TOP ACTIVATIONS
MAX = 0.108

with lots of other b unn ies . George was always
was a family of b unn ies . The b unn
my told her that b unn ies can be scared easily
there were two little b unn ies . They were best
Do you know what b unn ies eat ?"
ummy food for the b unn ies . It started with
was a family of b unn ies . They loved to
. <|endoftext|> Lisa loved her velvet bear very much . She
choose one of these b unn ies to come with us
you . You love b unn ies , right ?" Lily
there were two little b unn ies called Bob and Su
my , what do b unn ies do ?"
unn ies . The b unn ies lived in a cozy
Do you like the b unn ies ?" the lady asks
Fred played with the b unn ies all day , hopping
little girl who loved her rubber . Every day she found
of a family of b unn ies . One day one
my , do these b unn ies live here ?"
was ready , the b unn ies hopped over to the
He had taught the b unn ies to be friendly .

MIN ACTIVATIONS
MIN = -0.134

listen . She threw a tant rum in the store .
. He kept throwing a tant rum . His mom was
her feet and threw a tant rum . She grabbed the
She cried and threw a tant rum . Her mom tried
watched the colorful lights in amaz ement , feeling truly lucky
to cry and threw a tant rum . She didn 't
kept crying and throwing a tant rum . Finally
sad . She threw a tant rum and cried loudly .
and started to throw a tant rum . Suddenly , she
ered in , blinking in amaz ement . But
surprise . He threw a tant rum . He kicked and
. The deer stared in amaz ement . He had never
seen ! She gasped in amaz ement , and her tears
! They looked around in amaz ement and quickly closed the
curtains , she gasped in amaz ement . It was snow
looked at the rainbow in amaz ement and laughed with joy
looked at the rainbow in amaz ement and laughed with joy
. Tiger looked around in amaz ement and he knew he
ice . They stared in amaz ement . They wanted to
She opened her mouth in amaz ement . She had never

INTERVAL 0.048 - 0.108
CONTAINS 1.714%

to be careful because his wings were fragile and could break
winning . The persistent friend tried their best , but they
He felt like he didn 't belong . M
, Lucy took out her sewing machine . She carefully loaded
for you . You don 't have to be sad or

INTERVAL -0.013 - 0.048
CONTAINS 72.038%

on , Lily always picked herbs and covered her room with
safe . She quickly grabbed the laser and hid it away
know , Rover ," she said . That night
he didn 't behave , he wouldn 't receive any presents
. Clara asked her mom my what they were going to

INTERVAL -0.073 - -0.013
CONTAINS 26.206%

Are you ready for the meeting ? â € M addy
with soft fur and big eyes . One day , Lily
had just seen something truly magical . <|endoftext|> Once upon a
out came a big , foolish snake ! The snake was
of the garden . But they are too high for you

INTERVAL -0.134 - -0.073
CONTAINS 0.042%

went to bed with a smile on his face . <|endoftext|>
rode away with a big smile . He felt happy and
ride my bike now ? Please ?" M ummy
granted ! The star shone brightly and lit the night sky
. Tiger looked around in amaz ement and he knew he
Token with
Token ID351
Feature activation-1.60e-02

Pos logit contributions
 unison+0.015
 slices+0.014
 seventeen+0.014
 amaz+0.014
 aroma+0.014
Neg logit contributions
 wear-0.009
 Woo-0.009
 bath-0.008
 Mitt-0.008
 day-0.008
Token lots
Token ID6041
Feature activation-1.94e-02

Pos logit contributions
 slices+0.033
 unison+0.033
 amaz+0.033
 seventeen+0.032
 seconds+0.032
Neg logit contributions
 wear-0.019
 Woo-0.018
 bath-0.017
burn-0.016
 skipping-0.016
Token of
Token ID286
Feature activation+1.46e-02

Pos logit contributions
 slices+0.040
 unison+0.039
 seconds+0.039
 amaz+0.038
 seventeen+0.038
Neg logit contributions
 wear-0.024
 Woo-0.023
burn-0.021
 bath-0.021
 Mitt-0.020
Token other
Token ID584
Feature activation-7.72e-03

Pos logit contributions
 wear+0.024
burn+0.024
 Woo+0.023
 bath+0.021
 stub+0.021
Neg logit contributions
 slices-0.023
 amaz-0.022
 aroma-0.022
 seconds-0.022
 unison-0.022
Token b
Token ID275
Feature activation+2.97e-02

Pos logit contributions
 slices+0.013
 unison+0.013
 amaz+0.013
 aroma+0.013
fires+0.013
Neg logit contributions
 wear-0.012
 Woo-0.011
 bath-0.011
burn-0.011
 Lucky-0.010
Tokenunn
Token ID20935
Feature activation+1.08e-01

Pos logit contributions
 wear+0.030
 Woo+0.028
 bath+0.026
 Lucky+0.025
 Mitt+0.024
Neg logit contributions
 slices-0.069
 pulp-0.065
 seventeen-0.065
fires-0.064
pter-0.064
Tokenies
Token ID444
Feature activation+3.02e-02

Pos logit contributions
 wear+0.159
 Woo+0.152
 bath+0.147
 Lucky+0.137
 Mitt+0.137
Neg logit contributions
 slices-0.195
 pulp-0.184
pter-0.184
fires-0.184
 unison-0.184
Token.
Token ID13
Feature activation+1.65e-02

Pos logit contributions
 wear+0.047
 Woo+0.045
 bath+0.043
burn+0.043
 Mitt+0.042
Neg logit contributions
 slices-0.050
 unison-0.049
fires-0.048
 seconds-0.047
pter-0.047
Token George
Token ID4502
Feature activation+2.83e-02

Pos logit contributions
 wear+0.018
 Woo+0.016
 bath+0.016
 Mitt+0.015
 Lucky+0.014
Neg logit contributions
 unison-0.036
 slices-0.036
 seventeen-0.036
 amaz-0.035
 aroma-0.035
Token was
Token ID373
Feature activation+9.30e-03

Pos logit contributions
 Woo+0.043
 wear+0.042
burn+0.042
 bath+0.041
 Mitt+0.039
Neg logit contributions
 unison-0.047
 slices-0.046
fires-0.046
pter-0.045
 seconds-0.045
Token always
Token ID1464
Feature activation+3.11e-02

Pos logit contributions
burn+0.016
 wear+0.016
ibi+0.016
ogging+0.016
ongo+0.016
Neg logit contributions
 seconds-0.012
 amaz-0.011
 seventeen-0.011
 thirteen-0.011
fires-0.011
Token was
Token ID373
Feature activation+6.98e-03

Pos logit contributions
 wear+0.049
 Woo+0.048
burn+0.046
 bath+0.044
 important+0.043
Neg logit contributions
 amaz-0.047
 unison-0.046
 slices-0.046
 seconds-0.044
 aroma-0.043
Token a
Token ID257
Feature activation+2.01e-02

Pos logit contributions
 wear+0.013
burn+0.012
ongo+0.011
 Woo+0.011
 jog+0.011
Neg logit contributions
 slices-0.011
 unison-0.010
 conf-0.010
 amaz-0.009
 seconds-0.009
Token family
Token ID1641
Feature activation-2.80e-02

Pos logit contributions
ained+0.029
 wear+0.029
 Woo+0.027
burn+0.027
scar+0.026
Neg logit contributions
 unison-0.035
 aroma-0.033
 slices-0.033
 amaz-0.033
 pulp-0.032
Token of
Token ID286
Feature activation+4.28e-02

Pos logit contributions
 slices+0.040
 unison+0.038
pter+0.037
 seconds+0.036
 candles+0.035
Neg logit contributions
 Lucky-0.046
 Woo-0.045
scar-0.043
ibi-0.043
 Nut-0.043
Token b
Token ID275
Feature activation+3.84e-02

Pos logit contributions
 wear+0.070
 Woo+0.064
 bath+0.063
burn+0.063
scar+0.062
Neg logit contributions
 unison-0.067
 slices-0.066
 seconds-0.066
 pulp-0.065
 conf-0.064
Tokenunn
Token ID20935
Feature activation+1.08e-01

Pos logit contributions
 wear+0.044
 Woo+0.041
 bath+0.039
 Lucky+0.039
 Mitt+0.037
Neg logit contributions
 slices-0.083
 pulp-0.079
pter-0.077
als-0.077
 seventeen-0.076
Tokenies
Token ID444
Feature activation+3.60e-02

Pos logit contributions
 wear+0.166
 Woo+0.155
 bath+0.153
 Lucky+0.144
 Mitt+0.142
Neg logit contributions
 slices-0.184
pter-0.176
 pulp-0.175
 unison-0.175
fires-0.175
Token.
Token ID13
Feature activation+1.39e-02

Pos logit contributions
 wear+0.061
 Woo+0.058
ibi+0.057
 bath+0.057
scar+0.056
Neg logit contributions
 unison-0.052
 slices-0.049
fires-0.048
 seconds-0.047
pter-0.047
Token The
Token ID383
Feature activation+2.25e-02

Pos logit contributions
 wear+0.026
 Woo+0.024
 important+0.024
burn+0.024
 bath+0.024
Neg logit contributions
 unison-0.020
 slices-0.019
 seventeen-0.019
 amaz-0.018
 aroma-0.018
Token b
Token ID275
Feature activation+3.03e-02

Pos logit contributions
 wear+0.032
scar+0.031
ogging+0.030
 Razor+0.029
ongo+0.029
Neg logit contributions
 aroma-0.038
 slices-0.038
 unison-0.037
 pulp-0.037
 amaz-0.036
Tokenunn
Token ID20935
Feature activation+1.02e-01

Pos logit contributions
 wear+0.037
 bath+0.035
 Woo+0.034
 jog+0.034
 Lucky+0.034
Neg logit contributions
als-0.060
 slices-0.059
 pulp-0.058
edly-0.057
pter-0.056
Tokenmy
Token ID1820
Feature activation+1.56e-02

Pos logit contributions
 slices+0.052
 aroma+0.050
 amaz+0.049
 unison+0.049
 gasped+0.049
Neg logit contributions
 Woo-0.029
 bath-0.029
 wear-0.028
 jog-0.025
 exercise-0.024
Token told
Token ID1297
Feature activation-1.75e-03

Pos logit contributions
 bath+0.026
 wear+0.025
 Woo+0.025
 jog+0.023
ained+0.023
Neg logit contributions
 slices-0.024
 aroma-0.023
 unison-0.023
 seconds-0.023
 gasped-0.022
Token her
Token ID607
Feature activation+2.49e-02

Pos logit contributions
 unison+0.004
 slices+0.004
 seventeen+0.004
 amaz+0.004
fires+0.004
Neg logit contributions
 wear-0.001
 Woo-0.001
 bath-0.001
 Mitt-0.001
 Lucky-0.001
Token that
Token ID326
Feature activation+5.34e-02

Pos logit contributions
 wear+0.035
 Woo+0.033
 bath+0.032
burn+0.030
 Mitt+0.030
Neg logit contributions
 slices-0.045
 unison-0.044
 amaz-0.044
 seconds-0.044
 seventeen-0.044
Token b
Token ID275
Feature activation+2.44e-02

Pos logit contributions
 wear+0.082
 bath+0.074
ibi+0.074
ongo+0.074
 Woo+0.073
Neg logit contributions
 slices-0.091
 seconds-0.086
 pulp-0.086
 amaz-0.086
 conf-0.085
Tokenunn
Token ID20935
Feature activation+1.07e-01

Pos logit contributions
 wear+0.028
 bath+0.025
 Woo+0.025
 jog+0.024
 skipping+0.023
Neg logit contributions
 slices-0.053
als-0.051
 pulp-0.050
rs-0.050
 seconds-0.050
Tokenies
Token ID444
Feature activation+3.07e-02

Pos logit contributions
 wear+0.156
 Woo+0.148
 bath+0.144
 Mitt+0.134
 skipping+0.134
Neg logit contributions
 slices-0.190
 unison-0.185
 pulp-0.184
pter-0.182
 aroma-0.181
Token can
Token ID460
Feature activation+2.13e-02

Pos logit contributions
 wear+0.057
 Woo+0.057
 bath+0.055
burn+0.053
 Mitt+0.053
Neg logit contributions
 slices-0.039
 unison-0.039
fires-0.038
 aroma-0.038
 amaz-0.037
Token be
Token ID307
Feature activation+4.11e-03

Pos logit contributions
 Woo+0.031
 important+0.030
scar+0.030
 bath+0.029
 day+0.029
Neg logit contributions
 unison-0.032
 seventeen-0.032
als-0.031
 slices-0.031
 aroma-0.030
Token scared
Token ID12008
Feature activation+4.16e-02

Pos logit contributions
 wear+0.005
 bath+0.005
scar+0.005
ibi+0.005
burn+0.005
Neg logit contributions
 slices-0.007
 seconds-0.007
 unison-0.007
 pulp-0.007
 aroma-0.007
Token easily
Token ID3538
Feature activation+3.94e-02

Pos logit contributions
 wear+0.056
 Woo+0.052
burn+0.049
 bath+0.049
scar+0.048
Neg logit contributions
 slices-0.078
 seconds-0.077
 unison-0.076
 amaz-0.074
fires-0.074
Token there
Token ID612
Feature activation+3.36e-02

Pos logit contributions
 wear+0.032
 Woo+0.031
 bath+0.029
burn+0.029
 Mitt+0.028
Neg logit contributions
 slices-0.035
 unison-0.035
 seventeen-0.034
 amaz-0.033
 seconds-0.033
Token were
Token ID547
Feature activation-1.98e-02

Pos logit contributions
 wear+0.053
 Woo+0.052
burn+0.050
 bath+0.048
 important+0.046
Neg logit contributions
 amaz-0.055
 slices-0.054
 unison-0.054
 seconds-0.052
 seventeen-0.051
Token two
Token ID734
Feature activation+3.09e-02

Pos logit contributions
 slices+0.035
 conf+0.032
 seventeen+0.032
 pulp+0.031
 unison+0.031
Neg logit contributions
 wear-0.033
 Woo-0.028
 jog-0.027
burn-0.027
ibi-0.027
Token little
Token ID1310
Feature activation+3.47e-02

Pos logit contributions
 wear+0.036
 Woo+0.034
 bath+0.031
burn+0.029
 Lucky+0.028
Neg logit contributions
 slices-0.067
 unison-0.066
 seventeen-0.064
 amaz-0.064
 seconds-0.063
Token b
Token ID275
Feature activation+3.53e-02

Pos logit contributions
 wear+0.056
 Woo+0.052
 bath+0.052
 Mitt+0.049
 Lucky+0.048
Neg logit contributions
 unison-0.058
 slices-0.058
 seventeen-0.058
 amaz-0.057
fires-0.056
Tokenunn
Token ID20935
Feature activation+1.05e-01

Pos logit contributions
 wear+0.042
 Woo+0.039
 bath+0.038
 Lucky+0.035
 jog+0.035
Neg logit contributions
 slices-0.077
 pulp-0.073
 seventeen-0.071
pter-0.071
als-0.069
Tokenies
Token ID444
Feature activation+3.21e-02

Pos logit contributions
 wear+0.171
 Woo+0.163
 bath+0.160
 jog+0.150
 Lucky+0.147
Neg logit contributions
 slices-0.172
pter-0.163
 pulp-0.163
fires-0.158
 seconds-0.157
Token.
Token ID13
Feature activation+1.71e-02

Pos logit contributions
 wear+0.054
 Woo+0.052
ibi+0.050
 bath+0.050
scar+0.048
Neg logit contributions
 unison-0.048
 slices-0.047
pter-0.044
 seconds-0.043
 ah-0.042
Token They
Token ID1119
Feature activation+1.22e-02

Pos logit contributions
 wear+0.025
 important+0.023
burn+0.022
 bath+0.022
 stub+0.022
Neg logit contributions
 unison-0.031
 slices-0.030
pter-0.029
 seventeen-0.029
 pulp-0.028
Token were
Token ID547
Feature activation-1.91e-02

Pos logit contributions
 wear+0.020
 Woo+0.019
 bath+0.018
 Mitt+0.017
 Lucky+0.017
Neg logit contributions
 unison-0.020
 slices-0.020
 seventeen-0.020
 amaz-0.019
 aroma-0.019
Token best
Token ID1266
Feature activation+2.93e-02

Pos logit contributions
 slices+0.030
 ah+0.029
 tur+0.029
 candles+0.029
 pulp+0.028
Neg logit contributions
 wear-0.028
ogging-0.028
ongo-0.027
 jog-0.027
ibi-0.027
TokenDo
Token ID5211
Feature activation+3.03e-03

Pos logit contributions
 amaz+0.062
 unison+0.062
 slices+0.061
 aroma+0.061
 seventeen+0.060
Neg logit contributions
 wear-0.058
 Woo-0.056
 jog-0.052
 bath-0.051
 day-0.051
Token you
Token ID345
Feature activation-3.37e-03

Pos logit contributions
 wear+0.004
 Woo+0.004
 bath+0.004
 Mitt+0.004
burn+0.004
Neg logit contributions
 unison-0.005
 slices-0.005
 seventeen-0.005
 amaz-0.005
 seconds-0.005
Token know
Token ID760
Feature activation+2.10e-02

Pos logit contributions
 unison+0.005
 seventeen+0.005
 seconds+0.005
 amaz+0.005
 slices+0.005
Neg logit contributions
 Woo-0.006
 bath-0.005
burn-0.005
 wear-0.005
 Mitt-0.005
Token what
Token ID644
Feature activation+8.61e-04

Pos logit contributions
 wear+0.039
 Woo+0.038
 bath+0.037
burn+0.035
 Mitt+0.034
Neg logit contributions
 unison-0.029
 slices-0.029
 seconds-0.028
 seventeen-0.028
 amaz-0.028
Token b
Token ID275
Feature activation+2.31e-02

Pos logit contributions
 wear+0.001
 Woo+0.001
 bath+0.001
burn+0.001
 Mitt+0.001
Neg logit contributions
 slices-0.001
 unison-0.001
 seconds-0.001
 seventeen-0.001
 amaz-0.001
Tokenunn
Token ID20935
Feature activation+1.05e-01

Pos logit contributions
 bath+0.026
 Woo+0.025
 wear+0.025
 skipping+0.024
 stub+0.024
Neg logit contributions
als-0.047
 slices-0.046
rs-0.045
teen-0.045
 aroma-0.044
Tokenies
Token ID444
Feature activation+4.85e-02

Pos logit contributions
 wear+0.149
 Woo+0.148
 bath+0.145
 Mitt+0.137
 skipping+0.135
Neg logit contributions
 slices-0.177
 aroma-0.175
 pulp-0.172
fires-0.170
pter-0.170
Token eat
Token ID4483
Feature activation+2.49e-02

Pos logit contributions
 wear+0.065
 Woo+0.065
 bath+0.062
 Mitt+0.060
burn+0.059
Neg logit contributions
 slices-0.088
 unison-0.087
 seventeen-0.086
 aroma-0.086
fires-0.085
Token?"
Token ID1701
Feature activation+7.29e-03

Pos logit contributions
 wear+0.026
 Woo+0.025
 bath+0.023
 Mitt+0.022
burn+0.022
Neg logit contributions
 slices-0.055
 unison-0.053
 seventeen-0.052
 aroma-0.052
fires-0.052
Token
Token ID198
Feature activation+1.47e-02

Pos logit contributions
burn+0.012
 wear+0.011
 important+0.011
 bath+0.010
scar+0.010
Neg logit contributions
 slices-0.012
 seconds-0.012
 amaz-0.011
 unison-0.011
 pulp-0.011
Token
Token ID198
Feature activation+3.91e-03

Pos logit contributions
 wear+0.025
burn+0.024
 important+0.022
 Woo+0.022
 bath+0.022
Neg logit contributions
 slices-0.022
 unison-0.022
 seconds-0.021
 seventeen-0.020
fires-0.020
Tokenummy
Token ID13513
Feature activation-1.11e-02

Pos logit contributions
 slices+0.050
 unison+0.048
 seventeen+0.048
 aroma+0.048
 amaz+0.047
Neg logit contributions
 wear-0.029
 Woo-0.027
 bath-0.025
 Lucky-0.024
 Mitt-0.024
Token food
Token ID2057
Feature activation+9.76e-03

Pos logit contributions
 unison+0.022
 seventeen+0.021
atively+0.021
fires+0.020
anish+0.020
Neg logit contributions
 wear-0.017
 bath-0.016
 day-0.015
 exercise-0.015
 important-0.014
Token for
Token ID329
Feature activation-3.84e-02

Pos logit contributions
 wear+0.011
 bath+0.010
 Woo+0.010
 day+0.009
 Lucky+0.009
Neg logit contributions
 unison-0.021
 seventeen-0.021
 amaz-0.021
 slices-0.021
 seconds-0.020
Token the
Token ID262
Feature activation+1.99e-02

Pos logit contributions
 seventeen+0.085
 amaz+0.081
 unison+0.080
pter+0.079
 slices+0.079
Neg logit contributions
 wear-0.045
 bath-0.041
 Woo-0.041
 day-0.039
 Mitt-0.038
Token b
Token ID275
Feature activation+2.25e-02

Pos logit contributions
 wear+0.025
 Woo+0.023
 bath+0.023
 Mitt+0.021
 Lucky+0.021
Neg logit contributions
 unison-0.040
 slices-0.040
 seventeen-0.039
 amaz-0.039
 aroma-0.039
Tokenunn
Token ID20935
Feature activation+1.04e-01

Pos logit contributions
 wear+0.029
 Woo+0.027
 bath+0.026
 skipping+0.024
 Mitt+0.024
Neg logit contributions
 slices-0.046
 seventeen-0.044
 unison-0.044
 pulp-0.043
 seconds-0.043
Tokenies
Token ID444
Feature activation+3.19e-02

Pos logit contributions
 wear+0.124
 Woo+0.112
 bath+0.110
 day+0.103
 important+0.101
Neg logit contributions
 unison-0.225
 seventeen-0.222
 amaz-0.220
 slices-0.217
 aroma-0.213
Token.
Token ID13
Feature activation+1.69e-02

Pos logit contributions
 wear+0.040
 Woo+0.036
 bath+0.035
 Mitt+0.033
 Lucky+0.033
Neg logit contributions
 unison-0.065
 slices-0.065
 seventeen-0.064
 amaz-0.064
 aroma-0.063
Token It
Token ID632
Feature activation+6.81e-03

Pos logit contributions
 wear+0.020
 Woo+0.019
 bath+0.018
 day+0.017
 Mitt+0.017
Neg logit contributions
 slices-0.035
 unison-0.035
 seventeen-0.035
 amaz-0.035
 aroma-0.034
Token started
Token ID2067
Feature activation+5.14e-02

Pos logit contributions
 wear+0.008
 Woo+0.007
 bath+0.007
 Mitt+0.007
 day+0.007
Neg logit contributions
 unison-0.014
 slices-0.014
 seventeen-0.014
 amaz-0.014
 aroma-0.014
Token with
Token ID351
Feature activation-6.32e-03

Pos logit contributions
 wear+0.063
 Woo+0.058
 bath+0.053
 Lucky+0.051
burn+0.049
Neg logit contributions
 slices-0.108
 seventeen-0.103
 seconds-0.102
 aroma-0.102
 amaz-0.102
Token was
Token ID373
Feature activation+7.63e-03

Pos logit contributions
 wear+0.052
 Woo+0.052
burn+0.050
 bath+0.048
 important+0.046
Neg logit contributions
 amaz-0.052
 slices-0.051
 unison-0.050
 seconds-0.048
 aroma-0.048
Token a
Token ID257
Feature activation+2.22e-02

Pos logit contributions
 wear+0.014
burn+0.013
ongo+0.013
ibi+0.013
 Woo+0.013
Neg logit contributions
 slices-0.011
 unison-0.010
 conf-0.010
 seconds-0.009
 amaz-0.009
Token family
Token ID1641
Feature activation-3.04e-02

Pos logit contributions
 wear+0.032
ained+0.031
burn+0.029
 Woo+0.029
scar+0.027
Neg logit contributions
 unison-0.039
 slices-0.038
 aroma-0.037
 seconds-0.037
 amaz-0.036
Token of
Token ID286
Feature activation+4.13e-02

Pos logit contributions
 slices+0.043
 unison+0.040
pter+0.038
 seconds+0.037
 candles+0.036
Neg logit contributions
 Woo-0.052
 Lucky-0.051
 wear-0.050
scar-0.050
 Nut-0.049
Token b
Token ID275
Feature activation+3.65e-02

Pos logit contributions
 wear+0.067
 Woo+0.062
 bath+0.061
burn+0.059
 important+0.058
Neg logit contributions
 unison-0.068
 slices-0.067
 seconds-0.065
 amaz-0.064
 pulp-0.064
Tokenunn
Token ID20935
Feature activation+1.04e-01

Pos logit contributions
 wear+0.042
 Woo+0.039
 bath+0.038
 Lucky+0.038
 Mitt+0.035
Neg logit contributions
 slices-0.079
 pulp-0.075
pter-0.073
als-0.072
 seventeen-0.072
Tokenies
Token ID444
Feature activation+3.59e-02

Pos logit contributions
 wear+0.157
 Woo+0.146
 bath+0.144
 Lucky+0.134
 Mitt+0.133
Neg logit contributions
 slices-0.182
 unison-0.175
 pulp-0.173
pter-0.173
fires-0.173
Token.
Token ID13
Feature activation+1.69e-02

Pos logit contributions
 wear+0.060
 Woo+0.057
 bath+0.056
ibi+0.055
burn+0.054
Neg logit contributions
 unison-0.054
 slices-0.051
fires-0.049
 seconds-0.049
pter-0.049
Token They
Token ID1119
Feature activation+7.84e-03

