token ID339
Feature activation-1.31e-02

Pos logit contributions
 forth+0.033
irling+0.033
ault+0.031
 salon+0.031
icycle+0.030
Neg logit contributions
 cheese-0.021
 Some-0.019
 of-0.018
 pizz-0.017
 wine-0.017
Token had
Token ID550
Feature activation+2.54e-03

Pos logit contributions
 forth+0.029
irling+0.029
 salon+0.028
ault+0.028
 wrist+0.026
Neg logit contributions
 cheese-0.015
 Some-0.015
 of-0.013
oke-0.013
 pizz-0.013
Token made
Token ID925
Feature activation-9.01e-03

Pos logit contributions
 cheese+0.003
 Some+0.003
 of+0.003
oke+0.003
 pizz+0.003
Neg logit contributions
 forth-0.005
irling-0.005
 salon-0.005
ault-0.005
inge-0.005
Token a
Token ID257
Feature activation-2.78e-02

Pos logit contributions
 forth+0.020
irling+0.020
ault+0.019
 salon+0.019
inge+0.018
Neg logit contributions
 Some-0.009
oke-0.009
 cheese-0.009
 ago-0.009
 There-0.008
Token terrible
Token ID7818
Feature activation-5.57e-02

Pos logit contributions
 forth+0.054
irling+0.054
ault+0.050
 salon+0.050
icycle+0.048
Neg logit contributions
 cheese-0.042
 Some-0.039
 of-0.036
 pizz-0.036
 wine-0.035
Token mistake
Token ID7457
Feature activation-2.33e-02

Pos logit contributions
 forth+0.092
irling+0.089
ault+0.084
 salon+0.084
inge+0.078
Neg logit contributions
 cheese-0.099
 Some-0.096
 of-0.089
 pizz-0.088
oke-0.088
Token and
Token ID290
Feature activation-6.13e-03

Pos logit contributions
 forth+0.054
irling+0.052
ault+0.051
 salon+0.051
 wrist+0.047
Neg logit contributions
 cheese-0.025
 Some-0.025
 pizz-0.021
 Their-0.021
izza-0.020
Token felt
Token ID2936
Feature activation-2.25e-02

Pos logit contributions
 forth+0.012
irling+0.012
 salon+0.011
ault+0.011
inge+0.011
Neg logit contributions
 cheese-0.009
 Some-0.009
 of-0.008
 pizz-0.008
oke-0.008
Token bad
Token ID2089
Feature activation-2.16e-02

Pos logit contributions
 forth+0.043
irling+0.042
ault+0.041
inge+0.039
 salon+0.038
Neg logit contributions
 cheese-0.032
oke-0.030
 Some-0.030
 pizz-0.029
izza-0.029
Token.
Token ID13
Feature activation-1.45e-02

Pos logit contributions
 forth+0.054
irling+0.053
ault+0.051
 salon+0.051
 wrist+0.048
Neg logit contributions
 cheese-0.019
 Some-0.019
 pizz-0.016
oke-0.015
 Their-0.015
Token,
Token ID11
Feature activation-3.49e-03

Pos logit contributions
 forth+0.020
irling+0.020
 salon+0.019
ault+0.019
inge+0.018
Neg logit contributions
 cheese-0.015
 Some-0.014
 of-0.014
 pizz-0.013
oke-0.013
Token but
Token ID475
Feature activation-2.78e-02

Pos logit contributions
irling+0.008
 forth+0.008
ault+0.008
 salon+0.008
icycle+0.008
Neg logit contributions
 cheese-0.004
 Some-0.003
 of-0.003
 wine-0.003
 Their-0.003
Token she
Token ID673
Feature activation-2.75e-02

Pos logit contributions
irling+0.060
 forth+0.058
icycle+0.057
ault+0.056
 salon+0.054
Neg logit contributions
 cheese-0.035
 Some-0.033
 of-0.033
 wine-0.030
 Their-0.029
Token wouldn
Token ID3636
Feature activation-1.81e-03

Pos logit contributions
 forth+0.059
irling+0.058
ault+0.056
 salon+0.055
 wrist+0.053
Neg logit contributions
 cheese-0.034
 of-0.032
 Some-0.032
oke-0.030
 time-0.029
Token't
Token ID470
Feature activation-5.57e-03

Pos logit contributions
 forth+0.003
irling+0.003
 salon+0.003
 wrist+0.003
ault+0.003
Neg logit contributions
 of-0.003
 Some-0.003
 cheese-0.003
 There-0.002
oke-0.002
Token let
Token ID1309
Feature activation-6.64e-02

Pos logit contributions
irling+0.013
liv+0.012
icycle+0.012
 salon+0.012
 forth+0.012
Neg logit contributions
 of-0.007
 cheese-0.006
 time-0.006
 can-0.005
 Some-0.005
Token them
Token ID606
Feature activation+1.27e-02

Pos logit contributions
 forth+0.115
ault+0.108
 salon+0.107
irling+0.105
 wrist+0.097
Neg logit contributions
 cheese-0.111
 Some-0.110
oke-0.103
 pizz-0.102
 ago-0.098
Token.
Token ID13
Feature activation-6.41e-03

Pos logit contributions
 of+0.015
 cheese+0.014
 time+0.012
 Some+0.012
 Their+0.012
Neg logit contributions
irling-0.029
liv-0.027
 forth-0.027
 salon-0.027
icycle-0.027
Token She
Token ID1375
Feature activation-1.55e-02

Pos logit contributions
 forth+0.012
irling+0.012
 salon+0.012
ault+0.011
 wrist+0.011
Neg logit contributions
 cheese-0.009
 Some-0.008
 pizz-0.008
 of-0.008
oke-0.008
Token was
Token ID373
Feature activation-4.75e-03

Pos logit contributions
irling+0.031
 forth+0.031
ault+0.030
 salon+0.029
icycle+0.028
Neg logit contributions
 cheese-0.022
 Some-0.020
 of-0.020
 Their-0.018
 time-0.018
Token fierce
Token ID14800
Feature activation+2.21e-02

Pos logit contributions
 forth+0.010
irling+0.010
ault+0.010
 salon+0.010
icycle+0.009
Neg logit contributions
 cheese-0.006
 Some-0.006
 of-0.006
 Their-0.005
 time-0.005