TOP ACTIVATIONS
MAX = 6.022

amazed . He watched as Per c ival cut out two
. He watched as Per c ival cut out two shapes
They played catch and tug - of - war . The
hug and lots of up - downs to make it feel
playing a game of kick - ball . Lily was so
which tw irled and t - shirts that jumped . He
she stood up and tip - to ed out of the
play a game of tug - o - war .
catch and tug - of - war . The fox was
would always say ' thank - you ' to his toast
push - ups and pull - ups . He worked really
soft rug and even hand - fed the chickens her kept
jumping j acks and push - ups . Finally
over and get some ice - cream ! â So
out and collect some ice - cream . He went to
the yard and even zip - lined across the driveway .
" Let 's play tug - of - war !"
and could do more push - ups than most adults .
to read in her tree - house . One
They decided to play tug - of - war with it

MIN ACTIVATIONS
MIN = -5.251

had found the l ily pad again . Bobby told Freddy
to find the l ily pad . He searched and searched
big , beautiful l ily pad that he found in the
, you â ll always have your memories of
It became the happiest books he lf in the world !
before . This is O ll ie , the ostr ich
, we â ll mention it to the grown
key . She unlocked the pad lock and opened the door
back onto his l ily pad and stood there , feeling
. I â ll keep her obedient and make
stayed on the l ily pad and watched the butterfly .
Bang ! You 're under arrest !" Their mom
found a big l ily pad . He quickly hopped on
He found a l ily pad in the pond and rested
, " You are under arrest for harassing and stealing from
hopped off the l ily pad , looked around , and
. The bird saw O ll ie and wanted to eat
him on the l ily pad . They all rested together
giant ! You are under arrest ! You can 't take
, I â ll allow you to take it

INTERVAL 3.204 - 6.022
CONTAINS 0.028%

. We need a grown - up to help us read
dress - up and make - bel ieve . One day
Do you know how to stitch ?" The tree
and Mia lick their ice - cream . It is cold
They like to play dress - up . They like to

INTERVAL 0.386 - 3.204
CONTAINS 27.896%

big tree ." The race began , and Remy
said that ?" he asked . There was a
They hugged each other and played together happily . From that
. They have fun and are happy . <|endoftext|> L ily
, we will have to punish you ."

INTERVAL -2.433 - 0.386
CONTAINS 71.896%

her fingers and before long , the magic had made something
brave ly reached out and touched the ancient skeleton . She
an idea . He ran to get his dad 's ladder
Jack found an old anchor and said : " This will
castle was safe . Later that day , Tim

INTERVAL -5.251 - -2.433
CONTAINS 0.180%

nice tune , she made lots of strange noises .
of the day , they both knew they would be best
he had never seen this many fish before . He was
little boy some of his lunch and they had a happy
notebook . They both argued , but neither one
Token amazed
Token ID24562
Feature activation-4.81e-01

Pos logit contributions
agging+0.004
five+0.004
 mine+0.004
 cheek+0.004
 liking+0.003
Neg logit contributions
 Pig-0.004
wood-0.004
 Ally-0.004
 Bert-0.004
 Beth-0.004
Token.
Token ID13
Feature activation-3.23e-01

Pos logit contributions
agging+0.020
five+0.019
 cheek+0.018
 mine+0.017
 goodness+0.017
Neg logit contributions
 Pig-0.020
 Tweet-0.017
 known-0.017
 Beth-0.017
gy-0.017
Token He
Token ID679
Feature activation+1.51e-01

Pos logit contributions
five+0.012
arl+0.010
agging+0.010
 cheek+0.010
EEP+0.010
Neg logit contributions
 Pig-0.014
 known-0.013
 Madd-0.013
 Tweet-0.013
house-0.013
Token watched
Token ID7342
Feature activation-1.20e+00

Pos logit contributions
 Pig+0.005
 Tweet+0.005
 Beth+0.005
 Bunny+0.004
 Ally+0.004
Neg logit contributions
five-0.007
agging-0.007
 cheek-0.007
 mine-0.006
 fourteen-0.006
Token as
Token ID355
Feature activation-6.91e-01

Pos logit contributions
five+0.055
agging+0.053
 cheek+0.051
 fourteen+0.049
 mine+0.047
Neg logit contributions
 Pig-0.043
gy-0.039
wood-0.039
 known-0.039
 Beth-0.038
Token Per
Token ID2448
Feature activation+6.02e+00

Pos logit contributions
five+0.027
agging+0.024
 fourteen+0.023
 cheek+0.023
arl+0.023
Neg logit contributions
wood-0.027
house-0.027
gy-0.026
 dam-0.026
 Pig-0.026
Tokenc
Token ID66
Feature activation+5.39e+00

Pos logit contributions
 Pig+0.280
 Tweet+0.257
 Bunny+0.253
 Beth+0.252
 Ally+0.249
Neg logit contributions
five-0.223
agging-0.203
 cheek-0.194
 fourteen-0.182
 mine-0.177
Tokenival
Token ID2473
Feature activation+1.63e+00

Pos logit contributions
 Pig+0.213
 Beth+0.191
 Bunny+0.188
 Ally+0.186
 Tweet+0.186
Neg logit contributions
five-0.233
agging-0.222
 cheek-0.206
 fourteen-0.203
 goodness-0.190
Token cut
Token ID2005
Feature activation+3.94e-01

Pos logit contributions
 Pig+0.063
 Suz+0.057
 known+0.057
 Bunny+0.056
 Madd+0.056
Neg logit contributions
five-0.069
agging-0.062
 fourteen-0.060
 mine-0.059
 cheek-0.059
Token out
Token ID503
Feature activation+2.92e-01

Pos logit contributions
 known+0.015
 Pig+0.014
 Ally+0.013
 dam+0.013
gy+0.013
Neg logit contributions
five-0.016
agging-0.015
 fourteen-0.014
 goodness-0.014
 mine-0.013
Token two
Token ID734
Feature activation-1.44e-01

Pos logit contributions
 Pig+0.012
 Tweet+0.011
 known+0.011
gy+0.011
 Bunny+0.011
Neg logit contributions
five-0.012
agging-0.011
 cheek-0.010
 fourteen-0.010
 mine-0.010
Token.
Token ID13
Feature activation-3.23e-01

Pos logit contributions
agging+0.020
five+0.019
 cheek+0.018
 mine+0.017
 goodness+0.017
Neg logit contributions
 Pig-0.020
 Tweet-0.017
 known-0.017
 Beth-0.017
gy-0.017
Token He
Token ID679
Feature activation+1.51e-01

Pos logit contributions
five+0.012
arl+0.010
agging+0.010
 cheek+0.010
EEP+0.010
Neg logit contributions
 Pig-0.014
 known-0.013
 Madd-0.013
 Tweet-0.013
house-0.013
Token watched
Token ID7342
Feature activation-1.20e+00

Pos logit contributions
 Pig+0.005
 Tweet+0.005
 Beth+0.005
 Bunny+0.004
 Ally+0.004
Neg logit contributions
five-0.007
agging-0.007
 cheek-0.007
 mine-0.006
 fourteen-0.006
Token as
Token ID355
Feature activation-6.91e-01

Pos logit contributions
five+0.055
agging+0.053
 cheek+0.051
 fourteen+0.049
 mine+0.047
Neg logit contributions
 Pig-0.043
gy-0.039
wood-0.039
 known-0.039
 Beth-0.038
Token Per
Token ID2448
Feature activation+6.02e+00

Pos logit contributions
five+0.027
agging+0.024
 fourteen+0.023
 cheek+0.023
arl+0.023
Neg logit contributions
wood-0.027
house-0.027
gy-0.026
 dam-0.026
 Pig-0.026
Tokenc
Token ID66
Feature activation+5.39e+00

Pos logit contributions
 Pig+0.280
 Tweet+0.257
 Bunny+0.253
 Beth+0.252
 Ally+0.249
Neg logit contributions
five-0.223
agging-0.203
 cheek-0.194
 fourteen-0.182
 mine-0.177
Tokenival
Token ID2473
Feature activation+1.63e+00

Pos logit contributions
 Pig+0.213
 Beth+0.191
 Bunny+0.188
 Ally+0.186
 Tweet+0.186
Neg logit contributions
five-0.233
agging-0.222
 cheek-0.206
 fourteen-0.203
 goodness-0.190
Token cut
Token ID2005
Feature activation+3.94e-01

Pos logit contributions
 Pig+0.063
 Suz+0.057
 known+0.057
 Bunny+0.056
 Madd+0.056
Neg logit contributions
five-0.069
agging-0.062
 fourteen-0.060
 mine-0.059
 cheek-0.059
Token out
Token ID503
Feature activation+2.92e-01

Pos logit contributions
 known+0.015
 Pig+0.014
 Ally+0.013
 dam+0.013
gy+0.013
Neg logit contributions
five-0.016
agging-0.015
 fourteen-0.014
 goodness-0.014
 mine-0.013
Token two
Token ID734
Feature activation-1.44e-01

Pos logit contributions
 Pig+0.012
 Tweet+0.011
 known+0.011
gy+0.011
 Bunny+0.011
Neg logit contributions
five-0.012
agging-0.011
 cheek-0.010
 fourteen-0.010
 mine-0.010
Token shapes
Token ID15268
Feature activation+2.09e-01

Pos logit contributions
five+0.006
agging+0.006
 cheek+0.006
arl+0.005
 fourteen+0.005
Neg logit contributions
 Pig-0.006
 Tweet-0.005
 Beth-0.005
 Bunny-0.005
 Bert-0.005
Token They
Token ID1119
Feature activation+2.00e-01

Pos logit contributions
five+0.005
 cheek+0.005
agging+0.005
 fourteen+0.005
arl+0.005
Neg logit contributions
 Pig-0.004
gy-0.004
 known-0.004
wood-0.004
 Beth-0.003
Token played
Token ID2826
Feature activation+1.97e-01

Pos logit contributions
 Pig+0.008
wood+0.007
 Beth+0.007
 Ally+0.007
 Tweet+0.007
Neg logit contributions
five-0.008
agging-0.008
 cheek-0.008
 fourteen-0.007
ige-0.007
Token catch
Token ID4929
Feature activation-1.00e+00

Pos logit contributions
 Pig+0.006
 Tweet+0.006
 Bunny+0.005
 Beth+0.005
 Ally+0.005
Neg logit contributions
five-0.010
agging-0.010
 cheek-0.009
 fourteen-0.009
 Deal-0.009
Token and
Token ID290
Feature activation-1.16e-01

Pos logit contributions
five+0.045
agging+0.040
 cheek+0.039
 mine+0.037
 goodness+0.037
Neg logit contributions
 Pig-0.042
 known-0.037
wood-0.036
 Beth-0.036
gy-0.036
Token tug
Token ID27762
Feature activation-2.24e-01

Pos logit contributions
five+0.005
 cheek+0.004
agging+0.004
 mine+0.004
 fourteen+0.004
Neg logit contributions
 Pig-0.005
 Beth-0.004
wood-0.004
 Ally-0.004
 Tweet-0.004
Token-
Token ID12
Feature activation+5.35e+00

Pos logit contributions
five+0.010
agging+0.009
 cheek+0.009
 Deal+0.008
 sidelines+0.008
Neg logit contributions
 Pig-0.009
 Tweet-0.008
 Bunny-0.008
 Beth-0.008
gy-0.008
Tokenof
Token ID1659
Feature activation+6.56e-01

Pos logit contributions
 Pig+0.275
 Beth+0.250
 Tweet+0.249
 Bunny+0.248
 Ally+0.246
Neg logit contributions
five-0.180
agging-0.156
 cheek-0.148
 fourteen-0.142
 sidelines-0.131
Token-
Token ID12
Feature activation+4.99e+00

Pos logit contributions
 Pig+0.027
 Tweet+0.024
 Beth+0.023
 Bunny+0.023
 Ally+0.023
Neg logit contributions
five-0.027
agging-0.026
 cheek-0.026
 fourteen-0.024
 mine-0.023
Tokenwar
Token ID5767
Feature activation+3.43e-01

Pos logit contributions
 Pig+0.256
 Tweet+0.234
 Beth+0.232
 Bunny+0.231
 Ally+0.229
Neg logit contributions
five-0.163
agging-0.147
 cheek-0.140
 fourteen-0.130
 mine-0.123
Token.
Token ID13
Feature activation-2.72e-02

Pos logit contributions
 Pig+0.015
 known+0.014
 Ally+0.013
 Beth+0.013
 Bunny+0.013
Neg logit contributions
five-0.014
agging-0.014
 cheek-0.014
 fourteen-0.012
ater-0.011
Token The
Token ID383
Feature activation+3.72e-01

Pos logit contributions
five+0.001
 fourteen+0.001
 Deal+0.001
arl+0.001
agging+0.001
Neg logit contributions
 Pig-0.001
gy-0.001
wood-0.001
 known-0.001
 Beth-0.001
Token hug
Token ID16225
Feature activation-6.61e-01

Pos logit contributions
 Pig+0.012
 Tweet+0.011
 Beth+0.011
 Bunny+0.011
 Ally+0.011
Neg logit contributions
five-0.008
agging-0.008
 cheek-0.007
 fourteen-0.007
 mine-0.007
Token and
Token ID290
Feature activation+5.81e-01