Pos logit contributions
 wear+0.029
 Woo+0.027
 bath+0.027
 important+0.026
burn+0.026
Neg logit contributions
 unison-0.026
 slices-0.026
 seventeen-0.026
 amaz-0.025
 aroma-0.025
Token loved
Token ID6151
Feature activation+1.38e-02

Pos logit contributions
 wear+0.012
 Woo+0.012
 bath+0.012
burn+0.011
 Mitt+0.011
Neg logit contributions
 unison-0.013
 slices-0.013
 pulp-0.012
 seventeen-0.012
fires-0.012
Token to
Token ID284
Feature activation+2.52e-02

Pos logit contributions
 wear+0.015
 Woo+0.014
 bath+0.013
 Lucky+0.012
 Mitt+0.012
Neg logit contributions
 slices-0.030
 unison-0.030
 amaz-0.029
 seventeen-0.029
 seconds-0.029
Token.
Token ID13
Feature activation+2.55e-03

Pos logit contributions
 wear+0.006
 Woo+0.006
 bath+0.006
 day+0.006
 Mitt+0.005
Neg logit contributions
 seventeen-0.013
 unison-0.013
 slices-0.013
 pulp-0.013
 amaz-0.013
Token<|endoftext|>
Token ID50256
Feature activation-4.70e-02

Pos logit contributions
 wear+0.004
 bath+0.004
 Woo+0.004
burn+0.004
 important+0.004
Neg logit contributions
 unison-0.004
 amaz-0.004
 seventeen-0.004
 slices-0.004
 seconds-0.004
TokenLisa
Token ID44203
Feature activation+1.95e-03

Pos logit contributions
 slices+0.086
 unison+0.085
 amaz+0.082
 seventeen+0.082
fires+0.082
Neg logit contributions
 wear-0.067
 Woo-0.062
 bath-0.059
 important-0.059
burn-0.059
Token loved
Token ID6151
Feature activation+2.11e-02

Pos logit contributions
 Woo+0.003
 wear+0.003
 bath+0.003
burn+0.003
 Mitt+0.003
Neg logit contributions
 slices-0.003
 unison-0.003
 seconds-0.003
 amaz-0.003
 seventeen-0.003
Token her
Token ID607
Feature activation+6.59e-02

Pos logit contributions
 wear+0.028
scar+0.025
 Woo+0.025
 Lucky+0.025
opsy+0.025
Neg logit contributions
 slices-0.040
 conf-0.038
 pulp-0.038
 amaz-0.036
 seconds-0.036
Token velvet
Token ID47750
Feature activation+1.04e-01

Pos logit contributions
 Woo+0.091
scar+0.090
ained+0.090
tto+0.087
ongo+0.086
Neg logit contributions
 unison-0.120
 amaz-0.119
 slices-0.118
 conf-0.114
 ah-0.108
Token bear
Token ID6842
Feature activation+6.20e-02

Pos logit contributions
 wear+0.154
 Woo+0.145
 bath+0.136
 important+0.133
 Mitt+0.131
Neg logit contributions
 unison-0.184
 slices-0.183
 aroma-0.175
 amaz-0.175
 seventeen-0.174
Token very
Token ID845
Feature activation+9.35e-03

Pos logit contributions
 wear+0.098
 Woo+0.097
 stub+0.093
scar+0.091
ibi+0.090
Neg logit contributions
 slices-0.100
 unison-0.097
pter-0.087
als-0.086
 aroma-0.084
Token much
Token ID881
Feature activation+2.80e-02

Pos logit contributions
 wear+0.013
 Woo+0.013
 bath+0.012
burn+0.012
 Lucky+0.012
Neg logit contributions
 unison-0.017
 slices-0.017
 seconds-0.016
 seventeen-0.016
 amaz-0.016
Token.
Token ID13
Feature activation+2.76e-02

Pos logit contributions
 wear+0.033
 Woo+0.030
 bath+0.029
 day+0.028
 important+0.028
Neg logit contributions
 seventeen-0.060
 unison-0.059
 slices-0.059
 amaz-0.059
 pulp-0.058
Token She
Token ID1375
Feature activation+1.24e-02

Pos logit contributions
 wear+0.029
 Woo+0.024
 day+0.024
 bath+0.023
 Mitt+0.023
Neg logit contributions
 slices-0.063
fires-0.062
 pulp-0.062
 seventeen-0.062
 unison-0.062
Token choose
Token ID3853
Feature activation+1.80e-03

Pos logit contributions
 Woo+0.034
 wear+0.033
 bath+0.032
burn+0.032
 important+0.030
Neg logit contributions
 unison-0.060
 seventeen-0.057
 amaz-0.057
 aroma-0.056
 slices-0.056
Token one
Token ID530
Feature activation+3.02e-02

Pos logit contributions
 wear+0.003
 Woo+0.002
 bath+0.002
 Mitt+0.002
 Lucky+0.002
Neg logit contributions
 unison-0.003
 slices-0.003
 seventeen-0.003
 amaz-0.003
 seconds-0.003
Token of
Token ID286
Feature activation+3.75e-02

Pos logit contributions
 wear+0.047
 Woo+0.046
 bath+0.044
 Mitt+0.042
 Lucky+0.042
Neg logit contributions
 slices-0.052
 unison-0.050
 seventeen-0.050
 seconds-0.049
 amaz-0.049
Token these
Token ID777
Feature activation-2.18e-03

Pos logit contributions
 wear+0.052
 Woo+0.049
 bath+0.048
 Mitt+0.045
 Lucky+0.044
Neg logit contributions
 unison-0.071
 slices-0.070
 seventeen-0.069
 amaz-0.069
 seconds-0.067
Token b
Token ID275
Feature activation+2.08e-02

Pos logit contributions
 slices+0.004
 unison+0.004
 seventeen+0.004
 amaz+0.004
 aroma+0.004
Neg logit contributions
 wear-0.003
 Woo-0.003
 bath-0.003
 Mitt-0.003
burn-0.003
Tokenunn
Token ID20935
Feature activation+1.03e-01

Pos logit contributions
 wear+0.019
 Woo+0.017
 bath+0.017
 Mitt+0.015
 Lucky+0.015
Neg logit contributions
 slices-0.050
 seventeen-0.049
 unison-0.048
 pulp-0.048
 seconds-0.048
Tokenies
Token ID444
Feature activation+2.98e-02

Pos logit contributions
 wear+0.132
 Woo+0.120
 bath+0.118
 Mitt+0.110
 day+0.109
Neg logit contributions
 unison-0.209
 slices-0.206
 seventeen-0.205
 amaz-0.204
 aroma-0.200
Token to
Token ID284
Feature activation-2.98e-03

Pos logit contributions
 wear+0.043
 Woo+0.037
 bath+0.037
 day+0.036
 important+0.036
Neg logit contributions
 unison-0.059
 amaz-0.057
 seventeen-0.056
 slices-0.055
 aroma-0.055
Token come
Token ID1282
Feature activation-1.85e-02

Pos logit contributions
 unison+0.006
 slices+0.006
 seventeen+0.006
 amaz+0.006
 aroma+0.006
Neg logit contributions
 wear-0.003
 Woo-0.003
 bath-0.003
 Mitt-0.003
burn-0.003
Token with
Token ID351
Feature activation-2.72e-03

Pos logit contributions
 slices+0.036
 unison+0.035
 seventeen+0.035
 amaz+0.034
fires+0.034
Neg logit contributions
 wear-0.024
 Woo-0.022
 bath-0.022
 Mitt-0.021
 Lucky-0.020
Token us
Token ID514
Feature activation-2.10e-02

Pos logit contributions
 unison+0.005
 seventeen+0.005
 amaz+0.005
 slices+0.005
fires+0.005
Neg logit contributions
 wear-0.004
 Woo-0.004
 bath-0.004
 day-0.004
 important-0.004
Token you
Token ID345
Feature activation-3.65e-02

Pos logit contributions
 wear+0.024
 Woo+0.023
 bath+0.022
 Mitt+0.021
 important+0.021
Neg logit contributions
 seventeen-0.043
fires-0.042
atively-0.042
 aroma-0.041
 slices-0.041
Token.
Token ID13
Feature activation+2.04e-02

Pos logit contributions
 unison+0.067
 slices+0.066
 seventeen+0.065
 amaz+0.065
 aroma+0.064
Neg logit contributions
 wear-0.053
 Woo-0.050
 bath-0.049
 Mitt-0.046
 Lucky-0.045
Token You
Token ID921
Feature activation-5.44e-02

Pos logit contributions
 wear+0.041
 bath+0.038
 Woo+0.038
 day+0.036
burn+0.036
Neg logit contributions
 unison-0.026
 seventeen-0.026
 slices-0.026
 amaz-0.025
 seconds-0.025
Token love
Token ID1842
Feature activation-2.26e-02

Pos logit contributions
 slices+0.092
 seventeen+0.092
 unison+0.092
 amaz+0.090
 aroma+0.089
Neg logit contributions
 wear-0.093
 Woo-0.082
 bath-0.082
 always-0.078
 Lucky-0.077
Token b
Token ID275
Feature activation+2.33e-02

Pos logit contributions
 slices+0.042
 unison+0.041
 seconds+0.040
 seventeen+0.040
 amaz+0.040
Neg logit contributions
 wear-0.032
 Woo-0.030
 bath-0.029
burn-0.028
 Lucky-0.027
Tokenunn
Token ID20935
Feature activation+1.03e-01

Pos logit contributions
 wear+0.021
 Woo+0.019
 bath+0.019
 important+0.016
 Lucky+0.016
Neg logit contributions
 slices-0.056
 unison-0.055
 seventeen-0.054
 amaz-0.054
 seconds-0.053
Tokenies
Token ID444
Feature activation+5.34e-02

Pos logit contributions
 wear+0.120
 Woo+0.110
 bath+0.104
 Mitt+0.100
 Lucky+0.098
Neg logit contributions
 unison-0.225
 seventeen-0.223
 amaz-0.222
 slices-0.219
 seconds-0.213
Token,
Token ID11
Feature activation+8.94e-03

Pos logit contributions
 wear+0.071
 Woo+0.065
 bath+0.062
 day+0.060
 important+0.060
Neg logit contributions
 amaz-0.108
 seventeen-0.108
 unison-0.108
 pulp-0.105
 slices-0.105
Token right
Token ID826
Feature activation-4.93e-02

Pos logit contributions
 wear+0.012
 Woo+0.011
 bath+0.011
burn+0.010
 Mitt+0.010
Neg logit contributions
 slices-0.017
 unison-0.017
 amaz-0.016
 seventeen-0.016
 seconds-0.016
Token?"
Token ID1701
Feature activation-2.60e-03

Pos logit contributions
 seventeen+0.113
 slices+0.112
 unison+0.111
 amaz+0.108
 pulp+0.107
Neg logit contributions
 wear-0.054
 Woo-0.047
 day-0.047
 important-0.045
 bath-0.044
Token Lily
Token ID20037
Feature activation+4.60e-03

Pos logit contributions
 slices+0.005
 unison+0.005
 amaz+0.005
 pulp+0.005
 seconds+0.005
Neg logit contributions
 wear-0.003
burn-0.003
 important-0.003
 bath-0.003
 Woo-0.003
Token there
Token ID612
Feature activation+3.48e-02

Pos logit contributions
 wear+0.029
 Woo+0.028
 bath+0.027
burn+0.025
 Mitt+0.025
Neg logit contributions
 unison-0.035
 slices-0.035
 seventeen-0.034
 amaz-0.034
 seconds-0.033
Token were
Token ID547
Feature activation-2.02e-02

Pos logit contributions
 wear+0.052
 Woo+0.050
 bath+0.047
burn+0.047
 Mitt+0.045
Neg logit contributions
 unison-0.061
 amaz-0.061
 slices-0.060
 seventeen-0.058
 seconds-0.058
Token two
Token ID734
Feature activation+3.14e-02

Pos logit contributions
 slices+0.035
 conf+0.032
 unison+0.032
 seventeen+0.032
 pulp+0.032
Neg logit contributions
 wear-0.034
 Woo-0.029
 jog-0.028
burn-0.028
ibi-0.028
Token little
Token ID1310
Feature activation+3.37e-02

Pos logit contributions
 wear+0.035
 Woo+0.033
 bath+0.030
burn+0.028
 Lucky+0.028
Neg logit contributions
 slices-0.069
 unison-0.068
 seventeen-0.067
 amaz-0.066
 seconds-0.066
Token b
Token ID275
Feature activation+3.66e-02

Pos logit contributions
 wear+0.053
 Woo+0.050
 bath+0.049
 Mitt+0.047
 Lucky+0.046
Neg logit contributions
 unison-0.058
 seventeen-0.057
 slices-0.057
 amaz-0.056
fires-0.055
Tokenunn
Token ID20935
Feature activation+1.03e-01

Pos logit contributions
 wear+0.043
 Woo+0.041
 bath+0.040
 Lucky+0.037
 Mitt+0.036
Neg logit contributions
 slices-0.079
 pulp-0.075
 seventeen-0.075
pter-0.074
als-0.073
Tokenies
Token ID444
Feature activation+3.25e-02

Pos logit contributions
 wear+0.163
 Woo+0.155
 bath+0.153
 jog+0.142
 Lucky+0.140
Neg logit contributions
 slices-0.172
pter-0.164
 pulp-0.163
fires-0.161
 unison-0.161
Token called
Token ID1444
Feature activation+4.09e-02

Pos logit contributions
 wear+0.058
 Woo+0.057
 bath+0.055
ibi+0.054
burn+0.053
Neg logit contributions
 unison-0.046
 slices-0.045
pter-0.042
 seconds-0.041
fires-0.039
Token Bob
Token ID5811
Feature activation+2.52e-02

Pos logit contributions
 wear+0.050
 important+0.044
 stub+0.042
burn+0.041
 bath+0.041
Neg logit contributions
 unison-0.084
 slices-0.082
 seventeen-0.079
 ah-0.078
 amaz-0.078
Token and
Token ID290
Feature activation+3.78e-02

Pos logit contributions
 wear+0.037
 Woo+0.035
 bath+0.035
 skipping+0.032
 stub+0.032
Neg logit contributions
 slices-0.046
 unison-0.045
pter-0.043
 seventeen-0.043
 seconds-0.042
Token Su
Token ID1778
Feature activation+3.00e-02

Pos logit contributions
 wear+0.046
 bath+0.043
 Woo+0.040
 important+0.040
burn+0.039
Neg logit contributions
 unison-0.075
 slices-0.074
 seconds-0.073
 seventeen-0.072
 amaz-0.072
Tokenmy
Token ID1820
Feature activation+1.51e-02

Pos logit contributions
 slices+0.034
 unison+0.033
 seventeen+0.033
 amaz+0.033
 aroma+0.033
Neg logit contributions
 wear-0.012
 Woo-0.011
 bath-0.011
 important-0.010
 Lucky-0.010
Token,
Token ID11
Feature activation-8.23e-03

Pos logit contributions
 wear+0.018
 Woo+0.017
 bath+0.017
 important+0.015
 Lucky+0.015
Neg logit contributions
 slices-0.030
 unison-0.030
 seventeen-0.030
 amaz-0.030
 aroma-0.030
Token what
Token ID644
Feature activation-2.44e-02

Pos logit contributions
 unison+0.014
 slices+0.014
 seventeen+0.014
fires+0.014
 aroma+0.014
Neg logit contributions
 wear-0.013
 Woo-0.012
 bath-0.012
 Mitt-0.012
 day-0.011
Token do
Token ID466
Feature activation+4.19e-03

Pos logit contributions
 slices+0.036
 amaz+0.036
 unison+0.036
 seventeen+0.034
 seconds+0.034
Neg logit contributions
 Woo-0.042
 wear-0.041
 bath-0.039
 Mitt-0.038
burn-0.038
Token b
Token ID275
Feature activation+2.44e-02

Pos logit contributions
 wear+0.007
 Woo+0.007
 bath+0.007
burn+0.006
 Mitt+0.006
Neg logit contributions
 slices-0.006
 unison-0.006
 seventeen-0.006
 seconds-0.006
 amaz-0.006
Tokenunn
Token ID20935
Feature activation+1.03e-01

Pos logit contributions
 bath+0.029
 stub+0.029
 wear+0.029
 important+0.028
burn+0.028
Neg logit contributions
als-0.046
 goodness-0.044
 slices-0.044
 aroma-0.043
teen-0.042
Tokenies
Token ID444
Feature activation+4.27e-02

Pos logit contributions
 wear+0.145
 Woo+0.141
 bath+0.137
 Mitt+0.129
 important+0.128
Neg logit contributions
 slices-0.179
 aroma-0.175
 pulp-0.172
 ah-0.172
 unison-0.172
Token do
Token ID466
Feature activation+1.14e-02

Pos logit contributions
 Woo+0.053
 wear+0.052
 bath+0.049
 Mitt+0.048
burn+0.047
Neg logit contributions
 slices-0.081
 unison-0.081
 aroma-0.080
fires-0.080
 seventeen-0.080
Token?"
Token ID1701
Feature activation-8.13e-03

Pos logit contributions
 wear+0.012
 Woo+0.012
 bath+0.011
 Mitt+0.010
burn+0.010
Neg logit contributions
 slices-0.025
 unison-0.025
 seventeen-0.024
 amaz-0.024
fires-0.024
Token
Token ID198
Feature activation-4.47e-04

Pos logit contributions
 unison+0.016
 slices+0.015
 amaz+0.015
 seventeen+0.015
 seconds+0.015
Neg logit contributions
 wear-0.011
 Woo-0.010
 important-0.010
 bath-0.009
burn-0.009
Token
Token ID198
Feature activation-1.04e-02

Pos logit contributions
 unison+0.001
 slices+0.001
 seventeen+0.001
 seconds+0.001
 amaz+0.001
Neg logit contributions
 wear-0.001
working-0.001
 Woo-0.001
burn-0.001
 exercise-0.001
Tokenunn
Token ID20935
Feature activation+1.08e-01

Pos logit contributions
 wear+0.044
 Woo+0.041
 bath+0.039
 Lucky+0.039
 Mitt+0.037
Neg logit contributions
 slices-0.083
 pulp-0.079
pter-0.077
als-0.077
 seventeen-0.076
Tokenies
Token ID444
Feature activation+3.60e-02

Pos logit contributions
 wear+0.166
 Woo+0.155
 bath+0.153
 Lucky+0.144
 Mitt+0.142
Neg logit contributions
 slices-0.184
pter-0.176
 pulp-0.175
 unison-0.175
fires-0.175
Token.
Token ID13
Feature activation+1.39e-02

Pos logit contributions
 wear+0.061
 Woo+0.058
ibi+0.057
 bath+0.057
scar+0.056
Neg logit contributions
 unison-0.052
 slices-0.049
fires-0.048
 seconds-0.047
pter-0.047
Token The
Token ID383
Feature activation+2.25e-02

Pos logit contributions
 wear+0.026
 Woo+0.024
 important+0.024
burn+0.024
 bath+0.024
Neg logit contributions
 unison-0.020
 slices-0.019
 seventeen-0.019
 amaz-0.018
 aroma-0.018
Token b
Token ID275
Feature activation+3.03e-02

Pos logit contributions
 wear+0.032
scar+0.031
ogging+0.030
 Razor+0.029
ongo+0.029
Neg logit contributions
 aroma-0.038
 slices-0.038
 unison-0.037
 pulp-0.037
 amaz-0.036
Tokenunn
Token ID20935
Feature activation+1.02e-01

Pos logit contributions
 wear+0.037
 bath+0.035
 Woo+0.034
 jog+0.034
 Lucky+0.034
Neg logit contributions
als-0.060
 slices-0.059
 pulp-0.058
edly-0.057
pter-0.056
Tokenies
Token ID444
Feature activation+2.95e-02

Pos logit contributions
 wear+0.167
 Woo+0.159
 bath+0.157
 jog+0.150
 Lucky+0.149
Neg logit contributions
 slices-0.157
 pulp-0.156
pter-0.152
fires-0.152
als-0.150
Token lived
Token ID5615
Feature activation+1.07e-02

Pos logit contributions
 Woo+0.046
burn+0.044
 Mitt+0.043
 wear+0.043
 bath+0.043
Neg logit contributions
 slices-0.046
 unison-0.046
fires-0.045
 pulp-0.045
 aroma-0.044
Token in
Token ID287
Feature activation-1.13e-02

Pos logit contributions
 wear+0.017
 bath+0.016
 Woo+0.016
ibi+0.015
burn+0.015
Neg logit contributions
 slices-0.018
fires-0.017
 seconds-0.016
 unison-0.016
 pulp-0.016
Token a
Token ID257
Feature activation-1.04e-02

Pos logit contributions
 unison+0.021
 slices+0.021
 amaz+0.021
 seconds+0.020
 seventeen+0.020
Neg logit contributions
 wear-0.016
 Woo-0.015
 bath-0.014
burn-0.014
 skipping-0.013
Token cozy
Token ID37438
Feature activation+1.34e-02

Pos logit contributions
 unison+0.019
 slices+0.019
 pulp+0.019
 amaz+0.018
fires+0.018
Neg logit contributions
 wear-0.014
ibi-0.013
burn-0.012
scar-0.012
ido-0.012
Token Do
Token ID2141
Feature activation-5.65e-03

Pos logit contributions
 wear+0.015
 Woo+0.015
 bath+0.014
 Mitt+0.014
 Lucky+0.013
Neg logit contributions
 slices-0.013
 unison-0.012
 aroma-0.012
 seventeen-0.012
 amaz-0.012
Token you
Token ID345
Feature activation-1.42e-02

Pos logit contributions
 amaz+0.011
 unison+0.011
 slices+0.011
 seventeen+0.011
 aroma+0.011
Neg logit contributions
 wear-0.008
 Woo-0.008
 bath-0.007
 day-0.007
 Mitt-0.007
Token like
Token ID588
Feature activation+9.45e-03

Pos logit contributions
 unison+0.023
 slices+0.023
 seventeen+0.023
 amaz+0.022
 seconds+0.022
Neg logit contributions
 Woo-0.022
 wear-0.021
 bath-0.021
burn-0.021
 Mitt-0.021
Token the
Token ID262
Feature activation+2.29e-02

Pos logit contributions
 wear+0.015
ibi+0.014
 Woo+0.014
 stub+0.014
scar+0.014
Neg logit contributions
 slices-0.016
 seventeen-0.014
 seconds-0.014
 unison-0.014
 conf-0.014
Token b
Token ID275
Feature activation+2.27e-02

Pos logit contributions
 wear+0.035
 Woo+0.033
 bath+0.032
 Mitt+0.030
 Lucky+0.030
Neg logit contributions
 slices-0.040
 unison-0.040
 seventeen-0.039
 amaz-0.039
 aroma-0.039
Tokenunn
Token ID20935
Feature activation+1.02e-01

Pos logit contributions
 wear+0.022
 bath+0.021
 Woo+0.020
 skipping+0.019
 Lucky+0.019
Neg logit contributions
 slices-0.052
 seventeen-0.051
als-0.050
pter-0.050
 pulp-0.049
Tokenies
Token ID444
Feature activation+3.97e-02

Pos logit contributions
 wear+0.147
 Woo+0.139
 bath+0.136
 Mitt+0.128
 Lucky+0.127
Neg logit contributions
 slices-0.185
 pulp-0.178
 unison-0.177
 aroma-0.177
 seventeen-0.177
Token?"
Token ID1701
Feature activation+9.98e-04

Pos logit contributions
 Woo+0.042
 wear+0.041
 Mitt+0.039
 bath+0.038
 Lucky+0.037
Neg logit contributions
 slices-0.084
 unison-0.081
 aroma-0.080
fires-0.079
 seventeen-0.079
Token the
Token ID262
Feature activation-1.11e-02

Pos logit contributions
burn+0.001
 wear+0.001
 bath+0.001
 important+0.001
 Woo+0.001
Neg logit contributions
 slices-0.002
 seconds-0.002
 amaz-0.002
 unison-0.002
 pulp-0.002
Token lady
Token ID10846
Feature activation-4.66e-02

Pos logit contributions
 slices+0.020
 unison+0.020
 aroma+0.020
 pulp+0.020
 seconds+0.020
Neg logit contributions
 wear-0.016
 Woo-0.015
 bath-0.014
 important-0.014
burn-0.014
Token asks
Token ID7893
Feature activation-4.19e-03

Pos logit contributions
 slices+0.075
 unison+0.074
 amaz+0.074
 seventeen+0.074
 seconds+0.072
Neg logit contributions
 wear-0.076
 Woo-0.075
 bath-0.072
 Mitt-0.069
 important-0.068
TokenFred
Token ID30847
Feature activation+1.06e-02

Pos logit contributions
 unison+0.022
 slices+0.022
 amaz+0.022
 seventeen+0.021
 aroma+0.021
Neg logit contributions
 wear-0.018
 Woo-0.017
 bath-0.016
 Mitt-0.016
 Lucky-0.015
Token played
Token ID2826
Feature activation+4.45e-02

Pos logit contributions
 wear+0.015
 Woo+0.014
 bath+0.013
burn+0.012
 Mitt+0.012
Neg logit contributions
 unison-0.020
 slices-0.020
 seventeen-0.020
 amaz-0.020
 seconds-0.019
Token with
Token ID351
Feature activation-1.25e-02

Pos logit contributions
 wear+0.050
 Woo+0.046
 bath+0.044
 Lucky+0.042
 skipping+0.041
Neg logit contributions
 seventeen-0.098
 unison-0.098
 slices-0.096
 amaz-0.096
 pulp-0.096
Token the
Token ID262
Feature activation+5.02e-03

Pos logit contributions
 slices+0.024
 unison+0.024
 amaz+0.023
 seconds+0.023
 seventeen+0.023
Neg logit contributions
 wear-0.017
 Woo-0.015
 bath-0.015
burn-0.014
 important-0.014
Token b
Token ID275
Feature activation+1.87e-02