Pos logit contributions
five+0.026
 cheek+0.025
agging+0.025
 fourteen+0.022
 mine+0.022
Neg logit contributions
 Pig-0.027
 Tweet-0.026
 Ally-0.025
 known-0.025
 Beth-0.025
Token lots
Token ID6041
Feature activation-1.04e+00

Pos logit contributions
 Pig+0.022
gy+0.022
wood+0.022
 dam+0.021
 Tweet+0.020
Neg logit contributions
five-0.023
 cheek-0.021
 mine-0.019
 fourteen-0.019
 goodness-0.019
Token of
Token ID286
Feature activation+1.82e+00

Pos logit contributions
five+0.046
agging+0.045
 cheek+0.044
 Deal+0.041
 fourteen+0.041
Neg logit contributions
 Pig-0.039
 Tweet-0.035
 Bunny-0.034
 Beth-0.034
 Ally-0.033
Token up
Token ID510
Feature activation+8.83e-01

Pos logit contributions
 Pig+0.081
gy+0.073
 Tweet+0.073
wood+0.072
 Beth+0.072
Neg logit contributions
five-0.069
agging-0.066
 cheek-0.064
 mine-0.057
 fourteen-0.057
Token-
Token ID12
Feature activation+5.22e+00

Pos logit contributions
 Pig+0.036
 Tweet+0.032
gy+0.032
 Ally+0.032
wood+0.032
Neg logit contributions
agging-0.036
five-0.036
 cheek-0.033
 mine-0.032
 fourteen-0.031
Tokendowns
Token ID30371
Feature activation+2.00e+00

Pos logit contributions
 Pig+0.248
 Bunny+0.223
 Tweet+0.223
 Beth+0.221
 Bert+0.220
Neg logit contributions
five-0.202
agging-0.172
 cheek-0.167
 fourteen-0.155
leaf-0.152
Token to
Token ID284
Feature activation+6.43e-01

Pos logit contributions
 Pig+0.074
gy+0.068
 known+0.068
 Tweet+0.067
 Ally+0.066
Neg logit contributions
five-0.089
 cheek-0.083
agging-0.081
 mine-0.075
 goodness-0.075
Token make
Token ID787
Feature activation+7.39e-01

Pos logit contributions
 Pig+0.027
 Tweet+0.025
 Beth+0.024
 Bunny+0.024
 Ally+0.024
Neg logit contributions
five-0.026
agging-0.025
 cheek-0.024
 fourteen-0.022
 mine-0.022
Token it
Token ID340
Feature activation+2.04e-01

Pos logit contributions
gy+0.030
 Pig+0.029
wood+0.028
 known+0.027
house+0.027
Neg logit contributions
five-0.029
 goodness-0.027
 cheek-0.027
agging-0.027
 mine-0.025
Token feel
Token ID1254
Feature activation+2.43e-03

Pos logit contributions
 Pig+0.008
 Ally+0.007
 Beth+0.007
 Bert+0.007
wood+0.007
Neg logit contributions
 cheek-0.009
five-0.009
agging-0.008
 mine-0.008
 liking-0.007
Token playing
Token ID2712
Feature activation-1.50e-01

Pos logit contributions
 mine+0.006
five+0.006
agging+0.006
 arrest+0.005
 liking+0.005
Neg logit contributions
 Pig-0.005
wood-0.005
gy-0.005
 Ally-0.005
 Tweet-0.005
Token a
Token ID257
Feature activation+4.92e-01

Pos logit contributions
five+0.007
agging+0.007
 cheek+0.006
 mine+0.006
 goodness+0.006
Neg logit contributions
 Pig-0.006
 known-0.005
wood-0.005
 Ally-0.005
 Beth-0.005
Token game
Token ID983
Feature activation+2.28e-01

Pos logit contributions
 Pig+0.021
 Tweet+0.019
 Bunny+0.019
 Beth+0.019
 Ally+0.019
Neg logit contributions
five-0.019
agging-0.019
 cheek-0.018
 fourteen-0.017
 Deal-0.017
Token of
Token ID286
Feature activation+9.03e-01

Pos logit contributions
 Pig+0.009
 Tweet+0.007
 known+0.007
 Ally+0.007
gy+0.007
Neg logit contributions
five-0.010
agging-0.010
 cheek-0.009
 mine-0.009
 fourteen-0.009
Token kick
Token ID4829
Feature activation+2.56e-01

Pos logit contributions
 Pig+0.038
 Tweet+0.036
 Beth+0.035
 Bunny+0.034
 Ally+0.034
Neg logit contributions
five-0.035
agging-0.034
 cheek-0.033
arl-0.031
 fourteen-0.031
Token-
Token ID12
Feature activation+5.05e+00

Pos logit contributions
 Pig+0.010
 known+0.009
gy+0.009
 Beth+0.009
 Ally+0.009
Neg logit contributions
five-0.011
agging-0.011
 mine-0.010
 cheek-0.010
 la-0.009
Tokenball
Token ID1894
Feature activation+1.23e+00

Pos logit contributions
 Pig+0.235
 Tweet+0.218
 Beth+0.212
 known+0.212
wood+0.211
Neg logit contributions
agging-0.169
five-0.166
 cheek-0.166
 Deal-0.151
 fourteen-0.146
Token.
Token ID13
Feature activation+9.69e-01

Pos logit contributions
 Pig+0.044
 Tweet+0.039
 known+0.038
 Beth+0.038
 Ally+0.038
Neg logit contributions
five-0.058
agging-0.056
 cheek-0.054
 mine-0.051
 fourteen-0.050
Token Lily
Token ID20037
Feature activation+4.75e-01

Pos logit contributions
 Pig+0.033
 known+0.029
 Tweet+0.028
wood+0.028
 Ally+0.028
Neg logit contributions
five-0.047
 cheek-0.045
agging-0.044
 mine-0.042
 fourteen-0.041
Token was
Token ID373
Feature activation+1.84e-01

Pos logit contributions
 Pig+0.017
wood+0.016
 Tweet+0.015
 darker+0.015
 Ally+0.015
Neg logit contributions
five-0.021
 cheek-0.020
agging-0.019
 mine-0.019
ige-0.018
Token so
Token ID523
Feature activation+1.77e-02

Pos logit contributions
wood+0.009
 Pig+0.008
gy+0.007
bul+0.007
 Bert+0.007
Neg logit contributions
 liking-0.007
 mine-0.007
agging-0.006
five-0.006
 cheek-0.006
Token which
Token ID543
Feature activation-6.27e-03

Pos logit contributions
 Pig+0.000
 Tweet+0.000
 Bunny+0.000
 Beth+0.000
 Ally+0.000
Neg logit contributions
five-0.000
agging-0.000
 cheek-0.000
 fourteen-0.000
 mine-0.000
Token tw
Token ID665
Feature activation+6.57e-01

Pos logit contributions
five+0.000
 mine+0.000
 cheek+0.000
agging+0.000
 fourteen+0.000
Neg logit contributions
 Pig-0.000
gy-0.000
wood-0.000
 Tweet-0.000
 Bert-0.000
Tokenirled
Token ID49376
Feature activation+8.92e-01

Pos logit contributions
 Pig+0.024
 Tweet+0.022
 Bunny+0.021
 Beth+0.021
 Ally+0.021
Neg logit contributions
five-0.029
agging-0.029
 cheek-0.028
 fourteen-0.026
 mine-0.026
Token and
Token ID290
Feature activation+5.83e-01

Pos logit contributions
 Pig+0.033
 known+0.029
 Tweet+0.027
 Bunny+0.027
wood+0.027
Neg logit contributions
five-0.041
agging-0.041
 cheek-0.039
 mine-0.038
 la-0.036
Token t
Token ID256
Feature activation+1.21e+00

Pos logit contributions
 Pig+0.023
wood+0.020
gy+0.019
 Bunny+0.019
 Tweet+0.019
Neg logit contributions
five-0.025
 cheek-0.024
agging-0.023
 la-0.023
 mine-0.023
Token-
Token ID12
Feature activation+5.04e+00

Pos logit contributions
 Pig+0.048
 Tweet+0.043
 Beth+0.043
 Bunny+0.042
gy+0.042
Neg logit contributions
five-0.052
agging-0.050
 cheek-0.048
 fourteen-0.045
 Deal-0.044
Tokenshirts
Token ID23231
Feature activation+5.96e-01

Pos logit contributions
 Pig+0.225
 Tweet+0.206
 Beth+0.202
 Bunny+0.200
 Ally+0.199
Neg logit contributions
five-0.186
agging-0.181
 cheek-0.175
 fourteen-0.159
 Deal-0.158
Token that
Token ID326
Feature activation+1.46e+00

Pos logit contributions
 Pig+0.020
 Tweet+0.018
 Bunny+0.017
 Ally+0.017
 Beth+0.017
Neg logit contributions
five-0.029
agging-0.028
 cheek-0.027
 fourteen-0.025
 mine-0.025
Token jumped
Token ID11687
Feature activation-4.21e-01

Pos logit contributions
gy+0.054
 Pig+0.053
 dam+0.052
wood+0.052
 Ally+0.049
Neg logit contributions
five-0.055
 cheek-0.054
 mine-0.054
 la-0.050
 goodness-0.049
Token.
Token ID13
Feature activation+1.69e-01

Pos logit contributions
agging+0.019
five+0.018
 cheek+0.018
 mine+0.018
 fourteen+0.017
Neg logit contributions
 Pig-0.015
 known-0.014
 Tweet-0.013
 Ally-0.013
wood-0.013
Token He
Token ID679
Feature activation-1.65e-01

Pos logit contributions
 Pig+0.006
 known+0.005
wood+0.005
gy+0.005
 Tweet+0.005
Neg logit contributions
five-0.008
 cheek-0.007
agging-0.007
 Deal-0.007
 la-0.007
Token she
Token ID673
Feature activation+8.62e-01

Pos logit contributions
 cheek+0.034
agging+0.031
five+0.031
 goodness+0.029
 mine+0.028
Neg logit contributions
 Pig-0.035
wood-0.034
gy-0.033
 dam-0.032
house-0.031
Token stood
Token ID6204
Feature activation+4.07e-01

Pos logit contributions
 Pig+0.030
 Tweet+0.027
 Ally+0.027
 Beth+0.026
wood+0.026
Neg logit contributions
five-0.040
agging-0.037
 cheek-0.037
 fourteen-0.034
 la-0.034
Token up
Token ID510
Feature activation+2.98e-01

Pos logit contributions
 Pig+0.015
 Tweet+0.014
wood+0.014
 known+0.014
 Ally+0.013
Neg logit contributions
agging-0.018
 cheek-0.017
 mine-0.015
 goodness-0.015
ater-0.014
Token and
Token ID290
Feature activation+2.49e-01

Pos logit contributions
 Pig+0.013
wood+0.012
 known+0.012
 Tweet+0.012
gy+0.012
Neg logit contributions
agging-0.010
 cheek-0.010
five-0.009
 mine-0.009
 fourteen-0.009
Token tip
Token ID8171
Feature activation+2.48e-01

Pos logit contributions
 Pig+0.009
 Tweet+0.008
wood+0.008
 Ally+0.008
 dam+0.008
Neg logit contributions
 cheek-0.011
five-0.011
 mine-0.010
 la-0.010
agging-0.009
Token-
Token ID12
Feature activation+5.01e+00

Pos logit contributions
 Pig+0.010
 known+0.009
 Tweet+0.009
 Ally+0.009
wood+0.009
Neg logit contributions
agging-0.010
five-0.010
 cheek-0.010
 goodness-0.009
 fourteen-0.009
Tokento
Token ID1462
Feature activation-2.48e-01

Pos logit contributions
 Pig+0.209
 Tweet+0.189
 Bunny+0.185
 Beth+0.184
 Ally+0.182
Neg logit contributions
five-0.207
agging-0.191
 cheek-0.188
 fourteen-0.176
 mine-0.169
Tokened
Token ID276
Feature activation+1.42e+00

Pos logit contributions
five+0.011
agging+0.010
 cheek+0.010
 fourteen+0.009
 mine+0.009
Neg logit contributions
 Pig-0.010
 Tweet-0.009
 Bunny-0.008
 Beth-0.008
 Ally-0.008
Token out
Token ID503
Feature activation+5.67e-01

Pos logit contributions
 Pig+0.056
 known+0.051
 Tweet+0.049
 dam+0.049
gy+0.049
Neg logit contributions
five-0.059
 cheek-0.055
agging-0.054
 goodness-0.053
 mine-0.052
Token of
Token ID286
Feature activation+1.73e+00

Pos logit contributions
 Pig+0.024
gy+0.022
wood+0.022
 Tweet+0.022
 known+0.021
Neg logit contributions
five-0.022
agging-0.022
 cheek-0.021
 fourteen-0.019
 mine-0.019
Token the
Token ID262
Feature activation+4.08e-01

Pos logit contributions
 Pig+0.061
gy+0.057
wood+0.055
 Tweet+0.053
house+0.052
Neg logit contributions
five-0.075
 mine-0.072
 cheek-0.072
agging-0.071
 fourteen-0.069
Token play
Token ID711
Feature activation+4.48e-01