Pos logit contributions
 wear+0.006
 Woo+0.005
 bath+0.005
 Mitt+0.005
 Lucky+0.005
Neg logit contributions
 slices-0.010
 aroma-0.010
 amaz-0.010
 pulp-0.010
 unison-0.010
Tokenunn
Token ID20935
Feature activation+1.02e-01

Pos logit contributions
 wear+0.020
 Woo+0.018
 bath+0.017
 Lucky+0.016
 skipping+0.016
Neg logit contributions
 slices-0.042
als-0.041
 seventeen-0.041
 pulp-0.040
 aroma-0.040
Tokenies
Token ID444
Feature activation+1.81e-02

Pos logit contributions
 wear+0.161
 Woo+0.154
 bath+0.150
 Mitt+0.140
burn+0.139
Neg logit contributions
 slices-0.170
 pulp-0.163
pter-0.159
 aroma-0.158
fires-0.158
Token all
Token ID477
Feature activation+2.61e-03

Pos logit contributions
 wear+0.023
 Woo+0.022
 bath+0.021
 Mitt+0.020
burn+0.019
Neg logit contributions
 slices-0.036
 unison-0.036
 amaz-0.035
 seventeen-0.035
 seconds-0.034
Token day
Token ID1110
Feature activation-1.11e-02

Pos logit contributions
 wear+0.002
 Woo+0.001
 bath+0.001
 Mitt+0.001
burn+0.001
Neg logit contributions
 slices-0.007
 unison-0.007
 seventeen-0.007
 amaz-0.007
pter-0.007
Token,
Token ID11
Feature activation-5.47e-03

Pos logit contributions
 slices+0.022
 unison+0.022
 seventeen+0.021
 amaz+0.021
 seconds+0.021
Neg logit contributions
 wear-0.014
 Woo-0.014
 bath-0.013
burn-0.012
 Mitt-0.012
Token hopping
Token ID47153
Feature activation+2.00e-02

Pos logit contributions
 slices+0.011
 unison+0.011
 seventeen+0.011
 amaz+0.011
 seconds+0.011
Neg logit contributions
 wear-0.007
 Woo-0.006
 bath-0.006
burn-0.006
 important-0.006
Token little
Token ID1310
Feature activation+2.24e-02

Pos logit contributions
ained+0.030
 wear+0.030
 Woo+0.028
burn+0.028
ibi+0.026
Neg logit contributions
 unison-0.035
 aroma-0.033
 slices-0.033
 pulp-0.033
 seconds-0.032
Token girl
Token ID2576
Feature activation-7.29e-03

Pos logit contributions
 wear+0.041
 Woo+0.037
 important+0.035
 bath+0.035
ained+0.035
Neg logit contributions
 slices-0.032
 aroma-0.031
 unison-0.031
 pulp-0.031
 conf-0.029
Token who
Token ID508
Feature activation+3.93e-02

Pos logit contributions
pter+0.014
 seconds+0.013
 unison+0.013
 slices+0.013
als+0.012
Neg logit contributions
 Woo-0.009
ibi-0.008
ained-0.008
ongo-0.008
burn-0.008
Token loved
Token ID6151
Feature activation+2.00e-02

Pos logit contributions
 Woo+0.057
burn+0.055
 wear+0.054
 bath+0.053
 skipping+0.051
Neg logit contributions
 unison-0.065
fires-0.065
 aroma-0.064
pter-0.064
 amaz-0.063
Token her
Token ID607
Feature activation+6.35e-02

Pos logit contributions
 wear+0.025
 Woo+0.023
 Lucky+0.021
scar+0.021
 bath+0.021
Neg logit contributions
 slices-0.041
 pulp-0.039
 conf-0.038
 seconds-0.038
 amaz-0.038
Token rubber
Token ID14239
Feature activation+1.02e-01

Pos logit contributions
scar+0.092
 Woo+0.091
tto+0.086
ained+0.084
umper+0.083
Neg logit contributions
 slices-0.113
 amaz-0.111
 unison-0.111
 aroma-0.107
 conf-0.107
Token.
Token ID13
Feature activation+2.26e-02

Pos logit contributions
 wear+0.133
 Woo+0.123
 bath+0.118
 Mitt+0.111
 important+0.111
Neg logit contributions
 slices-0.200
 unison-0.199
 seventeen-0.194
 amaz-0.193
 aroma-0.191
Token Every
Token ID3887
Feature activation+5.48e-02

Pos logit contributions
 wear+0.035
 Woo+0.034
burn+0.033
 bath+0.033
 important+0.032
Neg logit contributions
 amaz-0.036
 unison-0.036
 slices-0.036
 seventeen-0.035
 aroma-0.034
Token day
Token ID1110
Feature activation-1.12e-02

Pos logit contributions
 Woo+0.050
 wear+0.050
ongo+0.047
 Nut+0.046
 Mitt+0.046
Neg logit contributions
 seconds-0.117
 moments-0.116
 unison-0.116
 aroma-0.112
 slices-0.110
Token she
Token ID673
Feature activation+1.28e-02

Pos logit contributions
 slices+0.019
als+0.019
 seconds+0.019
 aroma+0.019
 amaz+0.019
Neg logit contributions
 Woo-0.014
 wear-0.014
burn-0.014
scar-0.014
iny-0.014
Token found
Token ID1043
Feature activation+9.91e-04

Pos logit contributions
 Woo+0.019
ibi+0.019
 skipping+0.018
burn+0.018
 Mitt+0.018
Neg logit contributions
 seconds-0.020
pter-0.019
 slices-0.019
 pulp-0.019
ts-0.019
Token of
Token ID286
Feature activation+4.02e-02

Pos logit contributions
 slices+0.015
 unison+0.015
fires+0.014
 amaz+0.014
 aroma+0.014
Neg logit contributions
 wear-0.009
 Woo-0.009
 bath-0.008
 Lucky-0.008
burn-0.008
Token a
Token ID257
Feature activation+4.86e-03

Pos logit contributions
 wear+0.055
 Woo+0.051
 bath+0.049
burn+0.048
 Lucky+0.047
Neg logit contributions
 slices-0.077
 unison-0.075
 amaz-0.075
 seconds-0.074
 pulp-0.073
Token family
Token ID1641
Feature activation-3.30e-02

Pos logit contributions
 wear+0.006
 Woo+0.005
burn+0.005
 bath+0.005
 Lucky+0.005
Neg logit contributions
 unison-0.010
 slices-0.010
 amaz-0.010
 aroma-0.010
 seconds-0.010
Token of
Token ID286
Feature activation+3.38e-02

Pos logit contributions
 slices+0.050
 unison+0.049
pter+0.048
fires+0.047
 amaz+0.046
Neg logit contributions
 Woo-0.054
burn-0.051
 Mitt-0.051
 wear-0.051
 Lucky-0.050
Token b
Token ID275
Feature activation+2.73e-02

Pos logit contributions
 wear+0.054
 Woo+0.051
 bath+0.049
burn+0.048
 Mitt+0.047
Neg logit contributions
 slices-0.057
 unison-0.056
 amaz-0.055
 seconds-0.055
 pulp-0.054
Tokenunn
Token ID20935
Feature activation+1.02e-01

Pos logit contributions
 wear+0.029
 Woo+0.027
 bath+0.026
 Lucky+0.025
 Mitt+0.024
Neg logit contributions
 slices-0.061
 pulp-0.058
als-0.057
pter-0.056
 aroma-0.056
Tokenies
Token ID444
Feature activation+2.91e-02

Pos logit contributions
 wear+0.153
 Woo+0.144
 bath+0.141
 Lucky+0.131
 Mitt+0.131
Neg logit contributions
 slices-0.179
 pulp-0.171
 unison-0.171
fires-0.170
pter-0.170
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
 wear+0.045
 Woo+0.043
 bath+0.042
burn+0.042
 Mitt+0.041
Neg logit contributions
 unison-0.047
 slices-0.047
fires-0.045
 seconds-0.044
pter-0.044
Token One
Token ID1881
Feature activation+2.61e-02

Pos logit contributions
 wear+0.016
 Woo+0.015
 bath+0.015
 Mitt+0.014
 Lucky+0.014
Neg logit contributions
 slices-0.021
 seventeen-0.021
 unison-0.021
 amaz-0.021
 aroma-0.020
Token day
Token ID1110
Feature activation-2.45e-02

Pos logit contributions
 Woo+0.033
umper+0.028
ongo+0.027
 tying+0.027
 Barkley+0.027
Neg logit contributions
 aroma-0.049
 slices-0.047
 moments-0.046
 seconds-0.043
 amaz-0.043
Token one
Token ID530
Feature activation+2.29e-02

Pos logit contributions
 unison+0.055
 slices+0.055
 seventeen+0.054
 amaz+0.054
 aroma+0.053
Neg logit contributions
 wear-0.026
 Woo-0.024
 bath-0.023
 Mitt-0.021
 day-0.021
Tokenmy
Token ID1820
Feature activation+9.52e-03

Pos logit contributions
 unison+0.062
 slices+0.061
 seventeen+0.061
 amaz+0.060
fires+0.060
Neg logit contributions
 wear-0.008
 Woo-0.005
 bath-0.005
 Mitt-0.004
 day-0.004
Token,
Token ID11
Feature activation-1.07e-02

Pos logit contributions
 wear+0.013
 Woo+0.012
 bath+0.012
 Mitt+0.011
 Lucky+0.011
Neg logit contributions
 unison-0.018
 slices-0.018
 seventeen-0.018
 amaz-0.018
fires-0.017
Token do
Token ID466
Feature activation-6.46e-03

Pos logit contributions
 unison+0.021
 seventeen+0.021
 slices+0.021
fires+0.020
edly+0.020
Neg logit contributions
 wear-0.016
 bath-0.014
 Woo-0.014
 day-0.013
 always-0.013
Token these
Token ID777
Feature activation+1.68e-02

Pos logit contributions
 unison+0.013
 seventeen+0.013
 amaz+0.013
 slices+0.013
 pulp+0.012
Neg logit contributions
 wear-0.009
 Woo-0.008
 important-0.008
 bath-0.008
 Mitt-0.008
Token b
Token ID275
Feature activation+2.44e-02

Pos logit contributions
 wear+0.022
 Woo+0.021
 bath+0.020
 Mitt+0.019
 Lucky+0.019
Neg logit contributions
 slices-0.033
 unison-0.033
 seventeen-0.032
 amaz-0.032
 aroma-0.032
Tokenunn
Token ID20935
Feature activation+1.02e-01

Pos logit contributions
 wear+0.024
 Woo+0.022
 bath+0.021
 Lucky+0.020
 Mitt+0.019
Neg logit contributions
 slices-0.056
 seventeen-0.055
 aroma-0.054
 seconds-0.054
 pulp-0.053
Tokenies
Token ID444
Feature activation+3.95e-02

Pos logit contributions
 wear+0.132
 Woo+0.122
 bath+0.119
 Mitt+0.111
 Lucky+0.110
Neg logit contributions
 unison-0.202
 slices-0.201
 seventeen-0.199
 amaz-0.197
 aroma-0.194
Token live
Token ID2107
Feature activation+4.27e-02

Pos logit contributions
 wear+0.048
 bath+0.041
 Woo+0.040
 day+0.038
 important+0.037
Neg logit contributions
 unison-0.086
 seventeen-0.085
 slices-0.084
 amaz-0.084
 seconds-0.082
Token here
Token ID994
Feature activation+3.14e-03

Pos logit contributions
 wear+0.050
 Woo+0.045
 bath+0.045
 day+0.042
 important+0.041
Neg logit contributions
 unison-0.091
 seventeen-0.091
 slices-0.090
 amaz-0.089
 aroma-0.087
Token?"
Token ID1701
Feature activation-1.25e-02

Pos logit contributions
 wear+0.004
 Woo+0.004
 bath+0.004
 Mitt+0.003
 day+0.003
Neg logit contributions
 unison-0.006
 slices-0.006
 seventeen-0.006
 amaz-0.006
 aroma-0.006
Token
Token ID198
Feature activation-4.67e-03

Pos logit contributions
 slices+0.025
 unison+0.024
 amaz+0.024
 seconds+0.024
 seventeen+0.024
Neg logit contributions
 wear-0.016
 Woo-0.015
 bath-0.015
burn-0.014
 important-0.014
Token was
Token ID373
Feature activation+1.94e-02

Pos logit contributions
 unison+0.079
 slices+0.079
 seventeen+0.078
 amaz+0.077
 aroma+0.076
Neg logit contributions
 wear-0.055
 Woo-0.051
 bath-0.050
 Mitt-0.047
 day-0.047
Token ready
Token ID3492
Feature activation-1.47e-02

Pos logit contributions
 Woo+0.022
 wear+0.022
 bath+0.020
 Lucky+0.020
 Mitt+0.019
Neg logit contributions
 seventeen-0.040
 slices-0.040
 unison-0.039
 aroma-0.039
 seconds-0.039
Token,
Token ID11
Feature activation+5.96e-03

Pos logit contributions
 unison+0.035
 seventeen+0.035
 slices+0.034
 amaz+0.034
 pulp+0.034
Neg logit contributions
 wear-0.014
 Woo-0.013
 bath-0.013
 day-0.012
 Mitt-0.011
Token the
Token ID262
Feature activation+1.32e-02

Pos logit contributions
 wear+0.007
 Woo+0.007
 bath+0.006
 Mitt+0.006
 Lucky+0.006
Neg logit contributions
 seventeen-0.013
 unison-0.012
 slices-0.012
 amaz-0.012
 pulp-0.012
Token b
Token ID275
Feature activation+2.43e-02

Pos logit contributions
 wear+0.017
 Woo+0.016
 bath+0.015
 Mitt+0.014
 Lucky+0.014
Neg logit contributions
 unison-0.026
 slices-0.026
 seventeen-0.026
 amaz-0.025
 aroma-0.025
Tokenunn
Token ID20935
Feature activation+1.01e-01

Pos logit contributions
 wear+0.023
 Woo+0.021
 bath+0.020
 skipping+0.019
 Lucky+0.018
Neg logit contributions
 slices-0.057
 seventeen-0.056
 unison-0.055
 aroma-0.055
als-0.054
Tokenies
Token ID444
Feature activation+2.16e-02

Pos logit contributions
 wear+0.146
 Woo+0.139
 bath+0.135
 Mitt+0.126
 Lucky+0.126
Neg logit contributions
 slices-0.184
 unison-0.177
 pulp-0.176
 aroma-0.175
fires-0.175
Token hopped
Token ID45230
Feature activation+2.37e-02

Pos logit contributions
 wear+0.029
 Woo+0.026
 bath+0.026
 day+0.024
 skipping+0.024
Neg logit contributions
 unison-0.043
 seventeen-0.043
 slices-0.042
 amaz-0.042
 aroma-0.041
Token over
Token ID625
Feature activation-3.96e-02

Pos logit contributions
 wear+0.030
 Woo+0.028
 bath+0.027
 Mitt+0.025
 Lucky+0.025
Neg logit contributions
 unison-0.048
 slices-0.048
 seventeen-0.047
 amaz-0.047
 aroma-0.046
Token to
Token ID284
Feature activation-2.87e-02

Pos logit contributions
 seventeen+0.097
 unison+0.096
 aroma+0.094
 pulp+0.093
fires+0.093
Neg logit contributions
 wear-0.034
 bath-0.032
 Woo-0.031
 day-0.029
 skipping-0.029
Token the
Token ID262
Feature activation-2.08e-02

Pos logit contributions
 unison+0.060
 slices+0.060
 seventeen+0.059
 amaz+0.059
 aroma+0.058
Neg logit contributions
 wear-0.035
 Woo-0.032
 bath-0.031
 Mitt-0.029
 Lucky-0.028
Token He
Token ID679
Feature activation-1.63e-02

Pos logit contributions
 unison+0.002
 seventeen+0.002
 amaz+0.002
 slices+0.002
 seconds+0.002
Neg logit contributions
 wear-0.002
 bath-0.002
 Woo-0.002
burn-0.002
 important-0.002
Token had
Token ID550
Feature activation+9.25e-04

Pos logit contributions
 unison+0.028
 slices+0.027
 amaz+0.027
 seconds+0.027
 seventeen+0.027
Neg logit contributions
 wear-0.025
 Woo-0.024
 bath-0.024
burn-0.023
 Mitt-0.022
Token taught
Token ID7817
Feature activation+1.27e-02

Pos logit contributions
 wear+0.001
 Woo+0.001
 bath+0.001
 Mitt+0.001
 Lucky+0.001
Neg logit contributions
 unison-0.002
 slices-0.002
 seventeen-0.002
 amaz-0.002
 aroma-0.002
Token the
Token ID262
Feature activation+2.49e-02

Pos logit contributions
 wear+0.019
burn+0.017
 stub+0.017
 Woo+0.017
 bath+0.017
Neg logit contributions
 unison-0.021
 slices-0.021
 amaz-0.021
 seconds-0.021
 ah-0.020
Token b
Token ID275
Feature activation+2.24e-02

Pos logit contributions
 wear+0.032
 Woo+0.029
burn+0.027
ongo+0.027
ibi+0.026
Neg logit contributions
 slices-0.048
 seconds-0.048
 unison-0.048
 aroma-0.048
 amaz-0.047
Tokenunn
Token ID20935
Feature activation+1.01e-01

Pos logit contributions
 wear+0.022
 Woo+0.020
 bath+0.020
burn+0.018
 skipping+0.018
Neg logit contributions
 slices-0.052
 seventeen-0.050
 seconds-0.050
fires-0.049
 unison-0.049
Tokenies
Token ID444
Feature activation+2.40e-02

Pos logit contributions
 wear+0.136
 Woo+0.127
 bath+0.124
 Mitt+0.116
 Lucky+0.114
Neg logit contributions
 slices-0.194
 unison-0.193
 seventeen-0.190
 amaz-0.188
 aroma-0.187
Token to
Token ID284
Feature activation+8.54e-04

Pos logit contributions
 wear+0.032
 bath+0.028
 Woo+0.027
 important+0.027
 day+0.027
Neg logit contributions
 seventeen-0.049
 unison-0.048
 slices-0.048
 pulp-0.047
 aroma-0.047
Token be
Token ID307
Feature activation-6.89e-03

Pos logit contributions
 Woo+0.001
 wear+0.001
 bath+0.001
burn+0.001
 important+0.001
Neg logit contributions
 unison-0.002
 amaz-0.002
 slices-0.002
 aroma-0.002
 seventeen-0.002
Token friendly
Token ID8030
Feature activation-1.16e-02

Pos logit contributions
 unison+0.015
 slices+0.015
 seventeen+0.014
 amaz+0.014
 aroma+0.014
Neg logit contributions
 wear-0.008
 Woo-0.007
 bath-0.007
 Mitt-0.007
 Lucky-0.007
Token.
Token ID13
Feature activation-7.78e-03

Pos logit contributions
 seventeen+0.028
 pulp+0.027
 slices+0.027
 unison+0.026
 aroma+0.026
Neg logit contributions
 wear-0.012
 bath-0.010
 Woo-0.010
 day-0.010
 Lucky-0.010
Token listen
Token ID6004
Feature activation+1.99e-03

Pos logit contributions
 wear+0.022
 Woo+0.021
 bath+0.020
 Mitt+0.019
 Lucky+0.019
Neg logit contributions
 unison-0.029
 slices-0.029
 seventeen-0.029
 amaz-0.028
 aroma-0.028
Token.
Token ID13
Feature activation+3.24e-03

Pos logit contributions
 wear+0.002
 Woo+0.002
 bath+0.002
 Mitt+0.002
 important+0.002
Neg logit contributions
 unison-0.005
 slices-0.004
 seventeen-0.004
 amaz-0.004
 aroma-0.004
Token She
Token ID1375
Feature activation-1.71e-02

Pos logit contributions
 wear+0.005
 bath+0.004
burn+0.004
 Woo+0.004
 day+0.004
Neg logit contributions
 amaz-0.006
 slices-0.006
 unison-0.006
 seventeen-0.005
 seconds-0.005
Token threw
Token ID9617
Feature activation+2.53e-02

Pos logit contributions
 unison+0.029
 slices+0.028
 seconds+0.028
 seventeen+0.027
 amaz+0.027
Neg logit contributions
 wear-0.027
 Woo-0.026
 bath-0.026
 skipping-0.024
burn-0.024
Token a
Token ID257
Feature activation-8.82e-03

Pos logit contributions
 wear+0.028
 Woo+0.027
 bath+0.026
 Mitt+0.024
 Lucky+0.024
Neg logit contributions
 unison-0.057
fires-0.055
 seventeen-0.055
 amaz-0.054
 slices-0.054
Token tant
Token ID24246
Feature activation-1.34e-01

Pos logit contributions
 unison+0.012
 amaz+0.012
 slices+0.012
 seventeen+0.012
fires+0.012
Neg logit contributions
 wear-0.017
 bath-0.016
 Woo-0.016
 day-0.015
 Lucky-0.015
Tokenrum
Token ID6582
Feature activation-5.48e-02

Pos logit contributions
 unison+0.169
 amaz+0.162
 slices+0.161
 seventeen+0.160
fires+0.155
Neg logit contributions
 wear-0.275
 Woo-0.259
 bath-0.253
 Mitt-0.246
 important-0.246
Token in
Token ID287
Feature activation-2.63e-02

Pos logit contributions
 seventeen+0.133
 unison+0.132
 amaz+0.130
 slices+0.128
 aroma+0.128
Neg logit contributions
 wear-0.050
 Woo-0.047
 day-0.044
 skipping-0.043
 always-0.042
Token the
Token ID262
Feature activation-3.67e-02

Pos logit contributions
 unison+0.055
 seventeen+0.055
 slices+0.055
 amaz+0.054
fires+0.054
Neg logit contributions
 wear-0.031
 Woo-0.029
 bath-0.028
 Mitt-0.026
 day-0.026
Token store
Token ID3650
Feature activation-1.32e-03

Pos logit contributions
 unison+0.079
 slices+0.078
 seventeen+0.077
 amaz+0.077
 aroma+0.076
Neg logit contributions
 wear-0.042
 Woo-0.038
 bath-0.035
 Mitt-0.034
burn-0.034
Token.
Token ID13
Feature activation-8.14e-03

Pos logit contributions
 seventeen+0.003
 unison+0.003
 amaz+0.003
 pulp+0.003
 aroma+0.003
Neg logit contributions
 wear-0.001
 Woo-0.001
 bath-0.001
 day-0.001
 Mitt-0.001
Token.
Token ID13
Feature activation+1.10e-03

Pos logit contributions
 wear+0.007
 Woo+0.007
 bath+0.006
 day+0.006
 important+0.006
Neg logit contributions
 unison-0.013
 seventeen-0.013
 slices-0.013
 amaz-0.013
 pulp-0.013
Token He
Token ID679
Feature activation-2.43e-02

Pos logit contributions
 wear+0.001
 Woo+0.001
 Mitt+0.001
 bath+0.001
 day+0.001
Neg logit contributions
 unison-0.002
 seventeen-0.002
 slices-0.002
 aroma-0.002
 pulp-0.002
Token kept
Token ID4030
Feature activation+3.67e-02

Pos logit contributions
 slices+0.043
 unison+0.043
 seventeen+0.043
 amaz+0.042
 pulp+0.041
Neg logit contributions
 wear-0.038
 Woo-0.035
 bath-0.034
 Mitt-0.032
 Lucky-0.032
Token throwing
Token ID9644
Feature activation+2.06e-02

Pos logit contributions
 wear+0.044
 Woo+0.040
 bath+0.040
 important+0.037
 Lucky+0.037
Neg logit contributions
 slices-0.076
 seconds-0.074
 amaz-0.073
 unison-0.073
 seventeen-0.072
Token a
Token ID257
Feature activation-6.42e-03

Pos logit contributions
 wear+0.024
 bath+0.022
 Woo+0.021
 Mitt+0.020
 day+0.020
Neg logit contributions
 unison-0.046
fires-0.045
 seventeen-0.044
atively-0.043
 MacDonald-0.043
Token tant
Token ID24246
Feature activation-1.32e-01

Pos logit contributions
 unison+0.013
fires+0.013
pter+0.013
 amaz+0.013
 seventeen+0.013
Neg logit contributions
 wear-0.008
 bath-0.008
 Woo-0.007
 day-0.007
 important-0.007
Tokenrum
Token ID6582
Feature activation-4.88e-02

Pos logit contributions
 unison+0.182
 amaz+0.174
 slices+0.167
 seventeen+0.166
fires+0.166
Neg logit contributions
 wear-0.259
 Woo-0.240
 important-0.232
 bath-0.232
burn-0.231
Token.
Token ID13
Feature activation-5.87e-03

Pos logit contributions
 seventeen+0.111
 unison+0.110
 amaz+0.109
 aroma+0.108
 pulp+0.108
Neg logit contributions
 wear-0.050
 Woo-0.046
 day-0.044
 bath-0.043
 important-0.042
Token His
Token ID2399
Feature activation+2.62e-02

Pos logit contributions
 unison+0.011
 slices+0.011
 seventeen+0.011
 aroma+0.011
 amaz+0.011
Neg logit contributions
 wear-0.008
 Woo-0.008
 bath-0.008
 Mitt-0.007
 Lucky-0.007
Token mom
Token ID1995
Feature activation-3.98e-02

Pos logit contributions
 wear+0.026
 Woo+0.023
 bath+0.023
 Mitt+0.020
 day+0.020
Neg logit contributions
 unison-0.061
 slices-0.060
 seventeen-0.060
 amaz-0.060
fires-0.059
Token was
Token ID373
Feature activation-5.13e-03