Pos logit contributions
 Pig+0.029
 Tweet+0.026
 Beth+0.026
 Bunny+0.026
 Ally+0.026
Neg logit contributions
five-0.028
agging-0.028
 cheek-0.027
 fourteen-0.024
 mine-0.024
Token a
Token ID257
Feature activation+8.90e-01

Pos logit contributions
 Pig+0.017
wood+0.015
 Bunny+0.014
 known+0.014
 Ally+0.014
Neg logit contributions
five-0.021
agging-0.020
 cheek-0.019
 mine-0.019
 goodness-0.018
Token game
Token ID983
Feature activation+7.89e-02

Pos logit contributions
 Pig+0.040
 Tweet+0.037
 Beth+0.036
 Bunny+0.036
 Ally+0.035
Neg logit contributions
five-0.033
agging-0.032
 cheek-0.030
 fourteen-0.028
 Deal-0.028
Token of
Token ID286
Feature activation+1.17e+00

Pos logit contributions
 Pig+0.003
 Tweet+0.003
 Bunny+0.002
 Beth+0.002
 Ally+0.002
Neg logit contributions
five-0.004
agging-0.004
 cheek-0.003
 fourteen-0.003
 mine-0.003
Token tug
Token ID27762
Feature activation-6.41e-01

Pos logit contributions
 Pig+0.049
 Tweet+0.044
 Beth+0.043
 Bunny+0.043
 Ally+0.042
Neg logit contributions
five-0.048
agging-0.046
 cheek-0.045
 fourteen-0.041
 mine-0.041
Token-
Token ID12
Feature activation+5.00e+00

Pos logit contributions
five+0.029
agging+0.028
 cheek+0.027
 fourteen+0.025
 mine+0.025
Neg logit contributions
 Pig-0.024
 Tweet-0.022
 Beth-0.021
 Bunny-0.021
 Ally-0.021
Tokeno
Token ID78
Feature activation+1.46e+00

Pos logit contributions
 Pig+0.242
 Tweet+0.222
 Beth+0.218
 Bunny+0.217
 Ally+0.215
Neg logit contributions
five-0.169
agging-0.163
 cheek-0.156
 fourteen-0.141
 mine-0.138
Token-
Token ID12
Feature activation+4.54e+00

Pos logit contributions
 Pig+0.054
 Tweet+0.048
 Beth+0.047
 Bunny+0.047
gy+0.047
Neg logit contributions
five-0.065
agging-0.063
 cheek-0.061
 fourteen-0.057
 Deal-0.057
Tokenwar
Token ID5767
Feature activation+7.21e-02

Pos logit contributions
 Pig+0.209
 Tweet+0.191
 Beth+0.187
 Bunny+0.186
gy+0.185
Neg logit contributions
five-0.159
agging-0.158
 cheek-0.152
 Deal-0.138
 fourteen-0.136
Token.
Token ID13
Feature activation+2.72e-01

Pos logit contributions
 Pig+0.003
 known+0.003
 Tweet+0.003
 Ally+0.003
 Beth+0.003
Neg logit contributions
five-0.003
agging-0.003
 cheek-0.003
 mine-0.003
 fourteen-0.003
Token
Token ID198
Feature activation-2.77e-01

Pos logit contributions
 known+0.011
 Pig+0.011
 darker+0.010
gy+0.010
 rou+0.010
Neg logit contributions
five-0.011
 fourteen-0.009
EEP-0.009
 cheek-0.009
 goodness-0.008
Token catch
Token ID4929
Feature activation-1.00e+00

Pos logit contributions
 Pig+0.006
 Tweet+0.006
 Bunny+0.005
 Beth+0.005
 Ally+0.005
Neg logit contributions
five-0.010
agging-0.010
 cheek-0.009
 fourteen-0.009
 Deal-0.009
Token and
Token ID290
Feature activation-1.16e-01

Pos logit contributions
five+0.045
agging+0.040
 cheek+0.039
 mine+0.037
 goodness+0.037
Neg logit contributions
 Pig-0.042
 known-0.037
wood-0.036
 Beth-0.036
gy-0.036
Token tug
Token ID27762
Feature activation-2.24e-01

Pos logit contributions
five+0.005
 cheek+0.004
agging+0.004
 mine+0.004
 fourteen+0.004
Neg logit contributions
 Pig-0.005
 Beth-0.004
wood-0.004
 Ally-0.004
 Tweet-0.004
Token-
Token ID12
Feature activation+5.35e+00

Pos logit contributions
five+0.010
agging+0.009
 cheek+0.009
 Deal+0.008
 sidelines+0.008
Neg logit contributions
 Pig-0.009
 Tweet-0.008
 Bunny-0.008
 Beth-0.008
gy-0.008
Tokenof
Token ID1659
Feature activation+6.56e-01

Pos logit contributions
 Pig+0.275
 Beth+0.250
 Tweet+0.249
 Bunny+0.248
 Ally+0.246
Neg logit contributions
five-0.180
agging-0.156
 cheek-0.148
 fourteen-0.142
 sidelines-0.131
Token-
Token ID12
Feature activation+4.99e+00

Pos logit contributions
 Pig+0.027
 Tweet+0.024
 Beth+0.023
 Bunny+0.023
 Ally+0.023
Neg logit contributions
five-0.027
agging-0.026
 cheek-0.026
 fourteen-0.024
 mine-0.023
Tokenwar
Token ID5767
Feature activation+3.43e-01

Pos logit contributions
 Pig+0.256
 Tweet+0.234
 Beth+0.232
 Bunny+0.231
 Ally+0.229
Neg logit contributions
five-0.163
agging-0.147
 cheek-0.140
 fourteen-0.130
 mine-0.123
Token.
Token ID13
Feature activation-2.72e-02

Pos logit contributions
 Pig+0.015
 known+0.014
 Ally+0.013
 Beth+0.013
 Bunny+0.013
Neg logit contributions
five-0.014
agging-0.014
 cheek-0.014
 fourteen-0.012
ater-0.011
Token The
Token ID383
Feature activation+3.72e-01

Pos logit contributions
five+0.001
 fourteen+0.001
 Deal+0.001
arl+0.001
agging+0.001
Neg logit contributions
 Pig-0.001
gy-0.001
wood-0.001
 known-0.001
 Beth-0.001
Token fox
Token ID21831
Feature activation-4.37e-01

Pos logit contributions
 Pig+0.014
 Tweet+0.012
 Bunny+0.012
 Beth+0.012
 Ally+0.012
Neg logit contributions
five-0.017
agging-0.016
 cheek-0.016
 fourteen-0.015
 Deal-0.015
Token was
Token ID373
Feature activation-3.00e-02

Pos logit contributions
five+0.019
 cheek+0.017
agging+0.017
 fourteen+0.016
 la+0.016
Neg logit contributions
 Pig-0.018
wood-0.016
 Beth-0.016
 Ally-0.016
 Tweet-0.016
Token would
Token ID561
Feature activation-2.43e-01

Pos logit contributions
five+0.002
 cheek+0.001
agging+0.001
 fourteen+0.001
 mine+0.001
Neg logit contributions
 Pig-0.001
 Tweet-0.001
 Beth-0.001
 Ally-0.001
wood-0.001
Token always
Token ID1464
Feature activation+8.63e-02

Pos logit contributions
five+0.010
agging+0.010
 cheek+0.010
arl+0.009
 Deal+0.009
Neg logit contributions
 Pig-0.010
 Tweet-0.009
 Bunny-0.008
 Beth-0.008
 known-0.008
Token say
Token ID910
Feature activation-3.33e-01

Pos logit contributions
 Pig+0.004
 Tweet+0.003
 known+0.003
 Bunny+0.003
 Beth+0.003
Neg logit contributions
five-0.004
agging-0.003
 cheek-0.003
 fourteen-0.003
arl-0.003
Token '
Token ID705
Feature activation+2.02e+00

Pos logit contributions
five+0.015
agging+0.014
 cheek+0.014
 sidelines+0.013
 fourteen+0.013
Neg logit contributions
 Pig-0.013
 Tweet-0.011
 Bunny-0.011
 Beth-0.011
 Ally-0.011
Tokenthank
Token ID40716
Feature activation+4.23e-01

Pos logit contributions
 Pig+0.090
 Tweet+0.082
 Bunny+0.081
 Beth+0.081
 Ally+0.080
Neg logit contributions
five-0.078
agging-0.070
 cheek-0.069
 fourteen-0.064
 goodness-0.063
Token-
Token ID12
Feature activation+4.94e+00

Pos logit contributions
 Pig+0.025
 Tweet+0.023
 Bunny+0.022
 Beth+0.022
 Ally+0.022
Neg logit contributions
five-0.010
agging-0.010
 cheek-0.009
 fourteen-0.008
arl-0.008
Tokenyou
Token ID5832
Feature activation+3.12e-01

Pos logit contributions
 Pig+0.251
 known+0.232
 Tweet+0.231
wood+0.225
 Ally+0.225
Neg logit contributions
agging-0.157
 cheek-0.142
 Deal-0.134
five-0.133
arl-0.128
Token'
Token ID6
Feature activation+9.50e-01

Pos logit contributions
 Pig+0.014
 Ally+0.012
 Bunny+0.012
 Beth+0.012
wood+0.012
Neg logit contributions
agging-0.012
five-0.011
 cheek-0.011
 sidelines-0.011
arl-0.010
Token to
Token ID284
Feature activation+3.33e-01

Pos logit contributions
 Pig+0.036
 Tweet+0.033
 Beth+0.032
 Bunny+0.031
 known+0.031
Neg logit contributions
five-0.042
agging-0.040
 cheek-0.040
 fourteen-0.036
 mine-0.036
Token his
Token ID465
Feature activation-3.54e-01

Pos logit contributions
 Pig+0.011
 Tweet+0.010
 Beth+0.010
 Bunny+0.009
 Ally+0.009
Neg logit contributions
five-0.017
agging-0.017
 cheek-0.016
arl-0.015
 fourteen-0.015
Token toast
Token ID27805
Feature activation-7.80e-01

Pos logit contributions
five+0.016
agging+0.015
 cheek+0.015
 mine+0.014
 Deal+0.013
Neg logit contributions
 Pig-0.013
 Tweet-0.012
 Beth-0.012
 Ally-0.012
 known-0.012
Token push
Token ID4574
Feature activation-1.43e-01

Pos logit contributions
 Pig+0.027
gy+0.023
 Tweet+0.023
 Bunny+0.023
wood+0.023
Neg logit contributions
five-0.026
agging-0.024
 cheek-0.023
 mine-0.022
 goodness-0.021
Token-
Token ID12
Feature activation+4.27e+00

Pos logit contributions
five+0.006
agging+0.005
 mine+0.005
 goodness+0.005
 cheek+0.005
Neg logit contributions
 Pig-0.006
 known-0.006
 Ally-0.006
 Tweet-0.005
 Bunny-0.005
Tokenups
Token ID4739
Feature activation+1.63e+00

Pos logit contributions
 Pig+0.188
 Tweet+0.170
 Bunny+0.168
 Beth+0.167
 Ally+0.165
Neg logit contributions
five-0.171
agging-0.157
 cheek-0.150
 fourteen-0.142
 mine-0.136
Token and
Token ID290
Feature activation-6.35e-02

Pos logit contributions
 Pig+0.060
 Tweet+0.055
 Ally+0.052
 Bunny+0.052
 known+0.051
Neg logit contributions
five-0.075
agging-0.072
 cheek-0.070
 fourteen-0.065
 mine-0.065
Token pull
Token ID2834
Feature activation+1.17e-01

Pos logit contributions
five+0.002
 cheek+0.002
agging+0.002
 mine+0.002
 fourteen+0.002
Neg logit contributions
 Pig-0.003
 Tweet-0.003
 Ally-0.003
 Bunny-0.003
 Beth-0.002
Token-
Token ID12
Feature activation+4.93e+00

Pos logit contributions
 Pig+0.005
 known+0.005
 Ally+0.004
 Tweet+0.004
gy+0.004
Neg logit contributions
five-0.004
agging-0.004
 mine-0.004
 fourteen-0.004
 goodness-0.004
Tokenups
Token ID4739
Feature activation+2.58e+00

Pos logit contributions
 Pig+0.210
 Tweet+0.188
 Bunny+0.186
 Beth+0.185
 Ally+0.183
Neg logit contributions
five-0.207
agging-0.186
 cheek-0.179
 fourteen-0.174
 mine-0.165
Token.
Token ID13
Feature activation+4.15e-01

Pos logit contributions
 Pig+0.092
 Tweet+0.083
 Ally+0.080
 known+0.079
 Bunny+0.079
Neg logit contributions
five-0.121
agging-0.116
 cheek-0.114
 fourteen-0.106
 mine-0.106
Token He
Token ID679
Feature activation+2.62e-01

Pos logit contributions
 Pig+0.015
 known+0.014
 darker+0.014
wood+0.014
gy+0.013
Neg logit contributions
five-0.018
 Deal-0.016
 fourteen-0.016
 sidelines-0.015
agging-0.015
Token worked
Token ID3111
Feature activation+1.37e-01

Pos logit contributions
 Pig+0.010
 Ally+0.010
 Tweet+0.009
wood+0.009
 Bunny+0.009
Neg logit contributions
five-0.012
 fourteen-0.010
 mine-0.010
 cheek-0.010
agging-0.009
Token really
Token ID1107
Feature activation-3.81e-01

Pos logit contributions
 Pig+0.006
 Bunny+0.005
 Ally+0.005
 Tweet+0.005
gy+0.005
Neg logit contributions
agging-0.005
five-0.005
 fourteen-0.005
 mine-0.005
 cheek-0.005
Token soft
Token ID2705
Feature activation-4.27e-01

Pos logit contributions
 Pig+0.007
 Beth+0.006
 Bunny+0.006
 Ch+0.006
 Bert+0.006
Neg logit contributions
five-0.007
 fourteen-0.007
agging-0.007
 Deal-0.006
arl-0.006
Token rug
Token ID14477
Feature activation+6.20e-01

Pos logit contributions
five+0.017
agging+0.017
 Deal+0.017
 fourteen+0.016
arl+0.015
Neg logit contributions
 Pig-0.017
 Beth-0.016
 Bunny-0.016
gy-0.016
 Tweet-0.016
Token and
Token ID290
Feature activation-7.70e-02

Pos logit contributions
 Pig+0.026
 known+0.024
 Tweet+0.022
 Beth+0.022
 Ally+0.022
Neg logit contributions
five-0.026
agging-0.025
 cheek-0.025
 mine-0.022
 fourteen-0.022
Token even
Token ID772
Feature activation+1.25e-01

Pos logit contributions
five+0.003
 cheek+0.003
agging+0.003
 mine+0.003
 la+0.003
Neg logit contributions
 Pig-0.003
wood-0.003
 Tweet-0.003
 known-0.003
gy-0.003
Token hand
Token ID1021
Feature activation+1.26e+00

Pos logit contributions
 Pig+0.005
 Bert+0.004
gy+0.004
wood+0.004
 Ot+0.004
Neg logit contributions
five-0.005
 cheek-0.005
 la-0.005
 mine-0.004
agging-0.004
Token-
Token ID12
Feature activation+4.92e+00

Pos logit contributions
 Pig+0.047
 known+0.044
 Tweet+0.043
 Ally+0.042
 Bert+0.041
Neg logit contributions
five-0.053
 cheek-0.052
agging-0.052
 mine-0.047
 fourteen-0.045
Tokenfed
Token ID19082
Feature activation+1.03e+00

Pos logit contributions
 Pig+0.213
 Tweet+0.192
 Bunny+0.189
 Beth+0.187
 Ally+0.187
Neg logit contributions
five-0.200
agging-0.178
 cheek-0.175
 fourteen-0.167
 goodness-0.158
Token the
Token ID262
Feature activation+4.94e-01

Pos logit contributions
 Pig+0.041
 known+0.039
 Beth+0.036
 Bert+0.035
 Ally+0.035
Neg logit contributions
five-0.043
 cheek-0.042
agging-0.040
 mine-0.039
 goodness-0.037
Token chickens
Token ID25972
Feature activation+8.83e-01

Pos logit contributions
 Pig+0.021
 Tweet+0.019
 Beth+0.019
 Bunny+0.019
 known+0.019
Neg logit contributions
five-0.020
agging-0.019
 cheek-0.019
 sidelines-0.017
 fourteen-0.017
Token her
Token ID607
Feature activation+1.93e-01

Pos logit contributions
 Pig+0.030
 Tweet+0.026
 Beth+0.026
 Bunny+0.025
 Ally+0.025
Neg logit contributions
five-0.042
agging-0.041
 cheek-0.040
 fourteen-0.037
 mine-0.037
Token kept
Token ID4030
Feature activation-2.46e-01

Pos logit contributions
 Pig+0.010
 Tweet+0.009
 known+0.009
 Beth+0.009
 Ally+0.009
Neg logit contributions
five-0.006
 cheek-0.006
agging-0.006
 mine-0.005
 Deal-0.005
Token jumping
Token ID14284
Feature activation-8.92e-01

Pos logit contributions
five+0.029
agging+0.029
 cheek+0.028
 mine+0.025
 goodness+0.025
Neg logit contributions
 Pig-0.035
gy-0.034
wood-0.032
 Ally-0.031
 Tweet-0.031
Token j
Token ID474
Feature activation+1.89e-01

Pos logit contributions
five+0.039
agging+0.037
 cheek+0.036
 mine+0.035
 fourteen+0.035
Neg logit contributions
 Pig-0.035
 known-0.033
 Beth-0.030
 Ally-0.030
gy-0.029
Tokenacks
Token ID4595
Feature activation-1.46e-02

Pos logit contributions
 Pig+0.010
 Tweet+0.009
 Beth+0.009
 Bunny+0.009
 Ally+0.009
Neg logit contributions
five-0.006
agging-0.005
 cheek-0.005
 fourteen-0.005
 Deal-0.005
Token and
Token ID290
Feature activation-3.25e-01

Pos logit contributions
five+0.001
agging+0.001
 cheek+0.001
 fourteen+0.001
 mine+0.001
Neg logit contributions
 Pig-0.001
 known-0.001
 Tweet-0.001
 Ally-0.001
gy-0.001
Token push
Token ID4574
Feature activation+8.04e-01

Pos logit contributions
five+0.014
 cheek+0.013
agging+0.012
 mine+0.012
 la+0.012
Neg logit contributions
 Pig-0.013
wood-0.011
 Tweet-0.011
gy-0.011
 Ally-0.011
Token-
Token ID12
Feature activation+4.86e+00

Pos logit contributions
 Pig+0.033
 known+0.032
gy+0.030
wood+0.029
 dam+0.029
Neg logit contributions
five-0.034
agging-0.031
 goodness-0.030
 cheek-0.030
 mine-0.030
Tokenups
Token ID4739
Feature activation+2.47e+00

Pos logit contributions
 Pig+0.212
 Tweet+0.192
 Beth+0.188
 Bunny+0.188
 Ally+0.186
Neg logit contributions
five-0.191
agging-0.182
 cheek-0.175
 fourteen-0.162
 mine-0.158
Token.
Token ID13
Feature activation+8.60e-02

Pos logit contributions
 Pig+0.082
 Tweet+0.074
 Ally+0.070
 Bunny+0.070
 known+0.070
Neg logit contributions
five-0.121
agging-0.117
 cheek-0.114
 fourteen-0.106
 mine-0.105
Token
Token ID198
Feature activation-1.49e-01

Pos logit contributions
 Pig+0.003
 known+0.003
gy+0.003
wood+0.003
 darker+0.003
Neg logit contributions
five-0.004
 Deal-0.003
 cheek-0.003
 goodness-0.003
agging-0.003
Token
Token ID198
Feature activation-2.01e-01

Pos logit contributions
five+0.008
agging+0.007
 cheek+0.007
 fourteen+0.007
 Deal+0.007
Neg logit contributions
 Pig-0.005
 Tweet-0.004
gy-0.004
wood-0.004
 Beth-0.004
TokenFinally
Token ID11158
Feature activation-2.00e-01

Pos logit contributions
 cheek+0.008
five+0.008
agging+0.008
 mine+0.007
 fourteen+0.007
Neg logit contributions
 Pig-0.008
 Tweet-0.007
 Beth-0.007
 Ally-0.007
 known-0.007
Token over
Token ID625
Feature activation+2.72e-01

Pos logit contributions
 Pig+0.043
 Tweet+0.038
 Beth+0.037
 Bunny+0.037
 Ally+0.036
Neg logit contributions
five-0.064
agging-0.062
 cheek-0.061
 fourteen-0.057
 Deal-0.056
Token and
Token ID290
Feature activation-6.98e-02

Pos logit contributions
 Pig+0.008
 Tweet+0.007
 Beth+0.007
 Bunny+0.007
 Ally+0.007
Neg logit contributions
five-0.014
agging-0.014
 cheek-0.013
 Deal-0.012
 sidelines-0.012
Token get
Token ID651
Feature activation+1.24e+00

Pos logit contributions
five+0.003
agging+0.003
 cheek+0.002
 fourteen+0.002
arl+0.002
Neg logit contributions
 Pig-0.003
 Tweet-0.003
 Beth-0.003
 Bunny-0.003
 Ally-0.003
Token some
Token ID617
Feature activation+1.65e-01

Pos logit contributions
 Pig+0.043
 Tweet+0.038
gy+0.038
 Ally+0.038
 Beth+0.038
Neg logit contributions
five-0.060
 cheek-0.056
agging-0.055
 mine-0.054
 fourteen-0.052
Token ice
Token ID4771
Feature activation+7.87e-01

Pos logit contributions
 Pig+0.007
 Tweet+0.006
 Bunny+0.006
wood+0.006
 Beth+0.006
Neg logit contributions
agging-0.006
five-0.006
 cheek-0.006
 la-0.005
 Deal-0.005
Token-
Token ID12
Feature activation+4.80e+00

Pos logit contributions
 Pig+0.031
wood+0.028
gy+0.028
 Tweet+0.028
 Bunny+0.027
Neg logit contributions
five-0.033
agging-0.033
 cheek-0.031
 sidelines-0.030
 Deal-0.030
Tokencream
Token ID36277
Feature activation-4.39e-01

Pos logit contributions
 Pig+0.212
 Tweet+0.192
 Beth+0.190
 Ally+0.189
 Bunny+0.189
Neg logit contributions
five-0.187
agging-0.173
 cheek-0.169
 fourteen-0.158
 mine-0.152
Token!
Token ID0
Feature activation+1.25e-01

Pos logit contributions
agging+0.019
five+0.018
 cheek+0.017
 Deal+0.016
 sidelines+0.016
Neg logit contributions
 Pig-0.017
wood-0.016
 Tweet-0.015
 Bunny-0.015
 Beth-0.015
Tokenâ
Token ID22940
Feature activation+7.19e-01

Pos logit contributions
 Pig+0.004
 known+0.004
gy+0.004
 Tweet+0.004
 Ally+0.003
Neg logit contributions
five-0.006
 cheek-0.006
agging-0.006
 Deal-0.005
 mine-0.005
Token
Token ID26391
Feature activation+9.15e-01

Pos logit contributions
 Pig+0.029
 Tweet+0.026
gy+0.026
wood+0.026
 Beth+0.025
Neg logit contributions
five-0.029
agging-0.028
 cheek-0.027
 fourteen-0.026
 Deal-0.026
Token So
Token ID1406
Feature activation+6.94e-01

Pos logit contributions
 Pig+0.038
 Tweet+0.034
 Beth+0.034
 Bunny+0.034
 Ally+0.033
Neg logit contributions
five-0.037
agging-0.036
 cheek-0.035
 fourteen-0.032
 mine-0.031
Token out
Token ID503
Feature activation-3.54e-01

Pos logit contributions
 Pig+0.037
 Tweet+0.033
 Beth+0.032
 Bunny+0.032
 Ally+0.032
Neg logit contributions
five-0.047
agging-0.046
 cheek-0.045
 fourteen-0.042
 mine-0.041
Token and
Token ID290
Feature activation-4.39e-01

Pos logit contributions
five+0.014
agging+0.014
 cheek+0.013
 mine+0.012
 liking+0.012
Neg logit contributions
 Pig-0.015
 Tweet-0.014
 Ally-0.013
 Beth-0.013
gy-0.013
Token collect
Token ID2824
Feature activation-3.57e-02

Pos logit contributions
five+0.017
 cheek+0.015
agging+0.015
 mine+0.014
 sidelines+0.014
Neg logit contributions
 Pig-0.019
 Tweet-0.017
 Beth-0.017
 Bunny-0.017
 Ally-0.017
Token some
Token ID617
Feature activation+1.27e-01

Pos logit contributions
five+0.001
agging+0.001
 mine+0.001
 cheek+0.001
 goodness+0.001
Neg logit contributions
 Pig-0.002
gy-0.002
 Beth-0.001
 Ally-0.001
 known-0.001
Token ice
Token ID4771
Feature activation+8.36e-01

Pos logit contributions
 Pig+0.005
 Tweet+0.005
 Beth+0.005
gy+0.005
 Bunny+0.005
Neg logit contributions
five-0.005
agging-0.005
 cheek-0.005
 mine-0.004
 fourteen-0.004
Token-
Token ID12
Feature activation+4.79e+00

Pos logit contributions
 Pig+0.043
 Tweet+0.039
 Beth+0.039
 Ally+0.038
 Bunny+0.038
Neg logit contributions
five-0.027
agging-0.025
 cheek-0.024
 fourteen-0.022
 mine-0.021
Tokencream
Token ID36277
Feature activation-3.20e-01

Pos logit contributions
 Pig+0.214
 Beth+0.192
 Tweet+0.192
 Ally+0.191
 Bunny+0.191
Neg logit contributions
five-0.185
agging-0.168
 cheek-0.164
 fourteen-0.156
 mine-0.150
Token.
Token ID13
Feature activation+4.96e-01

Pos logit contributions
five+0.015
agging+0.015
 cheek+0.015
 fourteen+0.014
 mine+0.013
Neg logit contributions
 Pig-0.011
 Tweet-0.010
 Beth-0.010
 Ally-0.009
 Bunny-0.009
Token He
Token ID679
Feature activation+4.16e-01

Pos logit contributions
 Pig+0.015
 Tweet+0.014
 Beth+0.013
 Bunny+0.013
gy+0.013
Neg logit contributions
five-0.025
agging-0.025
 cheek-0.024
 fourteen-0.022
 Deal-0.022
Token went
Token ID1816
Feature activation+5.07e-01