Pos logit contributions
 unison+0.075
 seventeen+0.075
 slices+0.074
 amaz+0.074
 pulp+0.073
Neg logit contributions
 wear-0.056
 Woo-0.051
 bath-0.050
 Mitt-0.048
 Lucky-0.047
Token her
Token ID607
Feature activation+7.41e-03

Pos logit contributions
 seventeen+0.065
 unison+0.065
fires+0.064
 slices+0.062
 pulp+0.062
Neg logit contributions
 wear-0.018
 Woo-0.015
 Mitt-0.015
 bath-0.015
 Lucky-0.013
Token feet
Token ID3625
Feature activation+1.02e-02

Pos logit contributions
 wear+0.013
 bath+0.012
 Woo+0.012
 day+0.012
 skipping+0.012
Neg logit contributions
 seventeen-0.011
 unison-0.011
 slices-0.011
 amaz-0.011
fires-0.011
Token and
Token ID290
Feature activation-2.12e-03

Pos logit contributions
 wear+0.014
 Woo+0.013
 bath+0.012
 Lucky+0.012
 Mitt+0.012
Neg logit contributions
 slices-0.020
 unison-0.019
 seventeen-0.019
 amaz-0.019
 seconds-0.019
Token threw
Token ID9617
Feature activation+2.36e-02

Pos logit contributions
 unison+0.004
 seventeen+0.004
fires+0.004
 amaz+0.004
 slices+0.004
Neg logit contributions
 wear-0.003
 Woo-0.003
 Mitt-0.003
 Lucky-0.003
 bath-0.003
Token a
Token ID257
Feature activation-9.90e-03

Pos logit contributions
 wear+0.024
 Woo+0.023
 bath+0.022
 Mitt+0.022
 Lucky+0.020
Neg logit contributions
fires-0.055
 unison-0.054
 seventeen-0.053
 amaz-0.052
 aroma-0.051
Token tant
Token ID24246
Feature activation-1.31e-01

Pos logit contributions
 unison+0.013
fires+0.012
 amaz+0.012
pter+0.012
 seventeen+0.011
Neg logit contributions
 wear-0.021
 bath-0.020
 Woo-0.019
 day-0.019
 rubber-0.018
Tokenrum
Token ID6582
Feature activation-4.81e-02

Pos logit contributions
 unison+0.149
 slices+0.147
 seventeen+0.144
 amaz+0.143
 aroma+0.138
Neg logit contributions
 wear-0.283
 Woo-0.269
 bath-0.264
 Mitt-0.255
 day-0.253
Token.
Token ID13
Feature activation-1.00e-02

Pos logit contributions
 seventeen+0.105
 unison+0.104
 slices+0.103
 amaz+0.103
 aroma+0.101
Neg logit contributions
 wear-0.054
 Woo-0.050
 bath-0.047
 skipping-0.046
 day-0.045
Token She
Token ID1375
Feature activation-2.12e-02

Pos logit contributions
 slices+0.019
 unison+0.019
 seventeen+0.018
 amaz+0.018
 seconds+0.018
Neg logit contributions
 wear-0.014
 Woo-0.012
 bath-0.012
burn-0.012
 important-0.012
Token grabbed
Token ID13176
Feature activation-2.53e-02

Pos logit contributions
 unison+0.037
 slices+0.037
 seventeen+0.037
 amaz+0.037
 aroma+0.036
Neg logit contributions
 wear-0.033
 Woo-0.030
 bath-0.030
 Mitt-0.028
 Lucky-0.028
Token the
Token ID262
Feature activation-2.68e-03

Pos logit contributions
 slices+0.053
 unison+0.053
 seventeen+0.052
 amaz+0.052
 seconds+0.051
Neg logit contributions
 wear-0.030
 Woo-0.027
 bath-0.027
 important-0.025
 Mitt-0.024
Token She
Token ID1375
Feature activation-8.85e-03

Pos logit contributions
 wear+0.005
 Woo+0.004
 bath+0.004
burn+0.004
 jog+0.004
Neg logit contributions
 slices-0.005
 amaz-0.005
 unison-0.005
 seventeen-0.005
als-0.005
Token cried
Token ID16896
Feature activation+1.42e-02

Pos logit contributions
 seconds+0.014
 unison+0.013
 slices+0.013
 gasped+0.013
 amaz+0.012
Neg logit contributions
 wear-0.014
 Woo-0.014
 bath-0.014
burn-0.014
 skipping-0.013
Token and
Token ID290
Feature activation+7.14e-03

Pos logit contributions
 wear+0.017
 Woo+0.015
 bath+0.015
 Mitt+0.014
 Lucky+0.014
Neg logit contributions
 unison-0.030
 slices-0.030
 seventeen-0.030
 amaz-0.030
 aroma-0.029
Token threw
Token ID9617
Feature activation+2.76e-02

Pos logit contributions
 wear+0.010
 Woo+0.010
 bath+0.010
 Mitt+0.009
 Lucky+0.009
Neg logit contributions
 unison-0.013
 slices-0.013
 seventeen-0.013
 amaz-0.013
 aroma-0.012
Token a
Token ID257
Feature activation-5.17e-03

Pos logit contributions
 wear+0.019
 bath+0.016
 Woo+0.016
 Mitt+0.016
 day+0.015
Neg logit contributions
fires-0.075
 unison-0.075
 seventeen-0.074
 amaz-0.071
 pulp-0.071
Token tant
Token ID24246
Feature activation-1.29e-01

Pos logit contributions
 unison+0.008
 seventeen+0.008
 slices+0.008
 amaz+0.007
fires+0.007
Neg logit contributions
 wear-0.009
 bath-0.009
 Woo-0.009
 day-0.008
 Mitt-0.008
Tokenrum
Token ID6582
Feature activation-4.63e-02

Pos logit contributions
 unison+0.152
 slices+0.149
 seventeen+0.147
 amaz+0.146
fires+0.140
Neg logit contributions
 wear-0.273
 Woo-0.259
 bath-0.254
 Mitt-0.246
 day-0.244
Token.
Token ID13
Feature activation-9.61e-03

Pos logit contributions
 seventeen+0.106
 unison+0.104
 slices+0.103
 amaz+0.103
 pulp+0.101
Neg logit contributions
 wear-0.049
 Woo-0.046
 bath-0.043
 day-0.042
 Mitt-0.042
Token Her
Token ID2332
Feature activation+4.41e-02

Pos logit contributions
 slices+0.017
 amaz+0.017
 unison+0.016
 seventeen+0.016
 pulp+0.016
Neg logit contributions
 wear-0.014
burn-0.012
 Woo-0.012
 bath-0.012
 jog-0.012
Token mom
Token ID1995
Feature activation-3.56e-02

Pos logit contributions
 wear+0.052
 Woo+0.052
 bath+0.044
 Lucky+0.044
burn+0.044
Neg logit contributions
 slices-0.092
 amaz-0.090
 unison-0.088
 seconds-0.087
 pulp-0.087
Token tried
Token ID3088
Feature activation+5.71e-02

Pos logit contributions
 slices+0.060
 unison+0.060
 seconds+0.059
 amaz+0.058
 seventeen+0.058
Neg logit contributions
 wear-0.055
 Woo-0.052
 bath-0.051
 skipping-0.048
 important-0.047
Token watched
Token ID7342
Feature activation-7.76e-03

Pos logit contributions
 slices+0.024
 unison+0.024
 seventeen+0.024
fires+0.024
 aroma+0.024
Neg logit contributions
 wear-0.017
 Woo-0.015
 bath-0.015
 skipping-0.014
 day-0.014
Token the
Token ID262
Feature activation-1.41e-02

Pos logit contributions
 seventeen+0.016
 unison+0.016
 slices+0.016
fires+0.016
 pulp+0.016
Neg logit contributions
 wear-0.010
 Woo-0.008
 bath-0.008
 skipping-0.008
 day-0.008
Token colorful
Token ID20239
Feature activation-1.22e-02

Pos logit contributions
 seventeen+0.029
 slices+0.029
pter+0.028
 unison+0.028
fires+0.028
Neg logit contributions
 wear-0.018
 day-0.018
 bath-0.016
 skipping-0.016
 important-0.016
Token lights
Token ID7588
Feature activation+3.33e-03

Pos logit contributions
 unison+0.025
 seventeen+0.025
fires+0.025
 slices+0.025
pter+0.024
Neg logit contributions
 wear-0.016
 day-0.015
 skipping-0.015
 bath-0.014
 jog-0.013
Token in
Token ID287
Feature activation-2.64e-02

Pos logit contributions
 wear+0.004
 bath+0.003
 Woo+0.003
 day+0.003
 skipping+0.003
Neg logit contributions
 unison-0.007
 slices-0.007
 seventeen-0.007
 pulp-0.007
 seconds-0.007
Token amaz
Token ID40642
Feature activation-1.28e-01

Pos logit contributions
 seventeen+0.066
fires+0.065
 pulp+0.062
pter+0.061
 slices+0.061
Neg logit contributions
 wear-0.025
 day-0.021
 bath-0.021
 skipping-0.020
 Woo-0.019
Tokenement
Token ID972
Feature activation-4.62e-02

Pos logit contributions
 seventeen+0.168
 pulp+0.161
fires+0.157
 unison+0.153
 slices+0.145
Neg logit contributions
 wear-0.248
ie-0.236
 day-0.235
 bath-0.233
 important-0.231
Token,
Token ID11
Feature activation-1.89e-02

Pos logit contributions
 seventeen+0.098
 unison+0.097
 slices+0.097
 pulp+0.095
 seconds+0.094
Neg logit contributions
 wear-0.056
 bath-0.048
 day-0.046
 Woo-0.046
 skipping-0.046
Token feeling
Token ID4203
Feature activation-2.40e-02

Pos logit contributions
 unison+0.042
 slices+0.041
 seventeen+0.041
anish+0.041
fires+0.040
Neg logit contributions
 wear-0.022
 skipping-0.019
 always-0.018
 Woo-0.018
 day-0.017
Token truly
Token ID4988
Feature activation-1.68e-02

Pos logit contributions
 slices+0.052
 seventeen+0.052
 unison+0.051
 pulp+0.050
anish+0.050
Neg logit contributions
 wear-0.028
 Woo-0.025
 important-0.024
 bath-0.024
 skipping-0.024
Token lucky
Token ID9670
Feature activation-1.42e-02

Pos logit contributions
 seventeen+0.036
 slices+0.036
 unison+0.035
anish+0.035
 pulp+0.035
Neg logit contributions
 wear-0.021
 important-0.019
 skipping-0.018
 day-0.018
 always-0.017
Token to
Token ID284
Feature activation-1.01e-03

Pos logit contributions
ongo+0.091
 Woo+0.088
 wear+0.087
opsy+0.087
scar+0.087
Neg logit contributions
 slices-0.102
 amaz-0.102
 seconds-0.101
 faces-0.096
 moments-0.092
Token cry
Token ID3960
Feature activation+2.00e-03

Pos logit contributions
 amaz+0.002
 unison+0.002
 aroma+0.002
 gasp+0.002
 slices+0.001
Neg logit contributions
 Woo-0.002
ip-0.002
 important-0.002
scar-0.002
ained-0.002
Token and
Token ID290
Feature activation+1.18e-02

Pos logit contributions
 wear+0.003
 Woo+0.002
 bath+0.002
 skipping+0.002
burn+0.002
Neg logit contributions
 unison-0.004
 slices-0.004
 amaz-0.004
 seconds-0.004
 aroma-0.004
Token threw
Token ID9617
Feature activation+2.50e-02

Pos logit contributions
 wear+0.015
 Woo+0.014
 bath+0.013
burn+0.013
 important+0.012
Neg logit contributions
 unison-0.023
 amaz-0.023
 slices-0.023
 seconds-0.023
 aroma-0.023
Token a
Token ID257
Feature activation-5.29e-03

Pos logit contributions
 wear+0.022
 Woo+0.020
 bath+0.019
 Mitt+0.018
 day+0.017
Neg logit contributions
 unison-0.063
 seventeen-0.062
fires-0.061
 slices-0.060
 amaz-0.060
Token tant
Token ID24246
Feature activation-1.28e-01

Pos logit contributions
 slices+0.008
 unison+0.008
 seventeen+0.008
 amaz+0.008
 aroma+0.008
Neg logit contributions
 wear-0.009
 Woo-0.008
 bath-0.008
 Mitt-0.008
 Lucky-0.008
Tokenrum
Token ID6582
Feature activation-4.14e-02

Pos logit contributions
 slices+0.135
 unison+0.133
 seventeen+0.131
 amaz+0.128
 seconds+0.126
Neg logit contributions
 wear-0.282
 Woo-0.271
 bath-0.268
 Mitt-0.257
 Lucky-0.256
Token.
Token ID13
Feature activation-5.66e-03

Pos logit contributions
 unison+0.081
 slices+0.081
 seventeen+0.080
 amaz+0.079
 aroma+0.078
Neg logit contributions
 wear-0.055
 Woo-0.051
 bath-0.050
 Mitt-0.046
 Lucky-0.046
Token She
Token ID1375
Feature activation-1.40e-02

Pos logit contributions
 slices+0.011
 amaz+0.011
 unison+0.011
 seventeen+0.010
 aroma+0.010
Neg logit contributions
 wear-0.007
 Woo-0.007
 bath-0.007
burn-0.007
 day-0.006
Token didn
Token ID1422
Feature activation-1.16e-02

Pos logit contributions
 seconds+0.021
 unison+0.020
 slices+0.020
 gasped+0.020
 amaz+0.019
Neg logit contributions
 wear-0.023
 Woo-0.023
 bath-0.023
burn-0.023
 skipping-0.022
Token't
Token ID470
Feature activation+5.74e-02

Pos logit contributions
 slices+0.012
oor+0.012
 seventeen+0.012
 seconds+0.011
 unison+0.011
Neg logit contributions
ety-0.022
opsy-0.022
 wear-0.022
 day-0.021
 important-0.021
Token kept
Token ID4030
Feature activation+4.64e-02

Pos logit contributions
 seconds+0.005
 unison+0.004
 gasped+0.004
 slices+0.004
 aroma+0.004
Neg logit contributions
 wear-0.005
 Woo-0.005
 bath-0.005
burn-0.004
 skipping-0.004
Token crying
Token ID13774
Feature activation-6.83e-03

Pos logit contributions
 wear+0.061
ongo+0.055
 Woo+0.055
 bath+0.054
ibi+0.054
Neg logit contributions
 slices-0.088
 seconds-0.087
 amaz-0.084
 aroma-0.083
 unison-0.082
Token and
Token ID290
Feature activation+1.11e-02

Pos logit contributions
 seventeen+0.015
 unison+0.015
 slices+0.015
 amaz+0.015
 pulp+0.015
Neg logit contributions
 wear-0.008
 Woo-0.007
 bath-0.007
 important-0.006
 Mitt-0.006
Token throwing
Token ID9644
Feature activation+1.98e-02

Pos logit contributions
 wear+0.013
 Woo+0.012
 bath+0.012
 Mitt+0.011
 Lucky+0.011
Neg logit contributions
 unison-0.023
 slices-0.023
 seventeen-0.023
 amaz-0.023
 seconds-0.022
Token a
Token ID257
Feature activation-9.37e-04

Pos logit contributions
 wear+0.019
 Woo+0.018
 bath+0.017
 Mitt+0.017
 Lucky+0.016
Neg logit contributions
 unison-0.047
 seventeen-0.047
fires-0.046
 amaz-0.046
pter-0.045
Token tant
Token ID24246
Feature activation-1.27e-01

Pos logit contributions
 unison+0.001
 slices+0.001
 seventeen+0.001
 amaz+0.001
fires+0.001
Neg logit contributions
 wear-0.002
 Woo-0.002
 bath-0.002
 Mitt-0.002
 day-0.002
Tokenrum
Token ID6582
Feature activation-3.73e-02

Pos logit contributions
 slices+0.134
 unison+0.132
 seventeen+0.130
 amaz+0.127
 seconds+0.126
Neg logit contributions
 wear-0.280
 Woo-0.269
 bath-0.266
 Mitt-0.255
 Lucky-0.254
Token.
Token ID13
Feature activation+1.33e-04

Pos logit contributions
 unison+0.077
 seventeen+0.076
 slices+0.076
 amaz+0.075
 aroma+0.074
Neg logit contributions
 wear-0.046
 Woo-0.043
 bath-0.041
 Mitt-0.039
 day-0.039
Token
Token ID198
Feature activation+3.38e-04

Pos logit contributions
 wear+0.000
 Woo+0.000
burn+0.000
 bath+0.000
 jog+0.000
Neg logit contributions
 slices-0.000
 unison-0.000
 amaz-0.000
 seventeen-0.000
 seconds-0.000
Token
Token ID198
Feature activation-1.26e-02

Pos logit contributions
burn+0.001
 wear+0.001
 Woo+0.001
 bath+0.001
 exercise+0.001
Neg logit contributions
 slices-0.000
 seconds-0.000
 unison-0.000
 gasped-0.000
fires-0.000
TokenFinally
Token ID11158
Feature activation-3.52e-02

Pos logit contributions
 unison+0.017
 seconds+0.016
 slices+0.015
fires+0.015
 seventeen+0.015
Neg logit contributions
 wear-0.023
burn-0.023
 Woo-0.023
 bath-0.022
 Nut-0.021
Token sad
Token ID6507
Feature activation-6.63e-03

Pos logit contributions
 wear+0.034
 bath+0.033
 Woo+0.032
burn+0.032
opsy+0.029
Neg logit contributions
 slices-0.039
 unison-0.039
 aroma-0.039
 seconds-0.039
 amaz-0.038
Token.
Token ID13
Feature activation+1.77e-02

Pos logit contributions
 seventeen+0.016
 unison+0.016
 slices+0.015
 pulp+0.015
 amaz+0.015
Neg logit contributions
 wear-0.007
 Woo-0.006
 bath-0.006
 day-0.006
 important-0.006
Token She
Token ID1375
Feature activation-4.83e-03

Pos logit contributions
 wear+0.027
 bath+0.025
 Woo+0.025
burn+0.024
 important+0.022
Neg logit contributions
 slices-0.030
 amaz-0.030
 seventeen-0.029
 unison-0.029
 seconds-0.028
Token threw
Token ID9617
Feature activation+2.92e-02

Pos logit contributions
 unison+0.008
 seconds+0.008
 slices+0.008
 seventeen+0.008
 amaz+0.008
Neg logit contributions
 wear-0.007
 bath-0.007
 Woo-0.007
burn-0.007
 skipping-0.006
Token a
Token ID257
Feature activation+7.80e-04

Pos logit contributions
 wear+0.029
 Woo+0.027
 bath+0.025
 Mitt+0.025
 day+0.024
Neg logit contributions
 unison-0.070
fires-0.069
 seventeen-0.069
 pulp-0.066
 amaz-0.066
Token tant
Token ID24246
Feature activation-1.26e-01

Pos logit contributions
 wear+0.001
 Woo+0.001
 bath+0.001
 Mitt+0.001
 day+0.001
Neg logit contributions
 unison-0.001
 slices-0.001
 seventeen-0.001
 amaz-0.001
fires-0.001
Tokenrum
Token ID6582
Feature activation-4.43e-02

Pos logit contributions
 unison+0.143
 slices+0.141
 seventeen+0.138
 amaz+0.137
 aroma+0.132
Neg logit contributions
 wear-0.272
 Woo-0.259
 bath-0.254
 Mitt-0.245
 day-0.243
Token and
Token ID290
Feature activation+2.28e-04

Pos logit contributions
 seventeen+0.098
 unison+0.098
 slices+0.098
 amaz+0.096
 aroma+0.095
Neg logit contributions
 wear-0.048
 Woo-0.045
 bath-0.042
 skipping-0.041
 day-0.040
Token cried
Token ID16896
Feature activation+1.23e-02

Pos logit contributions
 wear+0.000
 Woo+0.000
 bath+0.000
 Mitt+0.000
 Lucky+0.000
Neg logit contributions
 unison-0.000
 slices-0.000
 seventeen-0.000
 amaz-0.000
 aroma-0.000
Token loudly
Token ID23112
Feature activation-4.23e-02

Pos logit contributions
 wear+0.017
 Woo+0.015
 bath+0.015
burn+0.014
 day+0.014
Neg logit contributions
 slices-0.024
 unison-0.024
 seventeen-0.023
 amaz-0.023
 seconds-0.023
Token.
Token ID13
Feature activation+2.59e-03

Pos logit contributions
 unison+0.099
 pulp+0.098
 seventeen+0.097
 slices+0.097
 amaz+0.097
Neg logit contributions
 wear-0.041
 Woo-0.038
 bath-0.036
 Mitt-0.035
 day-0.035
Token and
Token ID290
Feature activation+1.75e-02

Pos logit contributions
 unison+0.079
 slices+0.078
 seventeen+0.078
 amaz+0.077
 aroma+0.076
Neg logit contributions
 wear-0.044
 Woo-0.040
 bath-0.039
 Mitt-0.036
 Lucky-0.036
Token started
Token ID2067
Feature activation+5.47e-02

Pos logit contributions
 wear+0.028
 bath+0.026
 Woo+0.026
burn+0.025
 day+0.024
Neg logit contributions
 slices-0.028
 aroma-0.028
 seconds-0.028
 pulp-0.027
 unison-0.027
Token to
Token ID284
Feature activation-3.15e-03

Pos logit contributions
 wear+0.071
 Woo+0.066
 bath+0.060
ongo+0.060
 Lucky+0.059
Neg logit contributions
 slices-0.109
 seconds-0.104
 aroma-0.101
 pulp-0.100
 amaz-0.100
Token throw
Token ID3714
Feature activation+3.30e-02

Pos logit contributions
 aroma+0.005
 slices+0.004
 amaz+0.004
 unison+0.004
 pulp+0.004
Neg logit contributions
 Woo-0.005
 wear-0.005
 important-0.005
un-0.005
 bath-0.005
Token a
Token ID257
Feature activation+1.45e-03

Pos logit contributions
 wear+0.030
 Woo+0.029
 bath+0.029
 Mitt+0.028
 Lucky+0.026
Neg logit contributions
 unison-0.082
fires-0.081
 seventeen-0.080
 amaz-0.080
folk-0.077
Token tant
Token ID24246
Feature activation-1.26e-01

Pos logit contributions
 wear+0.002
 bath+0.002
 Woo+0.002
 day+0.002
 Lucky+0.002
Neg logit contributions
 unison-0.003
fires-0.002
 amaz-0.002
 seventeen-0.002
folk-0.002
Tokenrum
Token ID6582
Feature activation-4.16e-02

Pos logit contributions
 slices+0.137
 unison+0.137
 seventeen+0.134
 amaz+0.131
 aroma+0.128
Neg logit contributions
 wear-0.275
 Woo-0.263
 bath-0.260
 Mitt-0.249
 Lucky-0.248
Token.
Token ID13
Feature activation-6.12e-04

Pos logit contributions
 unison+0.082
 slices+0.082
 seventeen+0.081
 amaz+0.080
 aroma+0.079
Neg logit contributions
 wear-0.055
 Woo-0.051
 bath-0.050
 Mitt-0.046
 Lucky-0.046
Token Suddenly
Token ID24975
Feature activation+1.76e-02

Pos logit contributions
 slices+0.001
 amaz+0.001
 unison+0.001
 seventeen+0.001
 aroma+0.001
Neg logit contributions
 wear-0.001
 Woo-0.001
 bath-0.001
burn-0.001
 important-0.001
Token,
Token ID11
Feature activation-1.73e-02

Pos logit contributions
 wear+0.022
 Woo+0.021
 bath+0.020
burn+0.019
 important+0.019
Neg logit contributions
 slices-0.035
 unison-0.034
 amaz-0.034
 seconds-0.034
 seventeen-0.034
Token she
Token ID673
Feature activation-2.48e-02

Pos logit contributions
 slices+0.040
 unison+0.040
 seventeen+0.039
 amaz+0.039
 aroma+0.039
Neg logit contributions
 wear-0.017
 Woo-0.015
 bath-0.015
 Mitt-0.013
 Lucky-0.013
Tokenered
Token ID1068
Feature activation+2.71e-03

Pos logit contributions
 wear+0.009
 Woo+0.009
 bath+0.009
 Mitt+0.008
 Lucky+0.008
Neg logit contributions
 unison-0.007
 slices-0.007
 seventeen-0.007
 amaz-0.007
 aroma-0.007
Token in
Token ID287
Feature activation-2.45e-02

Pos logit contributions
 wear+0.003
 Woo+0.003
 bath+0.003
 skipping+0.002
 important+0.002
Neg logit contributions
 unison-0.006
 seventeen-0.006
 slices-0.006
 aroma-0.006
 amaz-0.006
Token,
Token ID11
Feature activation-8.09e-03

Pos logit contributions
 seventeen+0.058
 pulp+0.057
fires+0.057
 unison+0.055
 aroma+0.055
Neg logit contributions
 wear-0.025
 bath-0.021
 skipping-0.021
 day-0.020
 Woo-0.019
Token blinking
Token ID43196
Feature activation-1.55e-02

Pos logit contributions
 unison+0.017
 slices+0.016
 seventeen+0.016
 amaz+0.016
 aroma+0.016
Neg logit contributions
 wear-0.010
 Woo-0.009
 bath-0.009
 skipping-0.009
 Mitt-0.009
Token in
Token ID287
Feature activation-3.00e-02

Pos logit contributions
 seventeen+0.037
 unison+0.037
 slices+0.035
 pulp+0.035
anish+0.035
Neg logit contributions
 wear-0.014
 important-0.012
 skipping-0.012
 bath-0.012
 Lucky-0.011
Token amaz
Token ID40642
Feature activation-1.25e-01

Pos logit contributions
 seventeen+0.070
fires+0.070
 pulp+0.068
 slices+0.066
 aroma+0.066
Neg logit contributions
 wear-0.030
 bath-0.027
 skipping-0.026
 day-0.026
 Mitt-0.023
Tokenement
Token ID972
Feature activation-2.80e-02

Pos logit contributions
 pulp+0.166
 seventeen+0.166
 unison+0.164
fires+0.156
 slices+0.145
Neg logit contributions
 important-0.228
 wear-0.226
ie-0.223
 day-0.215
idy-0.214
Token.
Token ID13
Feature activation+9.49e-04

Pos logit contributions
 seventeen+0.062
 unison+0.062
 pulp+0.060
 slices+0.060
 amaz+0.059
Neg logit contributions
 wear-0.031
 bath-0.026
 day-0.026
 skipping-0.026
 Woo-0.025
Token
Token ID198
Feature activation-4.39e-03

Pos logit contributions
 wear+0.001
 Woo+0.001
 bath+0.001
 Mitt+0.001
 Lucky+0.001
Neg logit contributions
 unison-0.002
 slices-0.002
 seventeen-0.002
 amaz-0.002
 aroma-0.002
Token
Token ID198
Feature activation-1.67e-02

Pos logit contributions
 unison+0.009
 slices+0.009
 seventeen+0.009
 amaz+0.008
 seconds+0.008
Neg logit contributions
 wear-0.006
 Woo-0.005
 bath-0.005
burn-0.005
 Mitt-0.005
TokenBut
Token ID1537
Feature activation-1.91e-02

Pos logit contributions
 unison+0.028
 slices+0.028
 seventeen+0.028
 amaz+0.028
 aroma+0.027
Neg logit contributions
 wear-0.027
 Woo-0.025
 bath-0.024
 Mitt-0.023
 Lucky-0.023
Token surprise
Token ID5975
Feature activation-2.15e-02

Pos logit contributions
 wear+0.012
 bath+0.012
 day+0.011
 important+0.011
 Woo+0.011
Neg logit contributions
 unison-0.015
 seventeen-0.015
 slices-0.014
fires-0.014
 amaz-0.014
Token.
Token ID13
Feature activation+6.20e-03

Pos logit contributions
 unison+0.044
 seventeen+0.044
 amaz+0.043
 slices+0.043
 pulp+0.042
Neg logit contributions
 wear-0.027
 bath-0.024
 Woo-0.024
 day-0.023
 important-0.022
Token He
Token ID679
Feature activation-2.43e-02

Pos logit contributions
 wear+0.008
 Woo+0.008
 bath+0.007
 Mitt+0.007
 Lucky+0.007
Neg logit contributions
 unison-0.012
 slices-0.012
 aroma-0.012
 seventeen-0.012
 pulp-0.012
Token threw
Token ID9617
Feature activation+2.67e-02

Pos logit contributions
 unison+0.042
 slices+0.042
 seventeen+0.042
 amaz+0.041
 aroma+0.040
Neg logit contributions
 wear-0.038
 Woo-0.035
 bath-0.034
 Mitt-0.033
 Lucky-0.032
Token a
Token ID257
Feature activation-1.30e-02

Pos logit contributions
 Woo+0.020
 bath+0.020
 wear+0.020
 Mitt+0.019
 day+0.019
Neg logit contributions
fires-0.072
 unison-0.071
 MacDonald-0.067
edly-0.066
folk-0.066
Token tant
Token ID24246
Feature activation-1.24e-01

Pos logit contributions
 unison+0.025
fires+0.025
 amaz+0.024
pter+0.024
 MacDonald+0.024
Neg logit contributions
 wear-0.018
 bath-0.018
 Woo-0.016
 day-0.016
 Lucky-0.015
Tokenrum
Token ID6582
Feature activation-5.24e-02

Pos logit contributions
 unison+0.167
 amaz+0.161
 seventeen+0.155
 slices+0.154
fires+0.152
Neg logit contributions
 wear-0.247
 Woo-0.231
 bath-0.223
 important-0.222
 day-0.220
Token.
Token ID13
Feature activation-4.13e-03

Pos logit contributions
 seventeen+0.125
 unison+0.125
 amaz+0.124
 aroma+0.123
 pulp+0.121
Neg logit contributions
 wear-0.048
 Woo-0.044
 day-0.043
 bath-0.041
 always-0.040
Token He
Token ID679
Feature activation-3.44e-02

Pos logit contributions
 unison+0.008
 slices+0.008
 aroma+0.008
 seventeen+0.008
 amaz+0.008
Neg logit contributions
 wear-0.006
 Woo-0.005
 bath-0.005
 Mitt-0.005
 Lucky-0.005
Token kicked
Token ID12165
Feature activation+1.73e-02

Pos logit contributions
 unison+0.064
 amaz+0.064
 seventeen+0.063
 slices+0.063
fires+0.062
Neg logit contributions
 wear-0.050
 Woo-0.047
 bath-0.045
 Mitt-0.043
 Lucky-0.043
Token and
Token ID290
Feature activation-1.81e-02

Pos logit contributions
 Woo+0.012
 wear+0.012
 Mitt+0.012
 bath+0.011
 Lucky+0.011
Neg logit contributions
fires-0.047
 unison-0.046
pter-0.044
 amaz-0.044
 aroma-0.044
Token.
Token ID13
Feature activation-7.27e-03

Pos logit contributions
 seventeen+0.029
 pulp+0.029
 slices+0.028
 unison+0.028
 seconds+0.027
Neg logit contributions
 wear-0.012
 bath-0.011
 day-0.011
 always-0.010
 skipping-0.010
Token The
Token ID383
Feature activation+2.70e-03

Pos logit contributions
 unison+0.015
 slices+0.015
 aroma+0.015
 seventeen+0.015
 amaz+0.015
Neg logit contributions
 wear-0.009
 Woo-0.009
 Mitt-0.008
 bath-0.008
 Lucky-0.008
Token deer
Token ID20096
Feature activation+2.06e-02

Pos logit contributions
 wear+0.003
 Woo+0.003
 bath+0.003
 day+0.003
 important+0.003
Neg logit contributions
 slices-0.006
 seventeen-0.006
 unison-0.006
 amaz-0.005
 pulp-0.005
Token stared
Token ID18484
Feature activation+1.11e-02

Pos logit contributions
 wear+0.031
 Woo+0.028
 bath+0.027
 day+0.026
 skipping+0.026
Neg logit contributions
 slices-0.037
 unison-0.037
 seventeen-0.037
 amaz-0.036
 aroma-0.036
Token in
Token ID287
Feature activation-2.42e-02

Pos logit contributions
 wear+0.014
 Woo+0.013
 bath+0.012
 Mitt+0.012
 Lucky+0.011
Neg logit contributions
 unison-0.023
 slices-0.023
 seventeen-0.022
 amaz-0.022
 aroma-0.022
Token amaz
Token ID40642
Feature activation-1.24e-01

Pos logit contributions
fires+0.037
 seventeen+0.034
folk+0.034
 pulp+0.034
pter+0.034
Neg logit contributions
 wear-0.047
 skipping-0.045
 bath-0.044
 day-0.044
 jog-0.042
Tokenement
Token ID972
Feature activation-4.44e-02

Pos logit contributions
 seventeen+0.159
 pulp+0.154
 unison+0.151
fires+0.148
 slices+0.143
Neg logit contributions
 wear-0.243
ie-0.232
 important-0.230
 always-0.225
 bath-0.221
Token.
Token ID13
Feature activation-7.53e-03

Pos logit contributions
 seventeen+0.103
 unison+0.100
 slices+0.100
 pulp+0.099
fires+0.097
Neg logit contributions
 wear-0.046
 day-0.039
 bath-0.039
 skipping-0.038
 Woo-0.037
Token He
Token ID679
Feature activation-2.69e-02

Pos logit contributions
 unison+0.015
 slices+0.014
 aroma+0.014
 seventeen+0.014
 amaz+0.014
Neg logit contributions
 wear-0.010
 Woo-0.010
 bath-0.009
 Mitt-0.009
 Lucky-0.009
Token had
Token ID550
Feature activation-9.95e-03

Pos logit contributions
 slices+0.051
 seventeen+0.051
 unison+0.050
 aroma+0.049
 pulp+0.049
Neg logit contributions
 wear-0.039
 Woo-0.034
 always-0.034
 bath-0.033
 Lucky-0.033
Token never
Token ID1239
Feature activation+7.76e-04

Pos logit contributions
 unison+0.022
 slices+0.022
 seventeen+0.021
 aroma+0.021
fires+0.021
Neg logit contributions
 wear-0.011
 Woo-0.010
 always-0.010
 bath-0.010
 skipping-0.010
Token seen
Token ID1775
Feature activation+1.04e-02

Pos logit contributions
 unison+0.082
 amaz+0.078
 seventeen+0.078
atively+0.076
fires+0.076
Neg logit contributions
 wear-0.070
 day-0.064
 bath-0.062
 important-0.061
 always-0.060
Token!
Token ID0
Feature activation-8.47e-03

Pos logit contributions
 wear+0.012
 Woo+0.011
 bath+0.011
 day+0.011
 skipping+0.011
Neg logit contributions
 seventeen-0.022
 unison-0.022
 amaz-0.021
 slices-0.021
 pulp-0.021
Token She
Token ID1375
Feature activation-2.04e-02

Pos logit contributions
 slices+0.014
 unison+0.014
 amaz+0.014
 seventeen+0.013
 ah+0.013
Neg logit contributions
 wear-0.013
burn-0.012
 important-0.012
 bath-0.012
 Woo-0.012
Token gasped
Token ID45236
Feature activation-3.64e-02

Pos logit contributions
 unison+0.040
 slices+0.039
 seventeen+0.039
 amaz+0.039
 aroma+0.038
Neg logit contributions
 wear-0.028
 Woo-0.025
 bath-0.025
 Mitt-0.023
 Lucky-0.023
Token in
Token ID287
Feature activation-2.92e-02

Pos logit contributions
 unison+0.081
 seventeen+0.081
 slices+0.080
 pulp+0.078
fires+0.078
Neg logit contributions
 wear-0.039
 Woo-0.036
 bath-0.033
 Mitt-0.033
 skipping-0.033
Token amaz
Token ID40642
Feature activation-1.24e-01

Pos logit contributions
fires+0.043
 seventeen+0.038
works+0.036
ymes+0.036
folk+0.036
Neg logit contributions
 wear-0.062
 skipping-0.057
 bath-0.056
 day-0.056
 Mitt-0.054
Tokenement
Token ID972
Feature activation-3.28e-02

Pos logit contributions
fires+0.170
 seventeen+0.170
 unison+0.169
 pulp+0.165
 slices+0.149
Neg logit contributions
 important-0.224
 wear-0.224
ie-0.222
 always-0.218
idy-0.209
Token,
Token ID11
Feature activation-1.10e-02

Pos logit contributions
 seventeen+0.072
 unison+0.072
 slices+0.069
 pulp+0.069
 amaz+0.069
Neg logit contributions
 wear-0.038
 skipping-0.031
 Woo-0.031
 bath-0.031
 day-0.031
Token and
Token ID290
Feature activation+1.21e-02

Pos logit contributions
 unison+0.024
 slices+0.024
 seventeen+0.024
fires+0.023
pter+0.023
Neg logit contributions
 wear-0.013
 Woo-0.011
 skipping-0.011
 bath-0.010
 Mitt-0.010
Token her
Token ID607
Feature activation+2.51e-02

Pos logit contributions
 wear+0.015
 Woo+0.014
 Mitt+0.013
 bath+0.013
 skipping+0.013
Neg logit contributions
 unison-0.026
 seventeen-0.025
 slices-0.025
fires-0.024
pter-0.024
Token tears
Token ID10953
Feature activation-2.78e-02

Pos logit contributions
 wear+0.032
 day+0.031
 bath+0.030
 important+0.029
 skipping+0.027
Neg logit contributions
 seventeen-0.052
fires-0.051
 unison-0.050
 slices-0.049
anish-0.049
Token!
Token ID0
Feature activation-6.05e-03

Pos logit contributions
 seventeen+0.013
 unison+0.013
 slices+0.012
 pulp+0.012
fires+0.012
Neg logit contributions
 wear-0.012
 bath-0.011
 important-0.011
 Woo-0.011
 day-0.011
Token They
Token ID1119
Feature activation-1.46e-02

Pos logit contributions
 slices+0.011
 seventeen+0.011
 unison+0.011
 aroma+0.011
 amaz+0.011
Neg logit contributions
 wear-0.008
 Woo-0.008
 bath-0.008
 Mitt-0.007
 Lucky-0.007
Token looked
Token ID3114
Feature activation+1.86e-03

Pos logit contributions
 seventeen+0.030
 slices+0.029
 aroma+0.028
 MacDonald+0.028
 unison+0.028
Neg logit contributions
 wear-0.021
 always-0.019
 also-0.017
 day-0.017
 bath-0.016
Token around
Token ID1088
Feature activation-3.55e-02

Pos logit contributions
 wear+0.002
 Woo+0.002
 bath+0.002
 important+0.002
 day+0.002
Neg logit contributions
 unison-0.004
 slices-0.004
 seventeen-0.004
pter-0.004
 pulp-0.004
Token in
Token ID287
Feature activation-2.32e-02

Pos logit contributions
 seventeen+0.095
bridge+0.092
 pulp+0.092
 unison+0.091
pter+0.090
Neg logit contributions
 wear-0.025
 day-0.025
 skipping-0.022
 always-0.022
 bath-0.022
Token amaz
Token ID40642
Feature activation-1.24e-01

Pos logit contributions
 seventeen+0.040
bridge+0.039
fires+0.038
 pulp+0.038
folk+0.037
Neg logit contributions
 wear-0.039
 day-0.038
 bath-0.037
 skipping-0.036
 important-0.034
Tokenement
Token ID972
Feature activation-4.43e-02

Pos logit contributions
 seventeen+0.165
 pulp+0.154
 slices+0.144
 unison+0.142
fires+0.141
Neg logit contributions
 wear-0.241
 important-0.234
 always-0.228
idy-0.223
ie-0.222
Token and
Token ID290
Feature activation+6.07e-03

Pos logit contributions
 seventeen+0.109
 unison+0.104
 slices+0.104
 pulp+0.103
bridge+0.102
Neg logit contributions
 wear-0.041
 skipping-0.034
 day-0.034
 bath-0.033
 always-0.032
Token quickly
Token ID2952
Feature activation-9.53e-03

Pos logit contributions
 wear+0.008
 always+0.007
 day+0.007
 skipping+0.007
 Lucky+0.007
Neg logit contributions
 seventeen-0.013
 slices-0.013
 unison-0.013
anish-0.012
bridge-0.012
Token closed
Token ID4838
Feature activation+1.46e-02

Pos logit contributions
 seventeen+0.019
 unison+0.019
 slices+0.019
anish+0.019
fires+0.019
Neg logit contributions
 wear-0.013
 bath-0.011
 always-0.010
 Woo-0.010
 day-0.010
Token the
Token ID262
Feature activation-3.21e-02

Pos logit contributions
 wear+0.016
 Woo+0.015
 bath+0.014
 skipping+0.013
 Lucky+0.013
Neg logit contributions
 seventeen-0.033
 slices-0.032
 unison-0.031
fires-0.031
 pulp-0.031
Token curtains
Token ID41160
Feature activation-2.93e-02

Pos logit contributions
 seventeen+0.060
 slices+0.060
 unison+0.059
 pulp+0.057
fires+0.057
Neg logit contributions
 wear-0.056
 bath-0.056
 day-0.051
 important-0.050
 skipping-0.049
Token,
Token ID11
Feature activation-1.12e-02

Pos logit contributions
 seventeen+0.071
 unison+0.071
 pulp+0.069
 slices+0.068
fires+0.068
Neg logit contributions
 wear-0.027
 bath-0.024
 skipping-0.022
 Woo-0.022
 day-0.021
Token she
Token ID673
Feature activation-1.71e-02

Pos logit contributions
 slices+0.025
 unison+0.025
 amaz+0.025
 seconds+0.024
 seventeen+0.024
Neg logit contributions
 wear-0.011
 Woo-0.010
 bath-0.010
burn-0.009
 important-0.009
Token gasped
Token ID45236
Feature activation-3.77e-02

Pos logit contributions
 seventeen+0.031
 unison+0.031
 slices+0.030
 aroma+0.029
anish+0.029
Neg logit contributions
 wear-0.027
 bath-0.024
 stub-0.023
 always-0.023
 skipping-0.023
Token in
Token ID287
Feature activation-2.98e-02

Pos logit contributions
 seventeen+0.089
 unison+0.086
 slices+0.085
 pulp+0.084
pter+0.083
Neg logit contributions
 wear-0.038
 Woo-0.034
 bath-0.033
 skipping-0.032
 Mitt-0.032
Token amaz
Token ID40642
Feature activation-1.23e-01

Pos logit contributions
fires+0.042
 seventeen+0.042
 pulp+0.039
 slices+0.039
folk+0.039
Neg logit contributions
 wear-0.062
 bath-0.057
 skipping-0.057
 jog-0.056
 day-0.054
Tokenement
Token ID972
Feature activation-4.22e-02

Pos logit contributions
 seventeen+0.152
 pulp+0.139
 unison+0.137
fires+0.134
 slices+0.132
Neg logit contributions
 wear-0.262
 important-0.243
 always-0.239
 bath-0.239
ie-0.237
Token.
Token ID13
Feature activation-1.33e-02

Pos logit contributions
 seventeen+0.098
 unison+0.094
 slices+0.094
 pulp+0.093
anish+0.091
Neg logit contributions
 wear-0.045
 bath-0.038
 skipping-0.037
 Woo-0.036
 day-0.036
Token It
Token ID632
Feature activation+1.11e-05

Pos logit contributions
 amaz+0.022
 unison+0.022
 slices+0.022
 seventeen+0.022
 seconds+0.021
Neg logit contributions
 wear-0.021
 Woo-0.020
 bath-0.019
burn-0.019
 important-0.018
Token was
Token ID373
Feature activation-1.54e-02

Pos logit contributions
 wear+0.000
 bath+0.000
 always+0.000
 important+0.000
 day+0.000
Neg logit contributions
 slices-0.000
 seventeen-0.000
 unison-0.000
 pulp-0.000
pter-0.000
Token snow
Token ID6729
Feature activation+3.30e-02

Pos logit contributions
 unison+0.030
 slices+0.030
 amaz+0.030
 seventeen+0.030
 seconds+0.029
Neg logit contributions
 wear-0.021
 Woo-0.019
 bath-0.018
burn-0.017
 Lucky-0.017
Token looked
Token ID3114
Feature activation+2.59e-03

Pos logit contributions
 seventeen+0.031
 unison+0.031
 slices+0.030
 aroma+0.030
 amaz+0.029
Neg logit contributions
 wear-0.025
 bath-0.022
 Woo-0.022
 day-0.021
 skipping-0.021
Token at
Token ID379
Feature activation-3.06e-02

Pos logit contributions
 wear+0.003
 Woo+0.002
 bath+0.002
 important+0.002
 day+0.002
Neg logit contributions
 unison-0.006
 slices-0.006
 seventeen-0.006
 seconds-0.006
fires-0.006
Token the
Token ID262
Feature activation-1.63e-02

Pos logit contributions
 seventeen+0.074
fires+0.071
 slices+0.071
 unison+0.071
 aroma+0.070
Neg logit contributions
 wear-0.030
 day-0.028
 Woo-0.026
 bath-0.026
 Mitt-0.025
Token rainbow
Token ID27223
Feature activation+2.85e-03

Pos logit contributions
 unison+0.033
 seventeen+0.033
 slices+0.032
pter+0.032
fires+0.031
Neg logit contributions
 day-0.022
 bath-0.021
 wear-0.020
 important-0.019
 always-0.018
Token in
Token ID287
Feature activation-2.34e-02

Pos logit contributions
 wear+0.003
 bath+0.003
 Woo+0.003
 day+0.003
 skipping+0.003
Neg logit contributions
 unison-0.006
 seventeen-0.006
 slices-0.006
 amaz-0.006
 seconds-0.006
Token amaz
Token ID40642
Feature activation-1.23e-01

Pos logit contributions
 seventeen+0.060
fires+0.059
bridge+0.058
pter+0.058
edly+0.057
Neg logit contributions
 wear-0.019
 day-0.017
 bath-0.017
 Woo-0.015
 skipping-0.015
Tokenement
Token ID972
Feature activation-4.01e-02

Pos logit contributions
 seventeen+0.156
 pulp+0.145
 unison+0.142
fires+0.140
 slices+0.132
Neg logit contributions
 wear-0.245
 bath-0.233
 day-0.232
 important-0.231
ie-0.229
Token and
Token ID290
Feature activation+5.32e-03

Pos logit contributions
 seventeen+0.093
 unison+0.090
 slices+0.089
 pulp+0.088
 amaz+0.088
Neg logit contributions
 wear-0.042
 day-0.036
 bath-0.035
 skipping-0.034
 Woo-0.033
Token laughed
Token ID13818
Feature activation-1.63e-02

Pos logit contributions
 wear+0.007
 always+0.006
 day+0.006
 skipping+0.006
 also+0.006
Neg logit contributions
bridge-0.012
 seventeen-0.012
 slices-0.011
 unison-0.011
anish-0.011
Token with
Token ID351
Feature activation-2.73e-02

Pos logit contributions
 seventeen+0.039
 pulp+0.038
 slices+0.038
pter+0.037
 unison+0.037
Neg logit contributions
 wear-0.016
 Woo-0.014
 bath-0.014
 important-0.014
 day-0.013
Token joy
Token ID8716
Feature activation-5.06e-02

Pos logit contributions
fires+0.049
pter+0.047
 seventeen+0.047
 pulp+0.045
boards+0.045
Neg logit contributions
 wear-0.047
 day-0.044
 bath-0.042
 skipping-0.041
 important-0.041
Token looked
Token ID3114
Feature activation+2.59e-03

Pos logit contributions
 seventeen+0.031
 unison+0.031
 slices+0.030
 aroma+0.030
 amaz+0.029
Neg logit contributions
 wear-0.025
 bath-0.022
 Woo-0.022
 day-0.021
 skipping-0.021
Token at
Token ID379
Feature activation-3.06e-02

Pos logit contributions
 wear+0.003
 Woo+0.002
 bath+0.002
 important+0.002
 day+0.002
Neg logit contributions
 unison-0.006
 slices-0.006
 seventeen-0.006
 seconds-0.006
fires-0.006
Token the
Token ID262
Feature activation-1.63e-02

Pos logit contributions
 seventeen+0.074
fires+0.071
 slices+0.071
 unison+0.071
 aroma+0.070
Neg logit contributions
 wear-0.030
 day-0.028
 Woo-0.026
 bath-0.026
 Mitt-0.025
Token rainbow
Token ID27223
Feature activation+2.85e-03

Pos logit contributions
 unison+0.033
 seventeen+0.033
 slices+0.032
pter+0.032
fires+0.031
Neg logit contributions
 day-0.022
 bath-0.021
 wear-0.020
 important-0.019
 always-0.018
Token in
Token ID287
Feature activation-2.34e-02

Pos logit contributions
 wear+0.003
 bath+0.003
 Woo+0.003
 day+0.003
 skipping+0.003
Neg logit contributions
 unison-0.006
 seventeen-0.006
 slices-0.006
 amaz-0.006
 seconds-0.006
Token amaz
Token ID40642
Feature activation-1.23e-01

Pos logit contributions
 seventeen+0.060
fires+0.059
bridge+0.058
pter+0.058
edly+0.057
Neg logit contributions
 wear-0.019
 day-0.017
 bath-0.017
 Woo-0.015
 skipping-0.015
Tokenement
Token ID972
Feature activation-4.01e-02

Pos logit contributions
 seventeen+0.156
 pulp+0.145
 unison+0.142
fires+0.140
 slices+0.132
Neg logit contributions
 wear-0.245
 bath-0.233
 day-0.232
 important-0.231
ie-0.229
Token and
Token ID290
Feature activation+5.32e-03

Pos logit contributions
 seventeen+0.093
 unison+0.090
 slices+0.089
 pulp+0.088
 amaz+0.088
Neg logit contributions
 wear-0.042
 day-0.036
 bath-0.035
 skipping-0.034
 Woo-0.033
Token laughed
Token ID13818
Feature activation-1.63e-02

Pos logit contributions
 wear+0.007
 always+0.006
 day+0.006
 skipping+0.006
 also+0.006
Neg logit contributions
bridge-0.012
 seventeen-0.012
 slices-0.011
 unison-0.011
anish-0.011
Token with
Token ID351
Feature activation-2.73e-02

Pos logit contributions
 seventeen+0.039
 pulp+0.038
 slices+0.038
pter+0.037
 unison+0.037
Neg logit contributions
 wear-0.016
 Woo-0.014
 bath-0.014
 important-0.014
 day-0.013
Token joy
Token ID8716
Feature activation-5.06e-02

Pos logit contributions
fires+0.049
pter+0.047
 seventeen+0.047
 pulp+0.045
boards+0.045
Neg logit contributions
 wear-0.047
 day-0.044
 bath-0.042
 skipping-0.041
 important-0.041
Token.
Token ID13
Feature activation+1.61e-03

Pos logit contributions
 seventeen+0.121
 pulp+0.120
 slices+0.118
 unison+0.116
 amaz+0.113
Neg logit contributions
 wear-0.050
 Woo-0.045
 day-0.044
 important-0.042
 bath-0.042
Token Tiger
Token ID17030
Feature activation+9.36e-03

Pos logit contributions
 wear+0.002
 Woo+0.002
 bath+0.002
 Mitt+0.002
 Lucky+0.002
Neg logit contributions
 slices-0.003
 unison-0.003
 seventeen-0.003
 aroma-0.003
 amaz-0.003
Token looked
Token ID3114
Feature activation+6.20e-03