Pos logit contributions
 Pig+0.017
 Ally+0.016
 Tweet+0.016
 Beth+0.016
wood+0.016
Neg logit contributions
five-0.015
 mine-0.014
 cheek-0.013
ige-0.013
 picks-0.013
Token to
Token ID284
Feature activation-5.16e-01

Pos logit contributions
 Pig+0.018
 Tweet+0.016
 Beth+0.015
 Bunny+0.015
 Ally+0.015
Neg logit contributions
five-0.024
agging-0.023
 cheek-0.023
 fourteen-0.021
 mine-0.021
Token the
Token ID262
Feature activation-3.36e-01

Pos logit contributions
five+0.029
agging+0.028
 cheek+0.028
 mine+0.026
 sidelines+0.026
Neg logit contributions
 Pig-0.020
 Tweet-0.018
gy-0.018
wood-0.017
 known-0.017
Token yard
Token ID12699
Feature activation-7.63e-01

Pos logit contributions
five+0.015
agging+0.014
 cheek+0.014
 fourteen+0.013
 Deal+0.013
Neg logit contributions
 Pig-0.013
 Tweet-0.012
 Bunny-0.011
 Beth-0.011
 Ally-0.011
Token and
Token ID290
Feature activation-4.53e-02

Pos logit contributions
five+0.035
agging+0.034
 cheek+0.033
 fourteen+0.030
 sidelines+0.030
Neg logit contributions
 Pig-0.028
 Tweet-0.024
wood-0.024
 Ally-0.024
 Beth-0.024
Token even
Token ID772
Feature activation-7.25e-02

Pos logit contributions
five+0.002
 cheek+0.002
agging+0.002
 la+0.002
 sidelines+0.002
Neg logit contributions
 Pig-0.002
wood-0.002
 Tweet-0.002
 Ally-0.001
gy-0.001
Token zip
Token ID19974
Feature activation+1.79e+00

Pos logit contributions
five+0.003
 cheek+0.003
 la+0.003
agging+0.003
 liking+0.003
Neg logit contributions
 Pig-0.003
wood-0.003
 Bert-0.003
 Ally-0.002
 Tweet-0.002
Token-
Token ID12
Feature activation+4.78e+00

Pos logit contributions
 Pig+0.089
 known+0.082
 Ally+0.079
 dam+0.079
 Tweet+0.077
Neg logit contributions
five-0.058
agging-0.055
 cheek-0.051
 goodness-0.045
 mine-0.045
Tokenlined
Token ID10837
Feature activation+1.05e+00

Pos logit contributions
 Pig+0.201
 Ally+0.178
 Tweet+0.177
 Beth+0.177
 Bunny+0.176
Neg logit contributions
five-0.201
agging-0.177
 cheek-0.172
 fourteen-0.167
leaf-0.159
Token across
Token ID1973
Feature activation+1.05e-01

Pos logit contributions
 Pig+0.043
 known+0.038
 Tweet+0.038
 Beth+0.038
 Ally+0.037
Neg logit contributions
five-0.045
agging-0.042
 cheek-0.041
 mine-0.039
 fourteen-0.037
Token the
Token ID262
Feature activation-5.00e-01

Pos logit contributions
 Pig+0.004
gy+0.004
wood+0.004
 Ally+0.003
 Bunny+0.003
Neg logit contributions
five-0.004
 mine-0.004
agging-0.004
 liking-0.004
 goodness-0.004
Token driveway
Token ID33515
Feature activation-1.90e+00

Pos logit contributions
five+0.022
agging+0.021
 cheek+0.020
 Deal+0.019
 fourteen+0.019
Neg logit contributions
 Pig-0.020
 Tweet-0.017
 Bunny-0.017
gy-0.017
wood-0.017
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
five+0.083
agging+0.080
 cheek+0.079
 mine+0.072
 fourteen+0.072
Neg logit contributions
 Pig-0.074
 Tweet-0.066
 Bunny-0.065
 Ally-0.065
 Beth-0.063
Token "
Token ID366
Feature activation+8.14e-01

Pos logit contributions
five+0.005
 cheek+0.005
 wo+0.004
 fourteen+0.004
EEP+0.004
Neg logit contributions
 known-0.007
 Pig-0.007
wood-0.007
 increasingly-0.006
 shelters-0.006
TokenLet
Token ID5756
Feature activation-5.82e-01

Pos logit contributions
 Pig+0.030
 Tweet+0.029
 known+0.027
 Ally+0.027
wood+0.026
Neg logit contributions
agging-0.037
 cheek-0.034
five-0.033
 Deal-0.031
 mine-0.031
Token's
Token ID338
Feature activation+1.64e+00

Pos logit contributions
five+0.026
agging+0.026
 cheek+0.025
 fourteen+0.023
arl+0.023
Neg logit contributions
 Pig-0.022
 Tweet-0.020
 Bunny-0.019
 Beth-0.019
 Ally-0.019
Token play
Token ID711
Feature activation+2.46e-01

Pos logit contributions
 Pig+0.072
 known+0.065
 Tweet+0.065
 Beth+0.065
 Bunny+0.064
Neg logit contributions
five-0.062
agging-0.058
 cheek-0.057
 mine-0.054
 fourteen-0.052
Token tug
Token ID27762
Feature activation-8.43e-01

Pos logit contributions
 Pig+0.009
 Tweet+0.008
 Bunny+0.008
 Beth+0.008
 Ally+0.008
Neg logit contributions
five-0.011
agging-0.011
 cheek-0.011
 fourteen-0.010
 Deal-0.010
Token-
Token ID12
Feature activation+4.77e+00

Pos logit contributions
five+0.041
 cheek+0.039
agging+0.038
 Deal+0.038
 sidelines+0.037
Neg logit contributions
 Pig-0.027
 Tweet-0.024
 Bert-0.024
 Bunny-0.023
 Ch-0.023
Tokenof
Token ID1659
Feature activation+2.08e-01

Pos logit contributions
 Pig+0.233
 Tweet+0.214
 Beth+0.210
 Bunny+0.210
 Ally+0.208
Neg logit contributions
five-0.158
agging-0.153
 cheek-0.147
 fourteen-0.132
 Deal-0.130
Token-
Token ID12
Feature activation+4.58e+00

Pos logit contributions
 Pig+0.008
 Tweet+0.007
 Bunny+0.007
 Beth+0.006
 Ch+0.006
Neg logit contributions
five-0.009
agging-0.009
 cheek-0.009
 Deal-0.009
 sidelines-0.009
Tokenwar
Token ID5767
Feature activation-9.48e-02

Pos logit contributions
 Pig+0.226
 Tweet+0.209
 Beth+0.204
 Bunny+0.204
gy+0.202
Neg logit contributions
five-0.147
agging-0.144
 cheek-0.138
 Deal-0.123
 fourteen-0.122
Token!"
Token ID2474
Feature activation-4.99e-01

Pos logit contributions
five+0.004
agging+0.004
 cheek+0.004
 fourteen+0.003
 mine+0.003
Neg logit contributions
 Pig-0.004
 known-0.004
 Beth-0.004
 Ally-0.003
 Tweet-0.003
Token
Token ID198
Feature activation+4.92e-01

Pos logit contributions
five+0.021
 cheek+0.019
agging+0.017
EEP+0.016
 fourteen+0.016
Neg logit contributions
 Pig-0.020
 known-0.020
wood-0.019
 darker-0.018
gy-0.018
Token and
Token ID290
Feature activation-4.31e-01

Pos logit contributions
five+0.063
agging+0.062
 cheek+0.060
 fourteen+0.056
 mine+0.055
Neg logit contributions
 Pig-0.061
 Tweet-0.054
 Ally-0.053
 Beth-0.053
 Bunny-0.053
Token could
Token ID714
Feature activation+8.67e-01

Pos logit contributions
five+0.019
agging+0.017
 cheek+0.017
 mine+0.017
 fourteen+0.016
Neg logit contributions
 Pig-0.016
wood-0.014
 Tweet-0.014
gy-0.014
 Bunny-0.014
Token do
Token ID466
Feature activation+1.11e+00

Pos logit contributions
 Pig+0.037
 Tweet+0.033
 Beth+0.033
 Bunny+0.033
 Ally+0.032
Neg logit contributions
five-0.034
agging-0.033
 cheek-0.032
 fourteen-0.029
 mine-0.029
Token more
Token ID517
Feature activation+1.72e+00

Pos logit contributions
 Pig+0.045
wood+0.040
 Bunny+0.039
gy+0.038
 Tweet+0.038
Neg logit contributions
five-0.045
agging-0.044
 mine-0.042
 cheek-0.041
 goodness-0.040
Token push
Token ID4574
Feature activation+5.14e-01

Pos logit contributions
 Pig+0.068
 Tweet+0.060
gy+0.059
 Beth+0.059
 known+0.059
Neg logit contributions
five-0.074
agging-0.074
 cheek-0.069
 mine-0.065
 goodness-0.063
Token-
Token ID12
Feature activation+4.77e+00

Pos logit contributions
 Pig+0.021
 known+0.020
 dam+0.019
gy+0.018
 Tweet+0.018
Neg logit contributions
five-0.020
agging-0.020
 mine-0.019
 cheek-0.019
 goodness-0.018
Tokenups
Token ID4739
Feature activation+2.23e+00

Pos logit contributions
 Pig+0.209
 Bunny+0.189
 Beth+0.188
 Tweet+0.188
 Ally+0.184
Neg logit contributions
five-0.200
agging-0.177
 cheek-0.165
 fourteen-0.161
leaf-0.154
Token than
Token ID621
Feature activation+2.90e-01

Pos logit contributions
 Pig+0.078
 Tweet+0.070
 Bunny+0.067
 Beth+0.067
 Ally+0.067
Neg logit contributions
five-0.106
agging-0.103
 cheek-0.099
 mine-0.093
 fourteen-0.092
Token most
Token ID749
Feature activation+1.16e+00

Pos logit contributions
 Pig+0.011
 Tweet+0.009
gy+0.009
 Ally+0.009
 Bunny+0.009
Neg logit contributions
five-0.013
agging-0.013
 cheek-0.012
 fourteen-0.012
 mine-0.012
Token adults
Token ID6490
Feature activation+6.72e-01

Pos logit contributions
 Pig+0.043
 Tweet+0.038
 Beth+0.037
 Bunny+0.037
 Ally+0.037
Neg logit contributions
five-0.053
agging-0.051
 cheek-0.050
 fourteen-0.046
 mine-0.046
Token.
Token ID13
Feature activation+3.21e-01

Pos logit contributions
 Pig+0.024
 Tweet+0.022
 Bunny+0.021
gy+0.021
 Beth+0.021
Neg logit contributions
five-0.031
agging-0.030
 cheek-0.029
 mine-0.027
 fourteen-0.027
Token to
Token ID284
Feature activation+3.56e-01

Pos logit contributions
 Pig+0.056
 known+0.049
 Bunny+0.048
 Bert+0.047
 Tweet+0.047
Neg logit contributions
five-0.058
agging-0.055
 cheek-0.054
 mine-0.051
arl-0.048
Token read
Token ID1100
Feature activation+8.35e-01

Pos logit contributions
 Pig+0.012
 Tweet+0.011
 Beth+0.010
 known+0.010
 Ally+0.010
Neg logit contributions
five-0.017
agging-0.017
 cheek-0.016
 fourteen-0.015
arl-0.015
Token in
Token ID287
Feature activation+1.12e+00

Pos logit contributions
 Pig+0.033
wood+0.029
gy+0.029
 Bunny+0.028
 known+0.028
Neg logit contributions
five-0.037
agging-0.034
 cheek-0.033
 mine-0.033
 fourteen-0.031
Token her
Token ID607
Feature activation+1.21e+00

Pos logit contributions
 Pig+0.037
 Tweet+0.032
 Bunny+0.032
gy+0.031
 Beth+0.031
Neg logit contributions
five-0.055
agging-0.054
 cheek-0.052
 mine-0.049
 fourteen-0.049
Token tree
Token ID5509
Feature activation+3.76e-01

Pos logit contributions
 Pig+0.054
 Tweet+0.049
 Bunny+0.048
 Beth+0.048
gy+0.047
Neg logit contributions
five-0.045
agging-0.044
 cheek-0.042
 fourteen-0.039
 sidelines-0.038
Token-
Token ID12
Feature activation+4.77e+00

Pos logit contributions
 Pig+0.016
 known+0.014
 Bert+0.014
 Beth+0.014
wood+0.014
Neg logit contributions
five-0.014
agging-0.014
 cheek-0.014
 mine-0.013
 la-0.012
Tokenhouse
Token ID4803
Feature activation+2.85e+00

Pos logit contributions
 Pig+0.195
 Tweet+0.175
 Beth+0.172
 Bunny+0.171
 Ally+0.169
Neg logit contributions
five-0.198
agging-0.190
 cheek-0.184
 fourteen-0.170
 mine-0.168
Token.
Token ID13
Feature activation+1.89e-01

Pos logit contributions
 Pig+0.129
 known+0.115
 Bert+0.114
 Ally+0.113
 Beth+0.112
Neg logit contributions
five-0.103
 mine-0.096
 cheek-0.096
agging-0.095
 fourteen-0.086
Token
Token ID198
Feature activation-3.97e-02

Pos logit contributions
 Pig+0.005
 Tweet+0.004
 Bunny+0.004
 Ally+0.004
 Beth+0.004
Neg logit contributions
agging-0.010
five-0.010
 cheek-0.010
 sidelines-0.009
 fourteen-0.009
Token
Token ID198
Feature activation-1.39e-01

Pos logit contributions
five+0.002
agging+0.002
 cheek+0.002
 fourteen+0.002
 Deal+0.002
Neg logit contributions
 Pig-0.001
 Tweet-0.001
 Beth-0.001
wood-0.001
 Bunny-0.001
TokenOne
Token ID3198
Feature activation-2.60e-01

Pos logit contributions
 cheek+0.007
agging+0.007
arl+0.007
five+0.007
 sidelines+0.007
Neg logit contributions
 Tweet-0.004
 Ally-0.004
 known-0.004
 Pig-0.004
 Bunny-0.004
Token They
Token ID1119
Feature activation-2.96e-02

Pos logit contributions
 known+0.004
 Pig+0.004
wood+0.004
gy+0.004
 Bert+0.004
Neg logit contributions
five-0.004
 cheek-0.004
 mine-0.004
agging-0.004
arl-0.004
Token decided
Token ID3066
Feature activation-1.05e+00

Pos logit contributions
five+0.001
agging+0.001
 cheek+0.001
 fourteen+0.001
 mine+0.001
Neg logit contributions
 Pig-0.001
 Tweet-0.001
 Beth-0.001
 Bunny-0.001
wood-0.001
Token to
Token ID284
Feature activation-4.89e-01

Pos logit contributions
five+0.049
agging+0.047
 cheek+0.046
 mine+0.043
 fourteen+0.043
Neg logit contributions
 Pig-0.037
 Tweet-0.033
 Bunny-0.032
 Beth-0.032
wood-0.032
Token play
Token ID711
Feature activation+2.11e-01

Pos logit contributions
five+0.018
 cheek+0.016
agging+0.016
 mine+0.015
 sidelines+0.014
Neg logit contributions
 Pig-0.023
 known-0.020
 Tweet-0.020
 Bunny-0.020
 Beth-0.020
Token tug
Token ID27762
Feature activation-8.35e-01

Pos logit contributions
 Pig+0.007
 Tweet+0.006
 Beth+0.006
 Bunny+0.006
wood+0.006
Neg logit contributions
five-0.010
agging-0.010
 cheek-0.009
 fourteen-0.009
 mine-0.009
Token-
Token ID12
Feature activation+4.77e+00

Pos logit contributions
five+0.040
agging+0.039
 cheek+0.038
 fourteen+0.035
 Deal+0.035
Neg logit contributions
 Pig-0.029
 Tweet-0.025
 Beth-0.025
 Bunny-0.025
 Ally-0.024
Tokenof
Token ID1659
Feature activation+2.07e-01

Pos logit contributions
 Pig+0.225
 Tweet+0.205
 Bunny+0.202
 Beth+0.202
 Ally+0.200
Neg logit contributions
five-0.171
agging-0.160
 cheek-0.153
 fourteen-0.141
 mine-0.137
Token-
Token ID12
Feature activation+4.58e+00

Pos logit contributions
 Pig+0.007
 Tweet+0.006
 Beth+0.006
 Bunny+0.006
 Ally+0.006
Neg logit contributions
five-0.010
agging-0.010
 cheek-0.009
 fourteen-0.009
 Deal-0.009
Tokenwar
Token ID5767
Feature activation-2.17e-01

Pos logit contributions
 Pig+0.216
 Tweet+0.196
 Beth+0.193
 Bunny+0.193
 Ally+0.191
Neg logit contributions
five-0.164
agging-0.155
 cheek-0.149
 fourteen-0.136
 mine-0.133
Token with
Token ID351
Feature activation+9.71e-01

Pos logit contributions
five+0.009
agging+0.009
 cheek+0.009
 mine+0.007
ater+0.007
Neg logit contributions
 Pig-0.009
 known-0.009
 Ally-0.008
 Beth-0.008
 Bunny-0.008
Token it
Token ID340
Feature activation+7.24e-01

Pos logit contributions
 Pig+0.038
wood+0.036
 known+0.036
gy+0.034
 Bunny+0.032
Neg logit contributions
five-0.041
agging-0.037
 mine-0.037
 cheek-0.037
 goodness-0.036
Token had
Token ID550
Feature activation-3.62e-01

Pos logit contributions
 mine+0.030
five+0.030
 cheek+0.030
 la+0.028
 liking+0.028
Neg logit contributions
 Pig-0.033
wood-0.032
 shelters-0.029
 dam-0.028
 Ally-0.028
Token found
Token ID1043
Feature activation-7.41e-01

Pos logit contributions
five+0.016
agging+0.015
 mine+0.015
 cheek+0.015
 fourteen+0.014
Neg logit contributions
 Pig-0.013
 Beth-0.012
 Ally-0.012
wood-0.012
 Tweet-0.012
Token the
Token ID262
Feature activation-4.25e-01

Pos logit contributions
five+0.028
 goodness+0.028
 mine+0.028
 arrest+0.026
 yours+0.025
Neg logit contributions
 known-0.026
 Pig-0.026
 rou-0.025
house-0.025
gy-0.024
Token l
Token ID300
Feature activation-2.14e+00

Pos logit contributions
five+0.016
agging+0.016
 cheek+0.015
 fourteen+0.014
 Deal+0.014
Neg logit contributions
 Pig-0.019
 Tweet-0.017
 Bunny-0.017
 known-0.017
 Beth-0.017
Tokenily
Token ID813
Feature activation-5.40e-01

Pos logit contributions
 cheek+0.083
five+0.080
 sidelines+0.073
 Deal+0.073
 fourteen+0.071
Neg logit contributions
 Tweet-0.086
 Pig-0.083
 Bunny-0.082
 Madd-0.077
 known-0.076
Token pad
Token ID14841
Feature activation-4.69e+00

Pos logit contributions
five+0.022
agging+0.021
 cheek+0.021
 Deal+0.019
 fourteen+0.019
Neg logit contributions
 Pig-0.022
 Tweet-0.020
 Bunny-0.020
gy-0.019
 Beth-0.019
Token again
Token ID757
Feature activation-1.03e+00

Pos logit contributions
five+0.233
agging+0.228
 Deal+0.218
 sidelines+0.216
 cheek+0.214
Neg logit contributions
 Pig-0.147
gy-0.139
 Tweet-0.134
house-0.128
wood-0.128
Token.
Token ID13
Feature activation-4.33e-01

Pos logit contributions
five+0.048
agging+0.047
 cheek+0.046
 fourteen+0.043
 mine+0.042
Neg logit contributions
 Pig-0.036
 Tweet-0.032
 Beth-0.031
 Bunny-0.031
 Ally-0.031
Token Bobby
Token ID17155
Feature activation-3.58e-01

Pos logit contributions
 cheek+0.018
five+0.018
agging+0.018
 mine+0.017
 goodness+0.017
Neg logit contributions
 known-0.015
 Pig-0.014
wood-0.013
gy-0.013
 darker-0.013
Token told
Token ID1297
Feature activation-7.53e-01

Pos logit contributions
 cheek+0.015
five+0.015
agging+0.014
 mine+0.013
 fourteen+0.013
Neg logit contributions
 Pig-0.012
wood-0.011
 known-0.011
 Beth-0.011
 darker-0.011
Token Freddy
Token ID45437
Feature activation-1.60e+00

Pos logit contributions
agging+0.025
 mine+0.025
 goodness+0.024
 cheek+0.024
five+0.024
Neg logit contributions
 known-0.032
house-0.031
wood-0.030
 darker-0.029
 attendants-0.029
Token to
Token ID284
Feature activation-9.79e-01

Pos logit contributions
 Pig+0.003
 Tweet+0.002
 known+0.002
 Beth+0.002
 Ally+0.002
Neg logit contributions
five-0.003
agging-0.003
 cheek-0.003
 mine-0.003
arl-0.002
Token find
Token ID1064
Feature activation-1.41e+00

Pos logit contributions
five+0.038
 cheek+0.035
 mine+0.035
 arrest+0.034
 sidelines+0.034
Neg logit contributions
 Pig-0.036
wood-0.035
 darker-0.035
 rou-0.034
 known-0.034
Token the
Token ID262
Feature activation-3.60e-01

Pos logit contributions
five+0.063
agging+0.057
 cheek+0.055
 goodness+0.055
 mine+0.054
Neg logit contributions
gy-0.044
wood-0.043
 Pig-0.043
 known-0.042
 rou-0.042
Token l
Token ID300
Feature activation-2.00e+00

Pos logit contributions
five+0.014
agging+0.014
 cheek+0.014
 mine+0.013
 fourteen+0.012
Neg logit contributions
 Pig-0.015
 Beth-0.014
gy-0.013
wood-0.013
 Ally-0.013
Tokenily
Token ID813
Feature activation-5.61e-01

Pos logit contributions
 cheek+0.075
five+0.074
 fourteen+0.067
 sidelines+0.067
 Deal+0.066
Neg logit contributions
 Tweet-0.082
 Pig-0.080
 Bunny-0.078
 known-0.074
 Madd-0.074
Token pad
Token ID14841
Feature activation-4.67e+00

Pos logit contributions
five+0.024
agging+0.023
 cheek+0.023
 mine+0.021
 fourteen+0.020
Neg logit contributions
 Pig-0.022
 Tweet-0.020
 Beth-0.020
 Ally-0.019
 known-0.019
Token.
Token ID13
Feature activation-4.75e-01

Pos logit contributions
five+0.233
agging+0.227
 cheek+0.218
 fourteen+0.211
 Deal+0.211
Neg logit contributions
 Pig-0.147
 Tweet-0.132
gy-0.129
 Bunny-0.126
wood-0.124
Token He
Token ID679
Feature activation+9.00e-02

Pos logit contributions
five+0.018
 cheek+0.018
 mine+0.017
agging+0.016
 sidelines+0.016
Neg logit contributions
 known-0.019
 Pig-0.019
 Ally-0.016
 darker-0.016
gy-0.016
Token searched
Token ID16499
Feature activation-1.12e-01

Pos logit contributions
wood+0.004
ained+0.004
 Pig+0.004
 darker+0.004
bul+0.004
Neg logit contributions
 mine-0.002
 cheek-0.002
five-0.002
 liking-0.002
 wo-0.002
Token and
Token ID290
Feature activation+2.07e-01

Pos logit contributions
agging+0.004
five+0.004
 cheek+0.004
 mine+0.004
 fourteen+0.004
Neg logit contributions
 Pig-0.005
wood-0.004
 Beth-0.004
 known-0.004
 Tweet-0.004
Token searched
Token ID16499
Feature activation+7.91e-01

Pos logit contributions
 Pig+0.006
wood+0.005
 known+0.005
 attendants+0.005
 Kang+0.005
Neg logit contributions
five-0.010
 cheek-0.009
 mine-0.009
agging-0.009
 sidelines-0.009
Token big
Token ID1263
Feature activation+2.73e-01

Pos logit contributions
 cheek+0.009
 mine+0.009
five+0.009
agging+0.009
 liking+0.008
Neg logit contributions
 Pig-0.011
wood-0.010
 Beth-0.010
 known-0.010
gy-0.009
Token,
Token ID11
Feature activation-1.39e+00

Pos logit contributions
 Pig+0.010
 known+0.009
 Beth+0.009
wood+0.008
 Ally+0.008
Neg logit contributions
five-0.012
agging-0.012
 cheek-0.012
 mine-0.012
 sidelines-0.011
Token beautiful
Token ID4950
Feature activation+7.85e-02

Pos logit contributions
 cheek+0.056
five+0.055
agging+0.055
 mine+0.052
 la+0.049
Neg logit contributions
 Pig-0.055
wood-0.051
 known-0.051
gy-0.050
 Beth-0.050
Token l
Token ID300
Feature activation-1.89e+00

Pos logit contributions
 Pig+0.003
 known+0.003
wood+0.003
 Beth+0.003
gy+0.002
Neg logit contributions
agging-0.003
 cheek-0.003
five-0.003
 mine-0.003
 la-0.003
Tokenily
Token ID813
Feature activation-4.13e-01

Pos logit contributions
five+0.071
 cheek+0.071
 sidelines+0.065
 fourteen+0.063
 Deal+0.063
Neg logit contributions
 Pig-0.078
 Tweet-0.076
 Bunny-0.073
 known-0.072
 Bert-0.070
Token pad
Token ID14841
Feature activation-4.63e+00

Pos logit contributions
five+0.019
agging+0.018
 cheek+0.018
 fourteen+0.016
 mine+0.016
Neg logit contributions
 Pig-0.015
 Tweet-0.014
 Beth-0.013
 Bunny-0.013
 Ally-0.013
Token that
Token ID326
Feature activation+5.30e-01

Pos logit contributions
five+0.229
 Deal+0.221
 sidelines+0.221
agging+0.220
 fourteen+0.212
Neg logit contributions
 Pig-0.143
gy-0.140
 Tweet-0.130
house-0.129
 Bunny-0.125
Token he
Token ID339
Feature activation-6.30e-01