Pos logit contributions
 wear+0.013
 Woo+0.012
 bath+0.011
 Lucky+0.011
 Mitt+0.011
Neg logit contributions
 slices-0.018
 unison-0.018
 seventeen-0.018
 amaz-0.018
 pulp-0.017
Token around
Token ID1088
Feature activation-3.57e-02

Pos logit contributions
 wear+0.006
 Woo+0.005
 bath+0.005
 important+0.005
 day+0.005
Neg logit contributions
 slices-0.015
 unison-0.015
 seventeen-0.015
 pulp-0.014
 seconds-0.014
Token in
Token ID287
Feature activation-1.87e-02

Pos logit contributions
 seventeen+0.096
 pulp+0.096
 slices+0.093
 unison+0.092
bridge+0.091
Neg logit contributions
 day-0.025
 wear-0.025
 skipping-0.022
 always-0.021
 bath-0.021
Token amaz
Token ID40642
Feature activation-1.23e-01

Pos logit contributions
 seventeen+0.031
 pulp+0.031
fires+0.030
anish+0.029
 slices+0.029
Neg logit contributions
 wear-0.033
 day-0.031
 bath-0.031
 skipping-0.031
 jog-0.030
Tokenement
Token ID972
Feature activation-3.69e-02

Pos logit contributions
 pulp+0.169
 seventeen+0.169
 slices+0.155
 unison+0.150
fires+0.147
Neg logit contributions
 wear-0.226
 important-0.223
 always-0.220
ie-0.214
 day-0.210
Token and
Token ID290
Feature activation+1.57e-02

Pos logit contributions
 seventeen+0.087
 unison+0.085
 slices+0.085
 pulp+0.084
 aroma+0.082
Neg logit contributions
 wear-0.036
 day-0.030
 bath-0.030
 skipping-0.030
 Woo-0.029
Token he
Token ID339
Feature activation-1.20e-02

Pos logit contributions
 wear+0.021
 Woo+0.019
 day+0.018
 Lucky+0.018
 bath+0.018
Neg logit contributions
 unison-0.032
 slices-0.032
 seventeen-0.031
 pulp-0.030
anish-0.030
Token knew
Token ID2993
Feature activation-3.35e-02

Pos logit contributions
 seventeen+0.022
 slices+0.022
 unison+0.022
 aroma+0.021
 pulp+0.021
Neg logit contributions
 wear-0.018
 Woo-0.016
 bath-0.016
 always-0.015
 Lucky-0.015
Token he
Token ID339
Feature activation-6.68e-03

Pos logit contributions
 amaz+0.061
 unison+0.060
 seconds+0.060
 slices+0.059
fires+0.058
Neg logit contributions
 wear-0.048
 Woo-0.046
 bath-0.045
burn-0.044
 Mitt-0.042
Token ice
Token ID4771
Feature activation+1.53e-02

Pos logit contributions
 unison+0.026
 slices+0.025
 seventeen+0.025
fires+0.024
 amaz+0.024
Neg logit contributions
 wear-0.016
 bath-0.015
 Woo-0.015
 day-0.014
 important-0.014
Token.
Token ID13
Feature activation-8.43e-03

Pos logit contributions
 wear+0.025
 Woo+0.023
 bath+0.023
 day+0.022
 important+0.022
Neg logit contributions
 unison-0.025
 seventeen-0.025
 amaz-0.025
 slices-0.025
 seconds-0.024
Token They
Token ID1119
Feature activation-1.47e-02

Pos logit contributions
pter+0.017
 aroma+0.017
 seventeen+0.017
 slices+0.017
bridge+0.016
Neg logit contributions
 bath-0.010
 Lucky-0.010
 wear-0.010
 Woo-0.010
 D-0.010
Token stared
Token ID18484
Feature activation+8.17e-03

Pos logit contributions
 unison+0.026
 seventeen+0.026
 slices+0.025
 aroma+0.025
 amaz+0.025
Neg logit contributions
 wear-0.024
 Woo-0.021
 bath-0.021
 Mitt-0.020
 skipping-0.020
Token in
Token ID287
Feature activation-2.22e-02

Pos logit contributions
 wear+0.009
 Woo+0.008
 bath+0.008
 skipping+0.008
 important+0.008
Neg logit contributions
 unison-0.018
 seventeen-0.018
 slices-0.018
 pulp-0.017
 aroma-0.017
Token amaz
Token ID40642
Feature activation-1.23e-01

Pos logit contributions
fires+0.043
bridge+0.043
 seventeen+0.042
anish+0.042
 pulp+0.042
Neg logit contributions
 wear-0.032
 skipping-0.030
 bath-0.030
 day-0.029
 Woo-0.028
Tokenement
Token ID972
Feature activation-4.87e-02

Pos logit contributions
 seventeen+0.167
 pulp+0.165
 unison+0.154
fires+0.150
 slices+0.149
Neg logit contributions
 wear-0.231
 important-0.223
ie-0.217
 always-0.212
idy-0.212
Token.
Token ID13
Feature activation-1.15e-02

Pos logit contributions
 seventeen+0.117
 pulp+0.112
 unison+0.112
 slices+0.112
 amaz+0.110
Neg logit contributions
 wear-0.048
 day-0.041
 bath-0.039
 skipping-0.038
 important-0.037
Token They
Token ID1119
Feature activation-1.64e-02

Pos logit contributions
pter+0.025
 aroma+0.024
 seventeen+0.024
 slices+0.024
ymes+0.024
Neg logit contributions
 bath-0.012
 Lucky-0.012
 wear-0.012
 Woo-0.012
 Mitt-0.012
Token wanted
Token ID2227
Feature activation-2.93e-03

Pos logit contributions
 seventeen+0.029
 slices+0.029
 unison+0.029
fires+0.028
 aroma+0.028
Neg logit contributions
 wear-0.026
 Woo-0.023
 bath-0.022
 always-0.022
 skipping-0.022
Token to
Token ID284
Feature activation-7.35e-03

Pos logit contributions
 unison+0.006
 slices+0.006
 seventeen+0.006
 amaz+0.006
 seconds+0.006
Neg logit contributions
 wear-0.003
 Woo-0.003
 bath-0.003
 Mitt-0.003
 Lucky-0.003
Token She
Token ID1375
Feature activation-1.71e-02

Pos logit contributions
 slices+0.024
 unison+0.024
 seventeen+0.024
 amaz+0.023
 aroma+0.023
Neg logit contributions
 wear-0.015
 Woo-0.014
 bath-0.014
 Mitt-0.013
 day-0.013
Token opened
Token ID4721
Feature activation+2.28e-03

Pos logit contributions
 slices+0.033
 seventeen+0.032
 unison+0.032
 aroma+0.031
 pulp+0.031
Neg logit contributions
 wear-0.024
 bath-0.021
 Woo-0.021
 day-0.020
 important-0.020
Token her
Token ID607
Feature activation-1.44e-02

Pos logit contributions
 wear+0.002
 Woo+0.002
 bath+0.002
 skipping+0.002
 day+0.001
Neg logit contributions
 seventeen-0.006
 unison-0.006
fires-0.006
 slices-0.006
 pulp-0.005
Token mouth
Token ID5422
Feature activation-4.91e-03

Pos logit contributions
 seventeen+0.016
 slices+0.015
 unison+0.015
fires+0.015
 pulp+0.014
Neg logit contributions
 wear-0.033
 bath-0.032
 skipping-0.030
 day-0.030
 important-0.029
Token in
Token ID287
Feature activation-4.10e-02

Pos logit contributions
 unison+0.010
 slices+0.010
 seventeen+0.010
 amaz+0.010
 pulp+0.010
Neg logit contributions
 wear-0.006
 Woo-0.005
 bath-0.005
 Mitt-0.005
 skipping-0.005
Token amaz
Token ID40642
Feature activation-1.23e-01

Pos logit contributions
fires+0.099
 seventeen+0.098
 pulp+0.095
pter+0.093
folk+0.093
Neg logit contributions
 wear-0.044
 bath-0.036
 skipping-0.036
 day-0.035
 Woo-0.032
Tokenement
Token ID972
Feature activation-4.08e-02

Pos logit contributions
 seventeen+0.147
fires+0.139
 pulp+0.138
 unison+0.136
 slices+0.131
Neg logit contributions
 wear-0.260
 important-0.238
 bath-0.238
 skipping-0.236
 always-0.234
Token.
Token ID13
Feature activation-1.87e-02

Pos logit contributions
 seventeen+0.087
 unison+0.086
 slices+0.086
 pulp+0.084
 seconds+0.084
Neg logit contributions
 wear-0.049
 bath-0.042
 Woo-0.041
 skipping-0.040
 day-0.040
Token She
Token ID1375
Feature activation-2.25e-02

Pos logit contributions
 slices+0.033
 unison+0.033
 seventeen+0.033
 amaz+0.032
 aroma+0.032
Neg logit contributions
 wear-0.028
 Woo-0.026
 bath-0.026
 Mitt-0.024
 skipping-0.024
Token had
Token ID550
Feature activation-1.11e-02

Pos logit contributions
 slices+0.043
 seventeen+0.042
 unison+0.042
fires+0.041
 aroma+0.041
Neg logit contributions
 wear-0.033
 bath-0.028
 always-0.028
 skipping-0.027
 Woo-0.027
Token never
Token ID1239
Feature activation-1.48e-03

Pos logit contributions
 unison+0.023
 seventeen+0.023
 slices+0.023
fires+0.023
 aroma+0.023
Neg logit contributions
 wear-0.014
 always-0.012
 bath-0.012
 Woo-0.012
 skipping-0.012
Token to
Token ID284
Feature activation+8.35e-03

Pos logit contributions
 wear+0.007
 Woo+0.006
burn+0.006
ibi+0.006
 stub+0.006
Neg logit contributions
 seconds-0.009
 slices-0.009
fires-0.008
 unison-0.008
 amaz-0.008
Token be
Token ID307
Feature activation+2.95e-03

Pos logit contributions
ip+0.012
 Woo+0.012
scar+0.011
 Mitt+0.011
ibi+0.011
Neg logit contributions
 unison-0.014
 click-0.013
 amaz-0.013
 seconds-0.013
 aroma-0.013
Token careful
Token ID8161
Feature activation+3.72e-02

Pos logit contributions
 wear+0.004
 bath+0.004
 Woo+0.004
ibi+0.004
 Lucky+0.004
Neg logit contributions
 seconds-0.005
 slices-0.005
fires-0.005
 unison-0.005
 pulp-0.005
Token because
Token ID780
Feature activation+4.57e-02

Pos logit contributions
 Woo+0.050
 wear+0.049
 bath+0.047
 Lucky+0.045
opsy+0.044
Neg logit contributions
 slices-0.069
fires-0.068
 seconds-0.066
 unison-0.065
pter-0.065
Token his
Token ID465
Feature activation+3.82e-02

Pos logit contributions
ongo+0.081
 wear+0.080
ibi+0.079
burn+0.078
opsy+0.077
Neg logit contributions
 slices-0.057
 seconds-0.057
 lava-0.057
 statues-0.056
 pulp-0.056
Token wings
Token ID12098
Feature activation+6.93e-02

Pos logit contributions
 wear+0.049
 Woo+0.048
 Lucky+0.043
 Mitt+0.042
 bath+0.042
Neg logit contributions
 slices-0.074
 pulp-0.073
 amaz-0.073
 seconds-0.072
 unison-0.072
Token were
Token ID547
Feature activation-1.49e-02

Pos logit contributions
 wear+0.130
 Woo+0.121
 bath+0.120
 day+0.114
 important+0.114
Neg logit contributions
 unison-0.099
 slices-0.098
 seventeen-0.097
 amaz-0.096
 seconds-0.094
Token fragile
Token ID21049
Feature activation+3.51e-02

Pos logit contributions
 slices+0.027
 seconds+0.027
 seventeen+0.026
 pulp+0.026
 aroma+0.025
Neg logit contributions
 wear-0.020
 Woo-0.019
 bath-0.019
ibi-0.018
scar-0.018
Token and
Token ID290
Feature activation+2.12e-02

Pos logit contributions
 wear+0.051
 Woo+0.048
 bath+0.046
 Mitt+0.044
burn+0.044
Neg logit contributions
 slices-0.063
 unison-0.062
 seconds-0.061
 aroma-0.060
 amaz-0.060
Token could
Token ID714
Feature activation+3.77e-02

Pos logit contributions
 wear+0.027
 Woo+0.026
 bath+0.025
burn+0.024
 skipping+0.023
Neg logit contributions
 slices-0.040
 seventeen-0.040
 amaz-0.039
 seconds-0.039
 unison-0.039
Token break
Token ID2270
Feature activation+3.33e-02

Pos logit contributions
 Woo+0.047
 wear+0.044
scar+0.044
 bath+0.044
ido+0.043
Neg logit contributions
 slices-0.069
 seventeen-0.068
 seconds-0.067
 pulp-0.066
 unison-0.066
Token winning
Token ID5442
Feature activation-6.11e-04

Pos logit contributions
 wear+0.048
 bath+0.045
 Woo+0.044
opsy+0.042
 Mitt+0.041
Neg logit contributions
 unison-0.074
 slices-0.074
 seconds-0.073
 amaz-0.073
 seventeen-0.070
Token.
Token ID13
Feature activation+1.43e-03

Pos logit contributions
 seventeen+0.001
 slices+0.001
 pulp+0.001
 unison+0.001
 aroma+0.001
Neg logit contributions
 wear-0.001
 Woo-0.001
 bath-0.001
 important-0.001
 day-0.001
Token The
Token ID383
Feature activation+1.59e-02

Pos logit contributions
 wear+0.002
 Woo+0.002
 Mitt+0.001
 Lucky+0.001
 bath+0.001
Neg logit contributions
 aroma-0.003
 slices-0.003
 unison-0.003
 amaz-0.003
 seventeen-0.003
Token persistent
Token ID16218
Feature activation-4.48e-04

Pos logit contributions
 wear+0.020
 Woo+0.019
 bath+0.018
burn+0.017
 Mitt+0.017
Neg logit contributions
 unison-0.032
 slices-0.032
 seventeen-0.032
 amaz-0.031
 seconds-0.031
Token friend
Token ID1545
Feature activation+5.41e-03

Pos logit contributions
 unison+0.001
 slices+0.001
 seconds+0.001
 seventeen+0.001
 amaz+0.001
Neg logit contributions
 wear-0.000
 Woo-0.000
 bath-0.000
 Mitt-0.000
burn-0.000
Token tried
Token ID3088
Feature activation+5.52e-02

Pos logit contributions
 wear+0.008
 Woo+0.007
 bath+0.007
 Mitt+0.007
 Lucky+0.007
Neg logit contributions
 unison-0.010
 slices-0.010
 seventeen-0.010
 amaz-0.010
 seconds-0.010
Token their
Token ID511
Feature activation-3.44e-03

Pos logit contributions
 wear+0.080
opsy+0.075
 bath+0.073
 Woo+0.072
burn+0.072
Neg logit contributions
 slices-0.095
 amaz-0.094
 seconds-0.094
 unison-0.092
 seventeen-0.090
Token best
Token ID1266
Feature activation+3.79e-03

Pos logit contributions
 slices+0.007
 unison+0.007
 seconds+0.007
 amaz+0.007
 seventeen+0.007
Neg logit contributions
 wear-0.004
 Woo-0.004
burn-0.004
 bath-0.004
opsy-0.003
Token,
Token ID11
Feature activation-2.00e-03

Pos logit contributions
 wear+0.005
 Woo+0.005
 bath+0.005
 Mitt+0.004
burn+0.004
Neg logit contributions
 unison-0.007
 slices-0.007
 amaz-0.007
 seventeen-0.007
 seconds-0.007
Token but
Token ID475
Feature activation+1.11e-02

Pos logit contributions
 slices+0.003
 unison+0.003
 amaz+0.003
 seventeen+0.003
 seconds+0.003
Neg logit contributions
 wear-0.003
 Woo-0.003
 bath-0.003
burn-0.003
 Mitt-0.003
Token they
Token ID484
Feature activation-1.96e-02

Pos logit contributions
 wear+0.016
 Woo+0.015
 bath+0.015
burn+0.014
 Mitt+0.014
Neg logit contributions
 slices-0.020
 unison-0.020
 amaz-0.020
 seventeen-0.020
 seconds-0.020
Token He
Token ID679
Feature activation-1.77e-02

Pos logit contributions
 wear+0.012
 Woo+0.011
 bath+0.011
burn+0.011
 important+0.011
Neg logit contributions
 unison-0.015
 slices-0.015
 seventeen-0.015
 amaz-0.015
 seconds-0.014
Token felt
Token ID2936
Feature activation+1.18e-02

Pos logit contributions
 unison+0.029
 seconds+0.029
 slices+0.029
 amaz+0.028
 seventeen+0.028
Neg logit contributions
 wear-0.028
 Woo-0.027
 bath-0.026
burn-0.025
 Mitt-0.025
Token like
Token ID588
Feature activation-1.35e-02

Pos logit contributions
 wear+0.015
burn+0.014
 Woo+0.014
 bath+0.013
ibi+0.013
Neg logit contributions
 unison-0.023
 amaz-0.023
 seconds-0.022
 slices-0.022
 seventeen-0.022
Token he
Token ID339
Feature activation+6.13e-03

Pos logit contributions
 unison+0.029
 slices+0.028
 seventeen+0.028
 amaz+0.028
 aroma+0.027
Neg logit contributions
 wear-0.016
 Woo-0.015
 bath-0.014
 Mitt-0.013
 day-0.013
Token didn
Token ID1422
Feature activation-4.31e-03

Pos logit contributions
 wear+0.009
 Woo+0.009
 bath+0.009
burn+0.008
 Mitt+0.008
Neg logit contributions
 unison-0.011
 slices-0.010
 amaz-0.010
 seconds-0.010
fires-0.010
Token't
Token ID470
Feature activation+5.25e-02

Pos logit contributions
 seconds+0.006
 slices+0.005
 seventeen+0.005
oor+0.005
 thirteen+0.005
Neg logit contributions
ety-0.008
opsy-0.007
 wear-0.007
burn-0.007
 Woo-0.007
Token belong
Token ID5594
Feature activation+3.36e-03

Pos logit contributions
 Woo+0.083
burn+0.081
 bath+0.080
scar+0.079
opsy+0.078
Neg logit contributions
 seconds-0.080
fires-0.073
 slices-0.071
 amaz-0.071
 unison-0.071
Token.
Token ID13
Feature activation+1.32e-02

Pos logit contributions
 wear+0.004
 Woo+0.004
 bath+0.004
 Mitt+0.004
burn+0.004
Neg logit contributions
 slices-0.007
fires-0.006
 seconds-0.006
 unison-0.006
 amaz-0.006
Token
Token ID198
Feature activation+7.44e-03

Pos logit contributions
 wear+0.019
 Woo+0.018
 bath+0.017
burn+0.017
 skipping+0.016
Neg logit contributions
 unison-0.024
 slices-0.024
 amaz-0.023
 seventeen-0.023
 seconds-0.023
Token
Token ID198
Feature activation-6.72e-03

Pos logit contributions
 wear+0.012
burn+0.012
 Woo+0.011
 bath+0.011
 skipping+0.010
Neg logit contributions
 unison-0.012
 slices-0.012
 seconds-0.012
fires-0.011
 seventeen-0.011
TokenM
Token ID44
Feature activation-1.50e-02

Pos logit contributions
 unison+0.010
 slices+0.010
 seconds+0.010
 seventeen+0.009
fires+0.009
Neg logit contributions
 wear-0.012
 Woo-0.012
burn-0.011
 bath-0.011
 skipping-0.011
Token,
Token ID11
Feature activation+2.09e-03

Pos logit contributions
 slices+0.043
 amaz+0.043
 aroma+0.042
fires+0.041
 unison+0.041
Neg logit contributions
 wear-0.030
 Woo-0.030
 bath-0.027
burn-0.027
 Lucky-0.027
Token Lucy
Token ID22162
Feature activation+2.66e-02

Pos logit contributions
 wear+0.003
 Woo+0.002
 bath+0.002
 day+0.002
 Mitt+0.002
Neg logit contributions
 seventeen-0.004
 unison-0.004
 slices-0.004
 amaz-0.004
fires-0.004
Token took
Token ID1718
Feature activation-1.57e-02

Pos logit contributions
 Woo+0.037
 wear+0.037
 bath+0.035
burn+0.034
 important+0.033
Neg logit contributions
 slices-0.048
 amaz-0.046
 unison-0.046
 seconds-0.045
 aroma-0.045
Token out
Token ID503
Feature activation-3.65e-02

Pos logit contributions
 slices+0.031
 unison+0.030
 amaz+0.030
 aroma+0.030
 seconds+0.030
Neg logit contributions
 wear-0.020
 Woo-0.019
 bath-0.018
 important-0.017
 skipping-0.017
Token her
Token ID607
Feature activation+1.96e-02

Pos logit contributions
 slices+0.075
 unison+0.075
 amaz+0.073
 seventeen+0.073
 seconds+0.072
Neg logit contributions
 wear-0.045
 Woo-0.041
 bath-0.040
 Mitt-0.037
 Lucky-0.037
Token sewing
Token ID35356
Feature activation+4.83e-02

Pos logit contributions
 Woo+0.027
scar+0.027
ido+0.027
tto+0.026
burn+0.025
Neg logit contributions
 slices-0.038
 amaz-0.035
 seconds-0.033
 conf-0.033
 unison-0.033
Token machine
Token ID4572
Feature activation-1.52e-02

Pos logit contributions
 wear+0.080
 Woo+0.075
 bath+0.074
 Mitt+0.070
 Lucky+0.070
Neg logit contributions
 unison-0.079
 slices-0.078
 seventeen-0.077
 amaz-0.076
 aroma-0.075
Token.
Token ID13
Feature activation+2.87e-03

Pos logit contributions
 slices+0.031
 unison+0.030
 amaz+0.030
 seventeen+0.029
 aroma+0.029
Neg logit contributions
 wear-0.019
 Woo-0.018
 bath-0.017
 Mitt-0.016
 Lucky-0.016
Token She
Token ID1375
Feature activation-1.28e-02

Pos logit contributions
 wear+0.004
 Woo+0.004
 bath+0.003
 Mitt+0.003
 day+0.003
Neg logit contributions
 unison-0.006
 slices-0.006
 seventeen-0.006
 amaz-0.005
 aroma-0.005
Token carefully
Token ID7773
Feature activation-7.81e-03

Pos logit contributions
 slices+0.025
 unison+0.025
 amaz+0.024
 seconds+0.024
 seventeen+0.024
Neg logit contributions
 wear-0.016
 Woo-0.016
 bath-0.015
burn-0.015
 day-0.014
Token loaded
Token ID9639
Feature activation-2.75e-03

Pos logit contributions
 slices+0.015
 seconds+0.014
 amaz+0.014
 unison+0.014
 seventeen+0.014
Neg logit contributions
 Woo-0.010
 wear-0.010
 important-0.010
 day-0.010
 bath-0.010
Token for
Token ID329
Feature activation-4.11e-02

Pos logit contributions
 wear+0.010
 Woo+0.009
 bath+0.009
 day+0.009
 important+0.009
Neg logit contributions
 seventeen-0.022
 unison-0.022
 slices-0.022
 pulp-0.022
 amaz-0.022
Token you
Token ID345
Feature activation-2.46e-02

Pos logit contributions
 seventeen+0.080
 slices+0.080
 unison+0.079
 amaz+0.078
 aroma+0.078
Neg logit contributions
 wear-0.057
 Woo-0.053
 bath-0.052
 Mitt-0.049
 skipping-0.048
Token.
Token ID13
Feature activation+1.67e-02

Pos logit contributions
 unison+0.051
 slices+0.050
 seventeen+0.050
 amaz+0.050
 pulp+0.049
Neg logit contributions
 wear-0.031
 Woo-0.028
 bath-0.027
 day-0.025
 Mitt-0.025
Token You
Token ID921
Feature activation-5.70e-02

Pos logit contributions
 wear+0.032
 bath+0.030
 Woo+0.030
burn+0.029
 important+0.029
Neg logit contributions
 unison-0.022
 amaz-0.022
 seventeen-0.022
 seconds-0.021
 slices-0.021
Token don
Token ID836
Feature activation-2.32e-02

Pos logit contributions
 slices+0.100
 seventeen+0.099
 unison+0.097
 amaz+0.095
 pulp+0.095
Neg logit contributions
 wear-0.098
 bath-0.086
 Woo-0.084
 always-0.084
 Lucky-0.080
Token't
Token ID470
Feature activation+6.04e-02

Pos logit contributions
 slices+0.037
 unison+0.037
 seventeen+0.036
anish+0.034
folk+0.034
Neg logit contributions
 wear-0.036
 bath-0.033
 Woo-0.033
 day-0.033
opsy-0.033
Token have
Token ID423
Feature activation+1.95e-03

Pos logit contributions
 Woo+0.076
 wear+0.074
 bath+0.072
 Mitt+0.070
 skipping+0.070
Neg logit contributions
 unison-0.109
 seventeen-0.106
 aroma-0.105
 seconds-0.105
 amaz-0.104
Token to
Token ID284
Feature activation-1.39e-02

Pos logit contributions
 wear+0.002
 Woo+0.002
 bath+0.002
 Mitt+0.002
 Lucky+0.002
Neg logit contributions
 slices-0.004
 unison-0.004
 seventeen-0.004
 amaz-0.004
 seconds-0.004
Token be
Token ID307
Feature activation-7.49e-03