Pos logit contributions
wood+0.021
 Pig+0.021
gy+0.020
 dam+0.019
 increasingly+0.019
Neg logit contributions
 mine-0.019
five-0.018
 cheek-0.018
 wo-0.017
 la-0.016
Token found
Token ID1043
Feature activation-1.29e+00

Pos logit contributions
five+0.025
agging+0.024
 cheek+0.023
 mine+0.023
 la+0.022
Neg logit contributions
 Pig-0.026
wood-0.024
 Beth-0.023
 Ally-0.023
 Tweet-0.023
Token in
Token ID287
Feature activation-6.01e-01

Pos logit contributions
five+0.060
agging+0.059
 cheek+0.057
 mine+0.054
 goodness+0.053
Neg logit contributions
 Pig-0.045
 Beth-0.039
 Ally-0.039
gy-0.039
wood-0.038
Token the
Token ID262
Feature activation-2.32e-01

Pos logit contributions
 mine+0.024
five+0.024
 arrest+0.024
agging+0.024
 cheek+0.023
Neg logit contributions
 Pig-0.021
wood-0.020
 Ally-0.019
gy-0.019
 Beth-0.018
Token,
Token ID11
Feature activation-3.09e-01

Pos logit contributions
 Pig+0.019
 Tweet+0.017
gy+0.017
 Beth+0.017
 Ally+0.017
Neg logit contributions
five-0.022
agging-0.021
 cheek-0.021
 mine-0.020
 fourteen-0.019
Token you
Token ID345
Feature activation-9.62e-01

Pos logit contributions
five+0.013
agging+0.012
 cheek+0.012
 mine+0.011
 fourteen+0.011
Neg logit contributions
 Pig-0.013
 Tweet-0.011
 Beth-0.011
gy-0.011
 Bunny-0.011
Tokenâ
Token ID22940
Feature activation-8.07e-02

Pos logit contributions
five+0.037
agging+0.034
 cheek+0.034
 mine+0.031
 fourteen+0.031
Neg logit contributions
 Pig-0.042
 Tweet-0.039
 Beth-0.038
 Ally-0.037
gy-0.037
Token
Token ID26391
Feature activation+4.95e-01

Pos logit contributions
five+0.003
agging+0.003
 cheek+0.003
 fourteen+0.003
 Deal+0.002
Neg logit contributions
 Pig-0.004
 Tweet-0.003
 Beth-0.003
 Bunny-0.003
 Ally-0.003
Token
Token ID8151
Feature activation+7.84e-01

Pos logit contributions
 Pig+0.023
 Tweet+0.021
wood+0.020
 Ally+0.020
 Bunny+0.020
Neg logit contributions
five-0.018
agging-0.016
 cheek-0.016
 la-0.015
 fourteen-0.015
Tokenll
Token ID297
Feature activation-4.59e+00

Pos logit contributions
 Pig+0.034
 Tweet+0.030
 Beth+0.030
 Bunny+0.030
 Ally+0.030
Neg logit contributions
five-0.031
agging-0.029
 cheek-0.028
 fourteen-0.026
 mine-0.026
Token always
Token ID1464
Feature activation-2.18e-01

Pos logit contributions
five+0.189
agging+0.183
 cheek+0.176
 fourteen+0.164
 Deal+0.162
Neg logit contributions
 Pig-0.187
 Tweet-0.168
 Beth-0.165
 Bunny-0.164
gy-0.164
Token have
Token ID423
Feature activation-6.66e-01

Pos logit contributions
five+0.009
agging+0.008
 cheek+0.008
 mine+0.008
 fourteen+0.008
Neg logit contributions
 Pig-0.009
 Tweet-0.008
 Beth-0.008
 Ally-0.008
 Bunny-0.008
Token your
Token ID534
Feature activation-4.78e-01

Pos logit contributions
five+0.032
agging+0.031
 cheek+0.030
 mine+0.028
 fourteen+0.028
Neg logit contributions
 Pig-0.023
 Tweet-0.020
 Beth-0.020
 Bunny-0.019
gy-0.019
Token memories
Token ID9846
Feature activation-9.87e-01

Pos logit contributions
five+0.018
agging+0.018
 cheek+0.017
 mine+0.016
 fourteen+0.016
Neg logit contributions
 Pig-0.021
 Tweet-0.019
 Beth-0.018
 Ally-0.018
 Bunny-0.018
Token of
Token ID286
Feature activation+8.52e-01

Pos logit contributions
five+0.046
agging+0.045
 cheek+0.043
 sidelines+0.041
 Deal+0.041
Neg logit contributions
 Pig-0.034
 Tweet-0.030
 Beth-0.030
 Bunny-0.030
wood-0.030
Token It
Token ID632
Feature activation+7.44e-01

Pos logit contributions
 Pig+0.010
gy+0.009
wood+0.009
 darker+0.009
 Tweet+0.009
Neg logit contributions
five-0.011
 Deal-0.009
 cheek-0.009
 goodness-0.009
agging-0.009
Token became
Token ID2627
Feature activation+8.37e-02

Pos logit contributions
 Pig+0.025
 Tweet+0.023
wood+0.023
 Beth+0.022
gy+0.022
Neg logit contributions
five-0.034
 cheek-0.032
agging-0.031
 mine-0.029
 la-0.029
Token the
Token ID262
Feature activation-8.41e-01

Pos logit contributions
bank+0.004
gy+0.004
wood+0.003
stal+0.003
storms+0.003
Neg logit contributions
 mine-0.003
 yours-0.002
 my-0.002
 ours-0.002
 love-0.002
Token happiest
Token ID49414
Feature activation-7.88e-01

Pos logit contributions
 cheek+0.042
five+0.041
agging+0.041
 mine+0.039
 Deal+0.038
Neg logit contributions
 Pig-0.026
 Tweet-0.024
gy-0.024
 Beth-0.023
 Ally-0.022
Token books
Token ID3835
Feature activation-1.84e+00

Pos logit contributions
five+0.035
agging+0.034
 cheek+0.033
 mine+0.030
 fourteen+0.030
Neg logit contributions
 Pig-0.030
 Tweet-0.027
gy-0.026
wood-0.026
 Bunny-0.026
Tokenhe
Token ID258
Feature activation-4.55e+00

Pos logit contributions
five+0.082
agging+0.080
 cheek+0.077
 Deal+0.073
 fourteen+0.073
Neg logit contributions
 Pig-0.068
 Tweet-0.060
 Beth-0.059
 Bunny-0.059
 Ally-0.058
Tokenlf
Token ID1652
Feature activation-6.99e-01

Pos logit contributions
five+0.160
agging+0.145
 Deal+0.142
arl+0.140
 cheek+0.138
Neg logit contributions
 Pig-0.217
gy-0.199
 Tweet-0.198
 Bunny-0.197
 Beth-0.196
Token in
Token ID287
Feature activation-1.61e+00

Pos logit contributions
five+0.028
agging+0.027
 cheek+0.027
 mine+0.024
 fourteen+0.023
Neg logit contributions
 Pig-0.029
 Tweet-0.026
 Bunny-0.026
 Beth-0.026
wood-0.026
Token the
Token ID262
Feature activation-1.29e+00

Pos logit contributions
agging+0.073
five+0.073
 mine+0.071
 cheek+0.070
 fourteen+0.069
Neg logit contributions
 Pig-0.051
wood-0.047
 Tweet-0.046
gy-0.045
 Beth-0.045
Token world
Token ID995
Feature activation+2.28e-01

Pos logit contributions
five+0.067
agging+0.066
 cheek+0.063
 fourteen+0.060
arl+0.059
Neg logit contributions
 Pig-0.039
 Tweet-0.034
 Beth-0.034
 Bunny-0.033
gy-0.033
Token!
Token ID0
Feature activation-5.11e-01

Pos logit contributions
 Pig+0.009
 Tweet+0.008
 Bunny+0.008
 known+0.008
 Beth+0.008
Neg logit contributions
five-0.010
agging-0.009
 cheek-0.009
 mine-0.008
 fourteen-0.008
Token before
Token ID878
Feature activation+4.27e-01

Pos logit contributions
five+0.031
agging+0.030
 cheek+0.029
 fourteen+0.027
 Deal+0.026
Neg logit contributions
 Pig-0.033
 Tweet-0.030
 Beth-0.029
 Bunny-0.029
 Ally-0.029
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
 Pig+0.016
 Tweet+0.014
 Beth+0.014
 Bunny+0.014
 Ally+0.013
Neg logit contributions
five-0.019
agging-0.019
 cheek-0.018
 fourteen-0.017
 Deal-0.017
Token This
Token ID770
Feature activation+8.63e-02

Pos logit contributions
five+0.005
agging+0.004
 cheek+0.004
 fourteen+0.004
 Deal+0.004
Neg logit contributions
 Pig-0.006
 Tweet-0.005
 Beth-0.005
 Bunny-0.005
gy-0.005
Token is
Token ID318
Feature activation+3.41e-01

Pos logit contributions
 Pig+0.004
 Tweet+0.004
 Beth+0.004
 Bunny+0.004
gy+0.004
Neg logit contributions
five-0.003
 cheek-0.003
agging-0.003
 mine-0.002
 la-0.002
Token O
Token ID440
Feature activation-6.73e-01

Pos logit contributions
 Pig+0.013
gy+0.013
wood+0.012
 Beth+0.012
 Tweet+0.012
Neg logit contributions
 mine-0.014
five-0.013
 fourteen-0.013
 cheek-0.012
agging-0.012
Tokenll
Token ID297
Feature activation-4.54e+00

Pos logit contributions
five+0.028
agging+0.027
 cheek+0.026
 fourteen+0.024
 Deal+0.024
Neg logit contributions
 Pig-0.027
 Tweet-0.024
 Bunny-0.024
 Beth-0.024
gy-0.024
Tokenie
Token ID494
Feature activation-7.44e-01

Pos logit contributions
five+0.195
agging+0.182
 Deal+0.177
 cheek+0.173
 sidelines+0.172
Neg logit contributions
 Pig-0.182
 Ally-0.164
gy-0.162
 Tweet-0.162
 Beth-0.157
Token,
Token ID11
Feature activation-1.39e+00

Pos logit contributions
five+0.029
agging+0.028
 cheek+0.028
 mine+0.026
 la+0.025
Neg logit contributions
 Pig-0.031
 Tweet-0.029
 Beth-0.028
 known-0.028
wood-0.028
Token the
Token ID262
Feature activation-1.12e+00

Pos logit contributions
five+0.059
agging+0.057
 cheek+0.057
 mine+0.053
 la+0.052
Neg logit contributions
 Pig-0.053
 Tweet-0.047
gy-0.047
wood-0.047
 Beth-0.047
Token ostr
Token ID42387
Feature activation-2.20e+00

Pos logit contributions
five+0.046
agging+0.044
 cheek+0.043
 fourteen+0.040
 mine+0.039
Neg logit contributions
 Pig-0.046
 Tweet-0.041
 Beth-0.041
 Bunny-0.040
gy-0.040
Tokenich
Token ID488
Feature activation-1.14e+00

Pos logit contributions
five+0.090
 mine+0.079
 sidelines+0.078
 cheek+0.077
 Deal+0.076
Neg logit contributions
 Pig-0.094
gy-0.090
 Tweet-0.084
wood-0.081
 Ch-0.081
Token,
Token ID11
Feature activation-6.70e-01

Pos logit contributions
 cheek+0.035
five+0.034
agging+0.032
 mine+0.032
 goodness+0.031
Neg logit contributions
 Pig-0.029
 known-0.026
 Tweet-0.026
 Ally-0.026
 Bert-0.025
Token we
Token ID356
Feature activation-7.88e-01

Pos logit contributions
five+0.028
 cheek+0.026
agging+0.026
 mine+0.025
 fourteen+0.024
Neg logit contributions
 Pig-0.026
gy-0.024
wood-0.024
 known-0.023
 Tweet-0.023
Tokenâ
Token ID22940
Feature activation+5.93e-02

Pos logit contributions
five+0.029
agging+0.027
 cheek+0.027
 mine+0.026
 Deal+0.025
Neg logit contributions
 Pig-0.034
 Tweet-0.031
gy-0.031
wood-0.030
 Ally-0.030
Token
Token ID26391
Feature activation+5.75e-01

Pos logit contributions
 Pig+0.003
 Tweet+0.002
 Bunny+0.002
 Beth+0.002
 Ally+0.002
Neg logit contributions
five-0.002
agging-0.002
 cheek-0.002
 fourteen-0.002
 sidelines-0.002
Token
Token ID8151
Feature activation+1.08e+00

Pos logit contributions
 Pig+0.025
 Tweet+0.023
wood+0.022
 Bunny+0.022
 Beth+0.022
Neg logit contributions
five-0.022
agging-0.021
 cheek-0.021
 la-0.019
 fourteen-0.019
Tokenll
Token ID297
Feature activation-4.53e+00

Pos logit contributions
 Pig+0.046
 Tweet+0.041
 Beth+0.040
 Bunny+0.040
 Ally+0.040
Neg logit contributions
five-0.043
agging-0.041
 cheek-0.040
 fourteen-0.037
 mine-0.036
Token mention
Token ID3068
Feature activation+9.59e-02