Pos logit contributions
 unison+0.025
 aroma+0.023
 amaz+0.023
 seconds+0.022
rs+0.022
Neg logit contributions
ip-0.019
scar-0.018
 Woo-0.018
 Lucky-0.017
 important-0.017
Token sad
Token ID6507
Feature activation+7.19e-03

Pos logit contributions
 unison+0.015
 slices+0.014
 seventeen+0.014
 amaz+0.014
 seconds+0.014
Neg logit contributions
 wear-0.010
 Woo-0.009
 bath-0.009
 Mitt-0.008
burn-0.008
Token or
Token ID393
Feature activation+1.59e-02

Pos logit contributions
 wear+0.010
 Woo+0.009
 bath+0.009
 Mitt+0.008
 important+0.008
Neg logit contributions
 unison-0.014
 slices-0.014
 seventeen-0.014
 amaz-0.014
 aroma-0.014
Token on
Token ID319
Feature activation+5.47e-03

Pos logit contributions
 wear+0.059
 Woo+0.059
ibi+0.059
ety+0.058
ongo+0.057
Neg logit contributions
 moments-0.073
anish-0.071
 slices-0.070
 seconds-0.070
 seventeen-0.068
Token,
Token ID11
Feature activation+6.26e-03

Pos logit contributions
 wear+0.008
burn+0.008
 Woo+0.008
ibi+0.008
 bath+0.007
Neg logit contributions
 slices-0.009
 seconds-0.009
 aroma-0.009
 moments-0.009
anish-0.008
Token Lily
Token ID20037
Feature activation+3.72e-02

Pos logit contributions
scar+0.008
ido+0.008
ongo+0.008
ibi+0.008
burn+0.008
Neg logit contributions
 slices-0.012
 aroma-0.011
 amaz-0.011
 ah-0.011
 pulp-0.011
Token always
Token ID1464
Feature activation+6.98e-03

Pos logit contributions
 Woo+0.055
 wear+0.054
 bath+0.053
ido+0.049
 Lucky+0.049
Neg logit contributions
 amaz-0.061
 seconds-0.061
 slices-0.060
 moments-0.058
 aroma-0.058
Token picked
Token ID6497
Feature activation+2.09e-02

Pos logit contributions
 wear+0.011
 Woo+0.010
 bath+0.010
 Lucky+0.009
 Mitt+0.009
Neg logit contributions
 amaz-0.012
 unison-0.012
 seconds-0.012
 slices-0.012
 seventeen-0.011
Token herbs
Token ID25411
Feature activation+6.78e-03

Pos logit contributions
 wear+0.024
 Woo+0.022
 bath+0.021
burn+0.019
 stub+0.019
Neg logit contributions
 slices-0.045
 amaz-0.043
 aroma-0.043
 pulp-0.042
 seconds-0.042
Token and
Token ID290
Feature activation+2.20e-02

Pos logit contributions
 wear+0.008
 Woo+0.007
 bath+0.007
 Mitt+0.007
 Lucky+0.006
Neg logit contributions
 slices-0.014
 unison-0.014
 seventeen-0.014
 amaz-0.014
 aroma-0.014
Token covered
Token ID5017
Feature activation+1.43e-02

Pos logit contributions
 wear+0.030
 Woo+0.028
 bath+0.027
 Mitt+0.025
 Lucky+0.025
Neg logit contributions
 slices-0.042
 unison-0.042
 amaz-0.041
 seventeen-0.041
 seconds-0.041
Token her
Token ID607
Feature activation+1.20e-02

Pos logit contributions
 wear+0.021
 Woo+0.019
 bath+0.019
 Mitt+0.018
 Lucky+0.018
Neg logit contributions
 unison-0.027
 slices-0.026
 seventeen-0.026
 amaz-0.026
 seconds-0.025
Token room
Token ID2119
Feature activation+1.10e-02

Pos logit contributions
 wear+0.016
 bath+0.015
 important+0.014
 Mitt+0.014
 Woo+0.014
Neg logit contributions
 seventeen-0.025
 unison-0.024
 seconds-0.023
folk-0.023
bridge-0.023
Token with
Token ID351
Feature activation-1.94e-02

Pos logit contributions
 wear+0.013
 bath+0.011
 Woo+0.011
 important+0.010
 day+0.010
Neg logit contributions
 unison-0.024
 seventeen-0.024
 slices-0.023
 pulp-0.023
 amaz-0.023
Token safe
Token ID3338
Feature activation+6.50e-03

Pos logit contributions
 wear+0.069
 Woo+0.064
 bath+0.062
 Mitt+0.057
 Lucky+0.057
Neg logit contributions
 unison-0.116
 slices-0.115
 seventeen-0.114
 amaz-0.113
 aroma-0.111
Token.
Token ID13
Feature activation+6.41e-04

Pos logit contributions
 wear+0.008
 Woo+0.008
 bath+0.007
 Mitt+0.007
 day+0.007
Neg logit contributions
 unison-0.013
 slices-0.013
 seventeen-0.013
 amaz-0.013
 aroma-0.013
Token She
Token ID1375
Feature activation-7.33e-03

Pos logit contributions
 wear+0.001
 bath+0.001
 Woo+0.001
 Mitt+0.001
 day+0.001
Neg logit contributions
 seventeen-0.001
 unison-0.001
 slices-0.001
 pulp-0.001
fires-0.001
Token quickly
Token ID2952
Feature activation+2.93e-03

Pos logit contributions
 seconds+0.012
 slices+0.012
 unison+0.012
 amaz+0.012
 gasped+0.011
Neg logit contributions
 Woo-0.011
 wear-0.011
burn-0.011
 bath-0.010
 skipping-0.010
Token grabbed
Token ID13176
Feature activation-2.47e-02

Pos logit contributions
 Woo+0.004
 wear+0.004
burn+0.004
 bath+0.004
 day+0.004
Neg logit contributions
 slices-0.005
 unison-0.005
 seconds-0.005
 amaz-0.005
 pulp-0.005
Token the
Token ID262
Feature activation-3.39e-03

Pos logit contributions
 unison+0.051
 seventeen+0.051
 slices+0.050
fires+0.049
 amaz+0.049
Neg logit contributions
 wear-0.032
 Woo-0.029
 bath-0.028
 Mitt-0.026
 day-0.026
Token laser
Token ID12855
Feature activation+2.82e-02

Pos logit contributions
 unison+0.008
 slices+0.008
 seventeen+0.007
 amaz+0.007
 seconds+0.007
Neg logit contributions
 wear-0.004
 Woo-0.003
 bath-0.003
 Mitt-0.003
 day-0.003
Token and
Token ID290
Feature activation+2.60e-03

Pos logit contributions
 wear+0.034
 Woo+0.031
 bath+0.030
 Mitt+0.028
 Lucky+0.028
Neg logit contributions
 unison-0.059
 slices-0.058
 seventeen-0.058
 amaz-0.057
 aroma-0.056
Token hid
Token ID24519
Feature activation+2.16e-02

Pos logit contributions
 wear+0.003
 Woo+0.003
 bath+0.003
 Mitt+0.003
 Lucky+0.003
Neg logit contributions
 unison-0.005
 slices-0.005
 seventeen-0.005
 amaz-0.005
 aroma-0.005
Token it
Token ID340
Feature activation-1.19e-02

Pos logit contributions
 wear+0.022
 Woo+0.019
 skipping+0.019
 day+0.018
 bath+0.017
Neg logit contributions
 seventeen-0.057
 unison-0.052
 aroma-0.049
teen-0.049
 pulp-0.049
Token away
Token ID1497
Feature activation-2.04e-02

Pos logit contributions
 slices+0.023
 unison+0.023
 seventeen+0.023
 amaz+0.023
 seconds+0.022
Neg logit contributions
 wear-0.016
 Woo-0.015
 bath-0.014
 Mitt-0.014
burn-0.013
Token know
Token ID760
Feature activation+1.73e-02

Pos logit contributions
 Woo+0.106
 wear+0.103
 bath+0.102
burn+0.099
 Mitt+0.098
Neg logit contributions
 seconds-0.114
 unison-0.112
 amaz-0.111
 aroma-0.111
 slices-0.109
Token,
Token ID11
Feature activation+1.03e-02

Pos logit contributions
 wear+0.023
 Woo+0.022
 bath+0.021
 Mitt+0.020
 Lucky+0.020
Neg logit contributions
 unison-0.034
 slices-0.033
 seventeen-0.033
 amaz-0.033
 aroma-0.032
Token Rover
Token ID36718
Feature activation+2.99e-02

Pos logit contributions
 wear+0.015
 Woo+0.014
 bath+0.014
burn+0.013
 day+0.013
Neg logit contributions
 unison-0.019
 slices-0.018
 amaz-0.018
 seventeen-0.018
 seconds-0.018
Token,"
Token ID553
Feature activation-3.28e-02

Pos logit contributions
 wear+0.042
 Woo+0.040
 bath+0.039
 Mitt+0.036
 skipping+0.036
Neg logit contributions
 unison-0.055
 slices-0.055
 seventeen-0.054
 amaz-0.054
 aroma-0.053
Token she
Token ID673
Feature activation-9.86e-03

Pos logit contributions
 unison+0.065
 amaz+0.064
 slices+0.064
 seconds+0.063
 aroma+0.061
Neg logit contributions
 wear-0.040
 bath-0.037
 Woo-0.037
burn-0.037
 important-0.035
Token said
Token ID531
Feature activation+6.71e-03

Pos logit contributions
 unison+0.017
 slices+0.017
 seventeen+0.017
 amaz+0.017
 seconds+0.017
Neg logit contributions
 wear-0.015
 Woo-0.014
 bath-0.014
burn-0.013
 Mitt-0.013
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
 wear+0.009
 Woo+0.008
 bath+0.008
 Mitt+0.008
 Lucky+0.007
Neg logit contributions
 unison-0.013
 slices-0.013
 seventeen-0.013
 amaz-0.013
 seconds-0.013
Token
Token ID198
Feature activation-3.64e-03

Pos logit contributions
 unison+0.029
 slices+0.029
 seventeen+0.028
 amaz+0.028
 seconds+0.028
Neg logit contributions
 wear-0.020
 Woo-0.019
 bath-0.018
 Mitt-0.017
 day-0.017
Token
Token ID198
Feature activation-1.20e-02

Pos logit contributions
 unison+0.006
 slices+0.006
 seconds+0.006
fires+0.005
 amaz+0.005
Neg logit contributions
 wear-0.006
burn-0.005
 bath-0.005
 important-0.005
 Woo-0.005
TokenThat
Token ID2504
Feature activation-3.76e-02

Pos logit contributions
 unison+0.019
 slices+0.019
 seventeen+0.018
 amaz+0.018
 seconds+0.018
Neg logit contributions
 wear-0.021
 bath-0.019
 Woo-0.019
 day-0.018
 important-0.018
Token night
Token ID1755
Feature activation-6.22e-03

Pos logit contributions
 amaz+0.077
 unison+0.076
 aroma+0.076
 slices+0.075
 seconds+0.074
Neg logit contributions
 wear-0.045
 Woo-0.044
 bath-0.040
 Mitt-0.040
 skipping-0.038
Token he
Token ID339
Feature activation-1.68e-02

Pos logit contributions
 wear+0.018
 Woo+0.016
 bath+0.016
burn+0.015
 skipping+0.015
Neg logit contributions
 slices-0.027
 unison-0.026
 seconds-0.026
 amaz-0.026
 seventeen-0.026
Token didn
Token ID1422
Feature activation-3.53e-03

Pos logit contributions
 seconds+0.025
 slices+0.024
 aroma+0.023
 unison+0.022
fires+0.022
Neg logit contributions
 Woo-0.029
 wear-0.028
 bath-0.027
 skipping-0.027
burn-0.027
Token't
Token ID470
Feature activation+6.30e-02

Pos logit contributions
 slices+0.004
 seventeen+0.004
 unison+0.004
 seconds+0.004
fires+0.004
Neg logit contributions
ety-0.006
opsy-0.006
 wear-0.006
ibi-0.006
 important-0.006
Token behave
Token ID17438
Feature activation-4.22e-03

Pos logit contributions
scar+0.100
opsy+0.097
tto+0.093
 Woo+0.093
 Lucky+0.092
Neg logit contributions
 aroma-0.090
 click-0.090
rs-0.088
fires-0.088
 seconds-0.086
Token,
Token ID11
Feature activation+8.45e-03

Pos logit contributions
 unison+0.008
 slices+0.008
fires+0.008
 seconds+0.007
 aroma+0.007
Neg logit contributions
 wear-0.006
 Woo-0.005
 bath-0.005
burn-0.005
 skipping-0.005
Token he
Token ID339
Feature activation+1.49e-03

Pos logit contributions
 wear+0.010
 Woo+0.009
 bath+0.009
burn+0.008
 Lucky+0.008
Neg logit contributions
 slices-0.017
 unison-0.017
 amaz-0.017
 seventeen-0.017
 seconds-0.017
Token wouldn
Token ID3636
Feature activation-5.42e-03

Pos logit contributions
 Woo+0.002
 bath+0.002
 skipping+0.002
 wear+0.002
burn+0.002
Neg logit contributions
 seconds-0.002
fires-0.002
 slices-0.002
 aroma-0.002
 unison-0.002
Token't
Token ID470
Feature activation+4.87e-02

Pos logit contributions
 ah+0.006
 seconds+0.005
 slices+0.005
als+0.005
 click+0.005
Neg logit contributions
 important-0.010
 day-0.010
opsy-0.009
ety-0.009
 wear-0.009
Token receive
Token ID3328
Feature activation+2.29e-03

Pos logit contributions
scar+0.076
opsy+0.076
ip+0.072
 Woo+0.071
tto+0.070
Neg logit contributions
 click-0.071
 aroma-0.066
 seconds-0.066
 faces-0.065
fires-0.064
Token any
Token ID597
Feature activation+5.29e-03

Pos logit contributions
 wear+0.003
 Woo+0.003
 bath+0.003
 Mitt+0.003
 important+0.003
Neg logit contributions
 unison-0.004
 slices-0.004
 seventeen-0.004
 amaz-0.004
fires-0.004
Token presents
Token ID10969
Feature activation-2.97e-02

Pos logit contributions
 wear+0.007
 bath+0.007
 Woo+0.007
 important+0.006
 day+0.006
Neg logit contributions
 unison-0.010
 seventeen-0.010
 slices-0.010
 amaz-0.010
fires-0.010
Token.
Token ID13
Feature activation+1.52e-02

Pos logit contributions
 Woo+0.044
 wear+0.043
ibi+0.041
opsy+0.040
 stub+0.040
Neg logit contributions
 slices-0.041
 aroma-0.034
 unison-0.034
pter-0.033
fires-0.032
Token Clara
Token ID27443
Feature activation+1.61e-02

Pos logit contributions
 wear+0.021
 Woo+0.020
 bath+0.019
 important+0.019
burn+0.018
Neg logit contributions
 unison-0.028
 slices-0.028
 amaz-0.028
 seventeen-0.027
 aroma-0.027
Token asked
Token ID1965
Feature activation+1.84e-02

Pos logit contributions
 wear+0.024
 Woo+0.023
 bath+0.022
burn+0.021
 Mitt+0.021
Neg logit contributions
 slices-0.028
 unison-0.028
 amaz-0.027
 seventeen-0.027
 seconds-0.027
Token her
Token ID607
Feature activation+9.98e-03

Pos logit contributions
 wear+0.020
 Woo+0.018
 bath+0.018
burn+0.017
 Lucky+0.016
Neg logit contributions
 slices-0.040
 unison-0.039
 amaz-0.039
 seconds-0.038
 aroma-0.038
Token mom
Token ID1995
Feature activation-3.44e-02

Pos logit contributions
 Woo+0.015
 wear+0.014
ained+0.014
scar+0.014
burn+0.013
Neg logit contributions
 slices-0.018
 amaz-0.018
 seconds-0.017
 unison-0.016
 aroma-0.016
Tokenmy
Token ID1820
Feature activation+1.75e-03

Pos logit contributions
 slices+0.076
 amaz+0.070
 aroma+0.070
 seventeen+0.070
pter+0.069
Neg logit contributions
 Woo-0.036
 stub-0.032
 wear-0.032
 bath-0.031
opsy-0.030
Token what
Token ID644
Feature activation-2.28e-02

Pos logit contributions
 Woo+0.002
 wear+0.002
 bath+0.002
burn+0.002
 stub+0.002
Neg logit contributions
 slices-0.003
 amaz-0.003
 seventeen-0.003
 aroma-0.003
teen-0.003
Token they
Token ID484
Feature activation-9.94e-03

Pos logit contributions
 slices+0.036
 statues+0.033
 conf+0.033
 seconds+0.032
 amaz+0.032
Neg logit contributions
 wear-0.035
 Woo-0.035
ongo-0.035
umper-0.034
burn-0.034
Token were
Token ID547
Feature activation-1.07e-02

Pos logit contributions
 slices+0.012
 unison+0.012
 amaz+0.012
 seventeen+0.012
 aroma+0.012
Neg logit contributions
 wear-0.020
 Woo-0.019
 bath-0.019
 Mitt-0.018
 Lucky-0.018
Token going
Token ID1016
Feature activation+9.32e-03

Pos logit contributions
 slices+0.022
 aroma+0.022
fires+0.021
 pulp+0.021
 statues+0.020
Neg logit contributions
 Woo-0.012
 Lucky-0.012
 wear-0.012
 bath-0.011
 Mitt-0.011
Token to
Token ID284
Feature activation-5.33e-04

Pos logit contributions
opsy+0.015
 Woo+0.014
scar+0.014
 stub+0.014
ibi+0.014
Neg logit contributions
 slices-0.014
fires-0.013
als-0.012
pter-0.012
anish-0.012
TokenAre
Token ID8491
Feature activation-7.03e-03

Pos logit contributions
 unison+0.013
 slices+0.012
 seventeen+0.012
 amaz+0.012
 seconds+0.012
Neg logit contributions
 wear-0.018
 bath-0.017
 Woo-0.017
 Lucky-0.017
 Mitt-0.016
Token you
Token ID345
Feature activation-7.15e-03

Pos logit contributions
 ah+0.008
 seconds+0.008
 thirteen+0.008
 seventeen+0.008
fires+0.008
Neg logit contributions
 wear-0.013
burn-0.013
 bath-0.013
iny-0.013
ibi-0.012
Token ready
Token ID3492
Feature activation-1.05e-02

Pos logit contributions
 unison+0.014
 amaz+0.014
 slices+0.014
 aroma+0.014
fires+0.013
Neg logit contributions
 wear-0.008
 Woo-0.008
 bath-0.008
 Lucky-0.007
 Mitt-0.007
Token for
Token ID329
Feature activation-3.26e-02

Pos logit contributions
 amaz+0.019
 unison+0.019
 seconds+0.019
 slices+0.019
teen+0.019
Neg logit contributions
 Woo-0.013
 wear-0.012
 important-0.012
 Mitt-0.012
burn-0.011
Token the
Token ID262
Feature activation+2.68e-02

Pos logit contributions
 unison+0.060
 seconds+0.060
 slices+0.059
 amaz+0.059
 seventeen+0.057
Neg logit contributions
 wear-0.044
 Woo-0.042
burn-0.040
 bath-0.040
 Mitt-0.039
Token meeting
Token ID3249
Feature activation-1.72e-02

Pos logit contributions
 wear+0.033
 Woo+0.031
burn+0.029
 bath+0.028
 Mitt+0.028
Neg logit contributions
 unison-0.053
 slices-0.053
 aroma-0.052
fires-0.052
 seconds-0.052
Token?
Token ID30
Feature activation+1.02e-02

Pos logit contributions
 slices+0.038
 unison+0.038
 amaz+0.037
 seventeen+0.037
 seconds+0.037
Neg logit contributions
 wear-0.017
 Woo-0.017
 bath-0.015
 Mitt-0.014
burn-0.014
Tokenâ
Token ID22940
Feature activation-4.13e-03

Pos logit contributions
 wear+0.017
 important+0.016
burn+0.016
 day+0.016
 bath+0.016
Neg logit contributions
 unison-0.016
 amaz-0.015
 slices-0.015
fires-0.014
 seventeen-0.014
Token€
Token ID26391
Feature activation+5.90e-03

Pos logit contributions
 unison+0.007
 seventeen+0.007
fires+0.007
 aroma+0.007
 amaz+0.007
Neg logit contributions
 wear-0.006
 Woo-0.006
 bath-0.006
 Mitt-0.005
burn-0.005
Token M
Token ID337
Feature activation+2.96e-02

Pos logit contributions
 wear+0.010
 Woo+0.009
 bath+0.009
 Mitt+0.009
 skipping+0.008
Neg logit contributions
 seventeen-0.010
 slices-0.010
 unison-0.010
 pulp-0.010
 aroma-0.010
Tokenaddy
Token ID13218
Feature activation+2.67e-02

Pos logit contributions
 Woo+0.040
 wear+0.039
 Nut+0.036
 bath+0.036
 Lucky+0.036
Neg logit contributions
 amaz-0.054
 unison-0.053
 seconds-0.053
 aroma-0.052
teen-0.052
Token with
Token ID351
Feature activation-1.73e-02

Pos logit contributions
 wear+0.043
 bath+0.040
 Woo+0.039
 skipping+0.038
 jog+0.038
Neg logit contributions
 slices-0.044
 unison-0.043
als-0.042
fires-0.041
pter-0.041
Token soft
Token ID2705
Feature activation+1.34e-02

Pos logit contributions
 slices+0.034
 unison+0.034
 seventeen+0.034
 amaz+0.034
 aroma+0.033
Neg logit contributions
 wear-0.022
 Woo-0.021
 bath-0.020
burn-0.019
 Mitt-0.019
Token fur
Token ID9230
Feature activation+5.47e-02

Pos logit contributions
 wear+0.020
 Woo+0.019
 bath+0.018
 Mitt+0.018
 important+0.018
Neg logit contributions
 slices-0.023
 unison-0.023
 seventeen-0.023
 amaz-0.023
 aroma-0.023
Token and
Token ID290
Feature activation+1.20e-02

Pos logit contributions
 wear+0.075
 Woo+0.068
 bath+0.067
 Mitt+0.062
 important+0.062
Neg logit contributions
 slices-0.105
 unison-0.104
 seventeen-0.102
 aroma-0.101
 amaz-0.100
Token big
Token ID1263
Feature activation-2.20e-02

Pos logit contributions
 wear+0.016
 Woo+0.015
 bath+0.015
burn+0.014
ido+0.014
Neg logit contributions
 slices-0.023
 amaz-0.022
 unison-0.022
 seconds-0.022
 seventeen-0.022
Token eyes
Token ID2951
Feature activation-1.39e-02

Pos logit contributions
fires+0.031
 unison+0.030
 seventeen+0.028
 slices+0.028
anish+0.028
Neg logit contributions
 wear-0.043
 bath-0.043
 Woo-0.040
 Mitt-0.040
 skipping-0.039
Token.
Token ID13
Feature activation+1.59e-02

Pos logit contributions
 slices+0.027
 unison+0.027
 seventeen+0.026
 amaz+0.026
 aroma+0.026
Neg logit contributions
 wear-0.019
 Woo-0.018
 bath-0.017
 Mitt-0.016
 Lucky-0.016
Token One
Token ID1881
Feature activation+2.67e-02

Pos logit contributions
 wear+0.023
burn+0.022
 Woo+0.021
 important+0.021
scar+0.021
Neg logit contributions
 slices-0.027
 unison-0.027
 amaz-0.026
 seventeen-0.026
teen-0.025
Token day
Token ID1110
Feature activation-2.53e-02

Pos logit contributions
 Woo+0.037
 Cle+0.033
 Barkley+0.031
 Buster+0.031
 Nut+0.030
Neg logit contributions
 moments-0.045
 amaz-0.045
 slices-0.045
 aroma-0.045
 slice-0.043
Token,
Token ID11
Feature activation-3.94e-03

Pos logit contributions
 slices+0.048
 unison+0.046
 seventeen+0.046
 seconds+0.046
 aroma+0.046
Neg logit contributions
 wear-0.033
 Woo-0.031
burn-0.029
 important-0.029
 bath-0.029
Token Lily
Token ID20037
Feature activation+3.41e-02

Pos logit contributions
 unison+0.009
 slices+0.009
 seventeen+0.009
 amaz+0.009
 aroma+0.009
Neg logit contributions
 wear-0.004
 Woo-0.003
 bath-0.003
 Mitt-0.003
 important-0.003
Token had
Token ID550
Feature activation-6.24e-03

Pos logit contributions
 unison+0.033
 slices+0.032
 seventeen+0.032
 amaz+0.032
 aroma+0.031
Neg logit contributions
 wear-0.029
 Woo-0.027
 bath-0.027
 Mitt-0.025
 Lucky-0.025
Token just
Token ID655
Feature activation-2.16e-02

Pos logit contributions
fires+0.013
 aroma+0.013
 unison+0.013
 seventeen+0.013
 slices+0.013
Neg logit contributions
 wear-0.007
 Woo-0.007
 bath-0.007
 always-0.007
 important-0.006
Token seen
Token ID1775
Feature activation+2.28e-02

Pos logit contributions
 slices+0.041
 unison+0.041
 seventeen+0.040
fires+0.040
 aroma+0.039
Neg logit contributions
 wear-0.031
 day-0.027
 bath-0.027
 Woo-0.027
 always-0.026
Token something
Token ID1223
Feature activation-2.79e-03

Pos logit contributions
 wear+0.026
 Woo+0.024
 bath+0.024
 day+0.023
 Mitt+0.022
Neg logit contributions
 seventeen-0.049
 unison-0.048
 slices-0.048
fires-0.047
 pulp-0.047
Token truly
Token ID4988
Feature activation-1.90e-02

Pos logit contributions
 unison+0.006
 slices+0.006
 amaz+0.006
 seventeen+0.006
 seconds+0.006
Neg logit contributions
 wear-0.003
 Woo-0.003
 bath-0.003
burn-0.003
 Mitt-0.003
Token magical
Token ID10883
Feature activation-1.57e-02

Pos logit contributions
 slices+0.043
 unison+0.043
 seventeen+0.043
 pulp+0.041
 amaz+0.041
Neg logit contributions
 wear-0.020
 important-0.018
 day-0.017
 bath-0.017
 Woo-0.017
Token.
Token ID13
Feature activation-5.08e-05

Pos logit contributions
 seventeen+0.034
 slices+0.033
 unison+0.033
 pulp+0.033
 amaz+0.032
Neg logit contributions
 wear-0.019
 day-0.017
 bath-0.016
 important-0.016
 Woo-0.016
Token<|endoftext|>
Token ID50256
Feature activation-4.59e-02

Pos logit contributions
 unison+0.000
 slices+0.000
 amaz+0.000
 seventeen+0.000
 seconds+0.000
Neg logit contributions
 wear-0.000
 Woo-0.000
 bath-0.000
burn-0.000
 important-0.000
TokenOnce
Token ID7454
Feature activation+2.45e-02

Pos logit contributions
 slices+0.078
 unison+0.078
 amaz+0.075
 seventeen+0.075
fires+0.074
Neg logit contributions
 wear-0.072
 Woo-0.067
 bath-0.065
 important-0.063
 Mitt-0.062
Token upon
Token ID2402
Feature activation-5.66e-02

Pos logit contributions
 Woo+0.040
 wear+0.039
burn+0.039
 bath+0.036
 Mitt+0.035
Neg logit contributions
 slices-0.037
 amaz-0.037
 unison-0.036
pter-0.035
 seconds-0.035
Token a
Token ID257
Feature activation+4.38e-02

Pos logit contributions
 unison+0.113
 slices+0.112
 seventeen+0.111
 amaz+0.110
 aroma+0.108
Neg logit contributions
 wear-0.073
 Woo-0.067
 bath-0.066
 Mitt-0.061
 Lucky-0.060
Token out
Token ID503
Feature activation-3.94e-02

Pos logit contributions
 unison+0.028
pter+0.027
 seventeen+0.027
fires+0.026
 slices+0.026
Neg logit contributions
 wear-0.013
 Mitt-0.012
 Woo-0.012
 bath-0.012
 Lucky-0.012
Token came
Token ID1625
Feature activation-1.39e-02

Pos logit contributions
 seventeen+0.074
 unison+0.074
 slices+0.074
 pulp+0.073
pter+0.072
Neg logit contributions
 wear-0.056
 bath-0.050
 day-0.048
 skipping-0.047
 always-0.047
Token a
Token ID257
Feature activation-1.38e-02

Pos logit contributions
 slices+0.026
 unison+0.026
 amaz+0.026
 seventeen+0.026
 seconds+0.025
Neg logit contributions
 wear-0.020
 Woo-0.018
 bath-0.018
 day-0.016
 Mitt-0.016
Token big
Token ID1263
Feature activation-4.23e-02

Pos logit contributions
pter+0.030
 unison+0.030
 seventeen+0.030
 slices+0.029
fires+0.029
Neg logit contributions
 bath-0.015
 wear-0.015
 day-0.013
 Woo-0.013
 important-0.013
Token,
Token ID11
Feature activation-1.04e-02

Pos logit contributions
fires+0.091
 unison+0.089
pter+0.089
 seventeen+0.088
 slices+0.088
Neg logit contributions
 wear-0.049
 bath-0.049
 day-0.046
 Woo-0.044
 Mitt-0.042
Token foolish
Token ID19538
Feature activation-1.52e-02

Pos logit contributions
 unison+0.022
 slices+0.022
 seventeen+0.022
 amaz+0.022
fires+0.022
Neg logit contributions
 wear-0.012
 Woo-0.011
 bath-0.011
 important-0.010
 Mitt-0.010
Token snake
Token ID17522
Feature activation+6.69e-03

Pos logit contributions
 unison+0.029
 slices+0.029
 seventeen+0.029
 amaz+0.028
fires+0.028
Neg logit contributions
 wear-0.021
 Woo-0.020
 bath-0.020
 day-0.018
 Mitt-0.018
Token!
Token ID0
Feature activation-1.98e-02

Pos logit contributions
 wear+0.009
 bath+0.008
 Woo+0.008
 skipping+0.008
 Mitt+0.008
Neg logit contributions
 seventeen-0.013
 unison-0.013
 slices-0.013
 amaz-0.013
 aroma-0.013
Token The
Token ID383
Feature activation+1.66e-03

Pos logit contributions
 unison+0.042
pter+0.041
 seventeen+0.041
 amaz+0.041
 aroma+0.041
Neg logit contributions
 Woo-0.024
 Mitt-0.023
 wear-0.022
 bath-0.022
 Lucky-0.022
Token snake
Token ID17522
Feature activation+2.24e-02

Pos logit contributions
 wear+0.002
 bath+0.002
 Woo+0.002
 day+0.002
 important+0.002
Neg logit contributions
 unison-0.003
 seventeen-0.003
 slices-0.003
 amaz-0.003
fires-0.003
Token was
Token ID373
Feature activation-1.90e-03

Pos logit contributions
 wear+0.028
 bath+0.025
 always+0.025
 Mitt+0.024
 skipping+0.024
Neg logit contributions
 unison-0.045
 seventeen-0.045
 slices-0.044
fires-0.044
 amaz-0.044
Token of
Token ID286
Feature activation+9.52e-03

Pos logit contributions
 slices+0.021
 unison+0.020
 seventeen+0.020
 amaz+0.020
 seconds+0.019
Neg logit contributions
 wear-0.013
 Woo-0.013
 bath-0.012
 Mitt-0.011
burn-0.011
Token the
Token ID262
Feature activation-2.54e-02

Pos logit contributions
 wear+0.010
 Woo+0.010
 bath+0.009
 Mitt+0.009
 day+0.009
Neg logit contributions
 unison-0.021
 seventeen-0.021
fires-0.021
 slices-0.020
 amaz-0.020
Token garden
Token ID11376
Feature activation+3.71e-03

Pos logit contributions
 slices+0.048
 unison+0.046
 seventeen+0.046
 amaz+0.046
 pulp+0.046
Neg logit contributions
 wear-0.036
 Woo-0.034
 bath-0.033
burn-0.031
 Mitt-0.031
Token.
Token ID13
Feature activation+1.19e-02

Pos logit contributions
 wear+0.004
 day+0.004
 bath+0.004
 Woo+0.004
 skipping+0.003
Neg logit contributions
 unison-0.008
 seventeen-0.008
 amaz-0.008
 aroma-0.008
 pulp-0.008
Token But
Token ID887
Feature activation+1.06e-02

Pos logit contributions
 wear+0.021
 Woo+0.020
 Mitt+0.020
 bath+0.019
 Lucky+0.019
Neg logit contributions
 slices-0.018
 unison-0.018
 aroma-0.018
 seventeen-0.017
 pulp-0.017
Token they
Token ID484
Feature activation-1.94e-02

Pos logit contributions
 wear+0.015
 Woo+0.014
 bath+0.014
 Mitt+0.013
 day+0.013
Neg logit contributions
 unison-0.020
 seventeen-0.020
 slices-0.020
 amaz-0.019
fires-0.019
Token are
Token ID389
Feature activation-4.08e-02

Pos logit contributions
 unison+0.034
 seventeen+0.033
 slices+0.033
 amaz+0.032
 seconds+0.032
Neg logit contributions
 wear-0.032
 bath-0.028
 Woo-0.028
 day-0.027
 always-0.027
Token too
Token ID1165
Feature activation+8.31e-03

Pos logit contributions
 slices+0.083
 unison+0.082
 seventeen+0.081
 amaz+0.081
 seconds+0.080
Neg logit contributions
 wear-0.051
 Woo-0.048
 bath-0.047
burn-0.043
 Mitt-0.043
Token high
Token ID1029
Feature activation+1.39e-03

Pos logit contributions
 wear+0.011
 Woo+0.010
 bath+0.010
burn+0.010
 Lucky+0.009
Neg logit contributions
 slices-0.017
 seconds-0.016
 pulp-0.016
 seventeen-0.016
 amaz-0.016
Token for
Token ID329
Feature activation-4.19e-02

Pos logit contributions
 wear+0.002
 Woo+0.002
 bath+0.001
 Mitt+0.001
 Lucky+0.001
Neg logit contributions
 unison-0.003
 slices-0.003
 seventeen-0.003
 amaz-0.003
 aroma-0.003
Token you
Token ID345
Feature activation-2.93e-02

Pos logit contributions
 unison+0.077
 seventeen+0.076
 amaz+0.075
 slices+0.075
fires+0.073
Neg logit contributions
 wear-0.062
 Woo-0.058
 bath-0.057
 Mitt-0.054
 skipping-0.053
Token went
Token ID1816
Feature activation+7.45e-03

Pos logit contributions
 unison+0.072
 slices+0.072
 seventeen+0.071
 amaz+0.070
 seconds+0.069
Neg logit contributions
 wear-0.057
 Woo-0.053
 bath-0.052
 Mitt-0.049
 Lucky-0.048
Token to
Token ID284
Feature activation-3.12e-02

Pos logit contributions
 wear+0.011
 Woo+0.010
opsy+0.010
scar+0.010
 Mitt+0.010
Neg logit contributions
 slices-0.012
fires-0.012
 amaz-0.011
 seconds-0.011
 unison-0.011
Token bed
Token ID3996
Feature activation-6.61e-03

Pos logit contributions
 amaz+0.065
 unison+0.064
 slices+0.063
 seconds+0.062
 seventeen+0.061
Neg logit contributions
 wear-0.036
 Woo-0.035
burn-0.032
 important-0.032
 bath-0.032
Token with
Token ID351
Feature activation-1.94e-02

Pos logit contributions
 unison+0.015
 seventeen+0.015
 pulp+0.015
 slices+0.015
 amaz+0.015
Neg logit contributions
 wear-0.007
 Woo-0.006
 bath-0.006
 day-0.006
 Mitt-0.005
Token a
Token ID257
Feature activation-1.25e-02

Pos logit contributions
 unison+0.042
 seventeen+0.042
 slices+0.042
fires+0.041
 aroma+0.041
Neg logit contributions
 wear-0.022
 bath-0.020
 Woo-0.020
 Mitt-0.018
 day-0.018
Token smile
Token ID8212
Feature activation-7.58e-02

Pos logit contributions
 unison+0.026
 slices+0.026
 seventeen+0.026
fires+0.026
 seconds+0.026
Neg logit contributions
 wear-0.015
 bath-0.014
 Woo-0.013
 day-0.012
 Mitt-0.012
Token on
Token ID319
Feature activation-2.30e-02

Pos logit contributions
 slices+0.159
 unison+0.158
 seventeen+0.156
 amaz+0.156
 aroma+0.155
Neg logit contributions
 wear-0.087
 Woo-0.082
 bath-0.077
 Mitt-0.074
 important-0.073
Token his
Token ID465
Feature activation-9.62e-04

Pos logit contributions
fires+0.060
 unison+0.059
 seventeen+0.059
 slices+0.059
 pulp+0.058
Neg logit contributions
 wear-0.019
 bath-0.015
 Woo-0.015
 Mitt-0.013
 day-0.013
Token face
Token ID1986
Feature activation-3.28e-02

Pos logit contributions
 seventeen+0.002
 slices+0.002
teen+0.002
fires+0.002
pter+0.002
Neg logit contributions
 wear-0.002
 bath-0.001
 important-0.001
 day-0.001
 Lucky-0.001
Token.
Token ID13
Feature activation-1.02e-02

Pos logit contributions
 unison+0.066
 slices+0.066
 seventeen+0.065
 amaz+0.065
 aroma+0.063
Neg logit contributions
 wear-0.041
 Woo-0.038
 bath-0.037
 Mitt-0.035
 day-0.034
Token<|endoftext|>
Token ID50256
Feature activation-4.45e-02

Pos logit contributions
 unison+0.019
 slices+0.019
 amaz+0.019
 seventeen+0.019
 seconds+0.018
Neg logit contributions
 wear-0.014
 Woo-0.013
 bath-0.013
burn-0.012
 important-0.012
Token rode
Token ID22075
Feature activation+3.58e-02

Pos logit contributions
 wear+0.010
 Woo+0.010
 bath+0.010
 important+0.009
opsy+0.009
Neg logit contributions
 slices-0.014
 amaz-0.014
 unison-0.014
 seconds-0.014
 seventeen-0.013
Token away
Token ID1497
Feature activation-4.59e-02

Pos logit contributions
 wear+0.040
 Woo+0.037
 bath+0.035
 day+0.034
 Lucky+0.033
Neg logit contributions
 unison-0.081
 pulp-0.080
 slices-0.080
 seventeen-0.080
 aroma-0.079
Token with
Token ID351
Feature activation-1.94e-02

Pos logit contributions
 seventeen+0.107
 unison+0.106
 pulp+0.105
 slices+0.104
 aroma+0.103
Neg logit contributions
 wear-0.049
 Woo-0.042
 bath-0.041
 day-0.041
 skipping-0.039
Token a
Token ID257
Feature activation-1.37e-02

Pos logit contributions
 unison+0.041
 slices+0.041
 seventeen+0.040
 amaz+0.040
 aroma+0.039
Neg logit contributions
 wear-0.023
 Woo-0.021
 bath-0.021
 Mitt-0.019
 Lucky-0.019
Token big
Token ID1263
Feature activation-3.60e-02

Pos logit contributions
 unison+0.028
 slices+0.028
 seventeen+0.027
 amaz+0.027
 aroma+0.027
Neg logit contributions
 wear-0.017
 Woo-0.016
 bath-0.016
 Mitt-0.015
 Lucky-0.014
Token smile
Token ID8212
Feature activation-7.96e-02

Pos logit contributions
 slices+0.064
fires+0.064
 unison+0.064
 seventeen+0.063
 seconds+0.061
Neg logit contributions
 wear-0.055
 bath-0.052
 Woo-0.050
 day-0.048
 skipping-0.047
Token.
Token ID13
Feature activation-5.61e-03

Pos logit contributions
 slices+0.164
 unison+0.163
 seventeen+0.160
 amaz+0.159
pter+0.158
Neg logit contributions
 wear-0.094
 Woo-0.088
 bath-0.084
 Mitt-0.081
 important-0.079
Token He
Token ID679
Feature activation-3.26e-02

Pos logit contributions
 unison+0.009
 amaz+0.009
 slices+0.009
 seconds+0.008
 seventeen+0.008
Neg logit contributions
 wear-0.010
burn-0.009
 bath-0.009
 Woo-0.009
 skipping-0.008
Token felt
Token ID2936
Feature activation+4.85e-03

Pos logit contributions
 unison+0.053
 amaz+0.052
 slices+0.052
 seconds+0.051
 seventeen+0.051
Neg logit contributions
 wear-0.052
 Woo-0.050
 bath-0.050
 Mitt-0.047
burn-0.047
Token happy
Token ID3772
Feature activation-5.69e-02

Pos logit contributions
 wear+0.006
burn+0.006
 Woo+0.006
 bath+0.006
 Mitt+0.006
Neg logit contributions
 amaz-0.009
 unison-0.009
 slices-0.009
 seconds-0.009
 seventeen-0.009
Token and
Token ID290
Feature activation+2.13e-02

Pos logit contributions
 seventeen+0.159
 unison+0.151
 pulp+0.148
teen+0.147
 aroma+0.147
Neg logit contributions
 wear-0.045
 day-0.041
 bath-0.038
 always-0.037
 skipping-0.037
Token ride
Token ID6594
Feature activation+3.21e-02

Pos logit contributions
 Woo+0.022
 wear+0.020
 important+0.020
scar+0.020
burn+0.020
Neg logit contributions
 amaz-0.041
 unison-0.039
 slices-0.038
 seconds-0.038
 ah-0.038
Token my
Token ID616
Feature activation+1.12e-02

Pos logit contributions
 wear+0.041
 Woo+0.038
 bath+0.036
 day+0.034
 Lucky+0.034
Neg logit contributions
 unison-0.068
 amaz-0.067
 seventeen-0.066
 slices-0.066
 pulp-0.065
Token bike
Token ID7161
Feature activation+1.01e-02

Pos logit contributions
 wear+0.014
 Woo+0.013
 bath+0.013
 Mitt+0.012
 Lucky+0.012
Neg logit contributions
 unison-0.023
 slices-0.023
 seventeen-0.022
 amaz-0.022
 aroma-0.022
Token now
Token ID783
Feature activation+2.33e-02

Pos logit contributions
 wear+0.011
 Woo+0.010
 bath+0.009
 Mitt+0.009
 Lucky+0.008
Neg logit contributions
 slices-0.022
 unison-0.022
 seventeen-0.022
 amaz-0.022
fires-0.022
Token?
Token ID30
Feature activation+1.14e-02

Pos logit contributions
 wear+0.026
 Woo+0.025
 Mitt+0.024
 bath+0.024
 Lucky+0.023
Neg logit contributions
 slices-0.046
 aroma-0.046
 amaz-0.046
 seventeen-0.045
 unison-0.045
Token Please
Token ID4222
Feature activation-7.83e-02

Pos logit contributions
 wear+0.022
 Woo+0.021
 bath+0.021
 Mitt+0.020
 day+0.020
Neg logit contributions
 unison-0.015
 slices-0.015
 seventeen-0.015
 amaz-0.015
 seconds-0.014
Token?"
Token ID1701
Feature activation-1.21e-02

Pos logit contributions
 unison+0.150
 amaz+0.146
 seconds+0.146
 slices+0.145
 seventeen+0.145
Neg logit contributions
 Woo-0.095
 wear-0.095
 bath-0.091
 important-0.088
 Mitt-0.086
Token
Token ID198
Feature activation-3.13e-03

Pos logit contributions
 unison+0.021
 slices+0.021
 seventeen+0.021
 amaz+0.021
 aroma+0.021
Neg logit contributions
 wear-0.018
 Woo-0.017
 bath-0.017
 Mitt-0.016
 Lucky-0.016
Token
Token ID198
Feature activation-1.26e-02

Pos logit contributions
 slices+0.006
 unison+0.005
 seconds+0.005
 amaz+0.005
 seventeen+0.005
Neg logit contributions
 wear-0.005
 Woo-0.004
burn-0.004
 important-0.004
 bath-0.004
TokenM
Token ID44
Feature activation-2.45e-02

Pos logit contributions
 unison+0.021
 slices+0.021
 seventeen+0.021
 amaz+0.020
 aroma+0.020
Neg logit contributions
 wear-0.021
 Woo-0.019
 bath-0.019
 Mitt-0.018
 Lucky-0.018
Tokenummy
Token ID13513
Feature activation-2.32e-02

Pos logit contributions
 slices+0.049
 unison+0.048
 aroma+0.047
 amaz+0.047
 seconds+0.047
Neg logit contributions
 wear-0.033
 Woo-0.032
 bath-0.028
 Mitt-0.028
burn-0.028
Token granted
Token ID7520
Feature activation+1.18e-02

Pos logit contributions
 wear+0.008
 Woo+0.007
 bath+0.007
burn+0.007
 Mitt+0.006
Neg logit contributions
 unison-0.011
 slices-0.011
 amaz-0.010
 seventeen-0.010
 seconds-0.010
Token!
Token ID0
Feature activation-1.23e-02

Pos logit contributions
 wear+0.015
 Woo+0.014
 bath+0.013
 Mitt+0.012
 Lucky+0.012
Neg logit contributions
 unison-0.024
 slices-0.024
 seventeen-0.023
 amaz-0.023
 aroma-0.023
Token The
Token ID383
Feature activation+7.09e-03

Pos logit contributions
 unison+0.022
 slices+0.022
 amaz+0.021
 seconds+0.021
 seventeen+0.021
Neg logit contributions
 wear-0.018
 bath-0.016
burn-0.016
 Woo-0.016
 important-0.016
Token star
Token ID3491
Feature activation+6.91e-03

Pos logit contributions
 wear+0.009
 Woo+0.008
 bath+0.008
 Mitt+0.008
 day+0.008
Neg logit contributions
 unison-0.014
 slices-0.014
 seventeen-0.014
 amaz-0.014
 aroma-0.014
Token shone
Token ID44193
Feature activation+1.98e-02

Pos logit contributions
 wear+0.009
 bath+0.008
 day+0.008
 Woo+0.007
 important+0.007
Neg logit contributions
 unison-0.014
 seventeen-0.014
 slices-0.014
 amaz-0.014
fires-0.013
Token brightly
Token ID35254
Feature activation-7.38e-02

Pos logit contributions
 wear+0.025
 important+0.024
 Woo+0.023
 always+0.023
 day+0.023
Neg logit contributions
 unison-0.041
 seventeen-0.040
 pulp-0.040
pter-0.040
 slices-0.039
Token and
Token ID290
Feature activation-5.02e-04

Pos logit contributions
 unison+0.180
 seventeen+0.177
 slices+0.176
 pulp+0.176
 amaz+0.172
Neg logit contributions
 wear-0.066
 day-0.059
 bath-0.053
 Woo-0.049
 important-0.049
Token lit
Token ID6578
Feature activation-2.98e-02

Pos logit contributions
 unison+0.001
 seventeen+0.001
 slices+0.001
pter+0.001
fires+0.001
Neg logit contributions
 wear-0.001
 Woo-0.001
 day-0.001
 bath-0.001
 Mitt-0.001
Token the
Token ID262
Feature activation-1.21e-02

Pos logit contributions
 slices+0.078
 unison+0.077
 seventeen+0.076
 pulp+0.076
fires+0.075
Neg logit contributions
 wear-0.021
 Woo-0.017
 bath-0.016
 important-0.016
 day-0.015
Token night
Token ID1755
Feature activation-8.44e-03

Pos logit contributions
 slices+0.022
 seventeen+0.022
 unison+0.022
 seconds+0.021
fires+0.021
Neg logit contributions
 wear-0.017
 bath-0.017
 day-0.016
 important-0.016
 Woo-0.015
Token sky
Token ID6766
Feature activation+8.54e-03

Pos logit contributions
 seventeen+0.017
 unison+0.017
 pulp+0.017
 slices+0.016
anish+0.016
Neg logit contributions
 wear-0.011
 day-0.011
 bath-0.011
 always-0.009
 important-0.009
Token.
Token ID13
Feature activation+1.61e-03

Pos logit contributions
 seventeen+0.121
 pulp+0.120
 slices+0.118
 unison+0.116
 amaz+0.113
Neg logit contributions
 wear-0.050
 Woo-0.045
 day-0.044
 important-0.042
 bath-0.042
Token Tiger
Token ID17030
Feature activation+9.36e-03

Pos logit contributions
 wear+0.002
 Woo+0.002
 bath+0.002
 Mitt+0.002
 Lucky+0.002
Neg logit contributions
 slices-0.003
 unison-0.003
 seventeen-0.003
 aroma-0.003
 amaz-0.003
Token looked
Token ID3114
Feature activation+6.20e-03

Pos logit contributions
 wear+0.013
 Woo+0.012
 bath+0.011
 Lucky+0.011
 Mitt+0.011
Neg logit contributions
 slices-0.018
 unison-0.018
 seventeen-0.018
 amaz-0.018
 pulp-0.017
Token around
Token ID1088
Feature activation-3.57e-02

Pos logit contributions
 wear+0.006
 Woo+0.005
 bath+0.005
 important+0.005
 day+0.005
Neg logit contributions
 slices-0.015
 unison-0.015
 seventeen-0.015
 pulp-0.014
 seconds-0.014
Token in
Token ID287
Feature activation-1.87e-02

Pos logit contributions
 seventeen+0.096
 pulp+0.096
 slices+0.093
 unison+0.092
bridge+0.091
Neg logit contributions
 day-0.025
 wear-0.025
 skipping-0.022
 always-0.021
 bath-0.021
Token amaz
Token ID40642
Feature activation-1.23e-01

Pos logit contributions
 seventeen+0.031
 pulp+0.031
fires+0.030
anish+0.029
 slices+0.029
Neg logit contributions
 wear-0.033
 day-0.031
 bath-0.031
 skipping-0.031
 jog-0.030
Tokenement
Token ID972
Feature activation-3.69e-02

Pos logit contributions
 pulp+0.169
 seventeen+0.169
 slices+0.155
 unison+0.150
fires+0.147
Neg logit contributions
 wear-0.226
 important-0.223
 always-0.220
ie-0.214
 day-0.210
Token and
Token ID290
Feature activation+1.57e-02

Pos logit contributions
 seventeen+0.087
 unison+0.085
 slices+0.085
 pulp+0.084
 aroma+0.082
Neg logit contributions
 wear-0.036
 day-0.030
 bath-0.030
 skipping-0.030
 Woo-0.029
Token he
Token ID339
Feature activation-1.20e-02

Pos logit contributions
 wear+0.021
 Woo+0.019
 day+0.018
 Lucky+0.018
 bath+0.018
Neg logit contributions
 unison-0.032
 slices-0.032
 seventeen-0.031
 pulp-0.030
anish-0.030
Token knew
Token ID2993
Feature activation-3.35e-02

Pos logit contributions
 seventeen+0.022
 slices+0.022
 unison+0.022
 aroma+0.021
 pulp+0.021
Neg logit contributions
 wear-0.018
 Woo-0.016
 bath-0.016
 always-0.015
 Lucky-0.015
Token he
Token ID339
Feature activation-6.68e-03

Pos logit contributions
 amaz+0.061
 unison+0.060
 seconds+0.060
 slices+0.059
fires+0.058
Neg logit contributions
 wear-0.048
 Woo-0.046
 bath-0.045
burn-0.044
 Mitt-0.042