Pos logit contributions
five+0.186
agging+0.179
 cheek+0.172
 fourteen+0.160
 Deal+0.158
Neg logit contributions
 Pig-0.186
 Tweet-0.168
 Beth-0.165
 Bunny-0.165
gy-0.163
Token it
Token ID340
Feature activation+1.18e-01

Pos logit contributions
 Pig+0.004
 Tweet+0.003
gy+0.003
 Beth+0.003
 Bunny+0.003
Neg logit contributions
five-0.004
agging-0.004
 cheek-0.004
 fourteen-0.004
 mine-0.004
Token to
Token ID284
Feature activation+7.96e-02

Pos logit contributions
 Pig+0.004
 Tweet+0.004
 known+0.004
 Beth+0.004
 Ally+0.004
Neg logit contributions
five-0.005
 cheek-0.005
agging-0.005
 mine-0.005
 fourteen-0.005
Token the
Token ID262
Feature activation+8.36e-02

Pos logit contributions
 Pig+0.003
 Tweet+0.003
gy+0.003
wood+0.003
 Beth+0.003
Neg logit contributions
five-0.003
agging-0.003
 cheek-0.003
 mine-0.003
 fourteen-0.003
Token grown
Token ID7334
Feature activation+2.57e-01

Pos logit contributions
 Pig+0.004
 Tweet+0.003
 Beth+0.003
gy+0.003
 Ally+0.003
Neg logit contributions
five-0.003
agging-0.003
 cheek-0.003
 mine-0.003
 fourteen-0.003
Token key
Token ID1994
Feature activation-2.97e-01

Pos logit contributions
 Pig+0.011
 Tweet+0.010
 Bunny+0.009
 Ally+0.009
 Beth+0.009
Neg logit contributions
five-0.014
agging-0.013
 fourteen-0.012
 la-0.012
 cheek-0.012
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
five+0.015
agging+0.014
 cheek+0.014
 fourteen+0.013
 Deal+0.013
Neg logit contributions
 Pig-0.010
 Tweet-0.009
 Beth-0.008
 Bunny-0.008
 Ally-0.008
Token She
Token ID1375
Feature activation+3.32e-01

Pos logit contributions
 Pig+0.003
 Tweet+0.003
 Bunny+0.003
gy+0.003
 Beth+0.003
Neg logit contributions
five-0.005
agging-0.005
 cheek-0.005
 fourteen-0.005
 Deal-0.005
Token unlocked
Token ID14838
Feature activation-6.05e-02

Pos logit contributions
 Pig+0.012
wood+0.012
 Tweet+0.011
 Ally+0.011
 Beth+0.011
Neg logit contributions
five-0.014
 cheek-0.013
 mine-0.012
agging-0.012
ige-0.012
Token the
Token ID262
Feature activation-6.86e-02

Pos logit contributions
five+0.003
agging+0.003
 cheek+0.003
 mine+0.003
 fourteen+0.003
Neg logit contributions
 Pig-0.002
wood-0.002
gy-0.002
 Bunny-0.002
 known-0.002
Token pad
Token ID14841
Feature activation-4.52e+00

Pos logit contributions
five+0.004
agging+0.003
 la+0.003
leaf+0.003
 fourteen+0.003
Neg logit contributions
 Pig-0.002
 shelter-0.002
 Tweet-0.002
gy-0.002
 Bunny-0.002
Tokenlock
Token ID5354
Feature activation-2.22e+00

Pos logit contributions
agging+0.233
five+0.229
 Deal+0.218
 sidelines+0.217
 la+0.215
Neg logit contributions
 Pig-0.132
gy-0.123
house-0.118
 Tweet-0.117
wood-0.113
Token and
Token ID290
Feature activation+2.11e-01

Pos logit contributions
five+0.108
agging+0.105
 cheek+0.102
 Deal+0.098
 fourteen+0.095
Neg logit contributions
 Pig-0.074
 Tweet-0.065
 Beth-0.063
gy-0.062
 Bunny-0.062
Token opened
Token ID4721
Feature activation+8.00e-01

Pos logit contributions
 Pig+0.007
 Tweet+0.006
wood+0.006
 Bunny+0.006
gy+0.006
Neg logit contributions
five-0.010
 cheek-0.009
agging-0.009
 fourteen-0.009
 mine-0.008
Token the
Token ID262
Feature activation+6.72e-01

Pos logit contributions
 Pig+0.027
 known+0.023
wood+0.023
 Tweet+0.023
 Bunny+0.022
Neg logit contributions
five-0.039
agging-0.036
 cheek-0.036
 mine-0.035
 fourteen-0.035
Token door
Token ID3420
Feature activation+5.25e-01

Pos logit contributions
 Pig+0.022
 shelter+0.020
wood+0.019
 Tweet+0.019
gy+0.018
Neg logit contributions
five-0.034
agging-0.034
 la-0.031
 sidelines-0.030
leaf-0.030
Token back
Token ID736
Feature activation-3.30e-01

Pos logit contributions
five+0.024
agging+0.023
 cheek+0.022
 fourteen+0.021
 mine+0.021
Neg logit contributions
 Pig-0.017
 Tweet-0.015
 Beth-0.014
 known-0.014
gy-0.014
Token onto
Token ID4291
Feature activation-1.19e+00

Pos logit contributions
five+0.015
agging+0.014
 cheek+0.014
 mine+0.013
arl+0.012
Neg logit contributions
 Pig-0.013
 known-0.011
 Tweet-0.011
 Beth-0.011
 Ally-0.011
Token his
Token ID465
Feature activation-1.10e-01

Pos logit contributions
five+0.053
 cheek+0.050
 fourteen+0.048
 mine+0.048
 sidelines+0.048
Neg logit contributions
 Pig-0.040
wood-0.038
gy-0.037
 known-0.037
house-0.037
Token l
Token ID300
Feature activation-1.93e+00

Pos logit contributions
five+0.005
 fourteen+0.005
leaf+0.004
agging+0.004
 Deal+0.004
Neg logit contributions
 Pig-0.004
 Bunny-0.004
 Tweet-0.004
gy-0.004
 Ch-0.004
Tokenily
Token ID813
Feature activation-4.14e-01

Pos logit contributions
 cheek+0.071
five+0.070
 mine+0.065
 sidelines+0.065
 fourteen+0.064
Neg logit contributions
 Pig-0.078
 Tweet-0.074
 Bunny-0.072
 known-0.071
 Ch-0.070
Token pad
Token ID14841
Feature activation-4.49e+00

Pos logit contributions
five+0.016
agging+0.016
 cheek+0.015
 fourteen+0.014
 Deal+0.014
Neg logit contributions
 Pig-0.018
 Tweet-0.016
 Bunny-0.016
gy-0.016
 Beth-0.015
Token and
Token ID290
Feature activation+1.81e-01

Pos logit contributions
five+0.232
agging+0.224
 sidelines+0.214
 Deal+0.213
 fourteen+0.213
Neg logit contributions
 Pig-0.132
gy-0.119
 Tweet-0.117
 Bunny-0.112
wood-0.111
Token stood
Token ID6204
Feature activation+4.09e-01

Pos logit contributions
wood+0.007
 Pig+0.007
 Ally+0.006
 Bert+0.006
 Beth+0.006
Neg logit contributions
five-0.007
 cheek-0.007
 mine-0.006
 forehead-0.006
 la-0.006
Token there
Token ID612
Feature activation+1.30e+00

Pos logit contributions
 Pig+0.014
 Tweet+0.013
 Beth+0.013
 Ally+0.012
wood+0.012
Neg logit contributions
agging-0.019
five-0.019
 cheek-0.018
 mine-0.017
 fourteen-0.017
Token,
Token ID11
Feature activation-2.96e-01

Pos logit contributions
 Pig+0.052
 Beth+0.047
 Tweet+0.046
 Ally+0.046
wood+0.045
Neg logit contributions
five-0.055
agging-0.054
 cheek-0.053
 mine-0.047
 fourteen-0.047
Token feeling
Token ID4203
Feature activation-7.17e-01

Pos logit contributions
five+0.016
agging+0.015
 cheek+0.014
arl+0.014
 Deal+0.014
Neg logit contributions
 Pig-0.009
 Tweet-0.008
 Bunny-0.007
 known-0.007
 Beth-0.007
Token.
Token ID13
Feature activation-4.24e-01

Pos logit contributions
five+0.050
agging+0.050
 Deal+0.047
 cheek+0.047
 sidelines+0.046
Neg logit contributions
 Pig-0.036
 known-0.034
 Tweet-0.033
gy-0.032
 Bunny-0.031
Token I
Token ID314
Feature activation-4.51e-02

Pos logit contributions
five+0.019
 cheek+0.018
agging+0.018
 Deal+0.017
 fourteen+0.017
Neg logit contributions
 Pig-0.015
wood-0.013
 known-0.013
gy-0.013
 Tweet-0.013
Tokenâ
Token ID22940
Feature activation+7.50e-02

Pos logit contributions
five+0.002
 cheek+0.001
agging+0.001
 mine+0.001
 goodness+0.001
Neg logit contributions
 Pig-0.002
 Tweet-0.002
wood-0.002
 Ally-0.002
 Beth-0.002
Token
Token ID26391
Feature activation+6.41e-01

Pos logit contributions
 Pig+0.004
 Tweet+0.003
 Bunny+0.003
 Beth+0.003
 Ally+0.003
Neg logit contributions
five-0.003
agging-0.003
 cheek-0.002
 fourteen-0.002
 sidelines-0.002
Token
Token ID8151
Feature activation+8.52e-01

Pos logit contributions
 Pig+0.030
 Tweet+0.028
wood+0.028
 Bunny+0.027
 Beth+0.027
Neg logit contributions
five-0.022
agging-0.020
 cheek-0.020
 la-0.019
 goodness-0.018
Tokenll
Token ID297
Feature activation-4.48e+00

Pos logit contributions
 Pig+0.038
 Tweet+0.035
 Beth+0.034
 Bunny+0.034
 known+0.034
Neg logit contributions
five-0.031
agging-0.030
 cheek-0.029
 Deal-0.026
 sidelines-0.026
Token keep
Token ID1394
Feature activation-3.44e-01

Pos logit contributions
five+0.186
agging+0.178
 cheek+0.171
 fourteen+0.162
 Deal+0.160
Neg logit contributions
 Pig-0.182
 Tweet-0.164
 Beth-0.162
 Bunny-0.160
gy-0.160
Token her
Token ID607
Feature activation-7.01e-01

Pos logit contributions
five+0.014
agging+0.013
 cheek+0.013
 fourteen+0.012
 mine+0.012
Neg logit contributions
 Pig-0.015
 Tweet-0.013
 Beth-0.013
 Bunny-0.013
gy-0.013
Token obedient
Token ID41652
Feature activation-1.74e+00

Pos logit contributions
 cheek+0.029
five+0.028
agging+0.028
 mine+0.027
 Deal+0.025
Neg logit contributions
 Pig-0.028
 Tweet-0.025
 known-0.025
wood-0.025
 Ally-0.025
Token and
Token ID290
Feature activation-4.72e-01

Pos logit contributions
five+0.073
 cheek+0.071
agging+0.070
 mine+0.064
 la+0.062
Neg logit contributions
 Pig-0.068
 Tweet-0.063
 known-0.062
 Bert-0.060
 Beth-0.060
Token make
Token ID787
Feature activation+7.75e-01

Pos logit contributions
five+0.017
agging+0.016
 cheek+0.015
 mine+0.014
 fourteen+0.014
Neg logit contributions
 Pig-0.022
 Tweet-0.020
 Beth-0.020
 Bunny-0.020
gy-0.020
Token stayed
Token ID9658
Feature activation-5.00e-02

Pos logit contributions
five+0.020
 cheek+0.020
agging+0.019
 mine+0.018
 fourteen+0.018
Neg logit contributions
 Pig-0.019
wood-0.018
 Beth-0.018
 Tweet-0.017
 Ally-0.017
Token on
Token ID319
Feature activation-4.04e-01

Pos logit contributions
agging+0.002
 cheek+0.002
five+0.002
 mine+0.002
 goodness+0.002
Neg logit contributions
 Pig-0.002
 Tweet-0.002
wood-0.002
 Beth-0.002
 Bert-0.002
Token the
Token ID262
Feature activation-3.92e-01

Pos logit contributions
 mine+0.016
five+0.016
agging+0.015
 cheek+0.015
 arrest+0.015
Neg logit contributions
 Pig-0.015
wood-0.015
gy-0.013
 Beth-0.013
 known-0.013
Token l
Token ID300
Feature activation-2.07e+00

Pos logit contributions
five+0.018
 Deal+0.018
agging+0.017
arl+0.017
 la+0.016
Neg logit contributions
 Pig-0.014
 Tweet-0.013
 Bunny-0.013
 dam-0.012
 shelter-0.012
Tokenily
Token ID813
Feature activation-4.96e-01

Pos logit contributions
 cheek+0.074
five+0.073
 Deal+0.068
 mine+0.066
agging+0.066
Neg logit contributions
 Pig-0.089
 Tweet-0.085
 Bunny-0.081
house-0.080
 dam-0.079
Token pad
Token ID14841
Feature activation-4.46e+00

Pos logit contributions
five+0.017
agging+0.016
 cheek+0.016
 mine+0.014
 fourteen+0.014
Neg logit contributions
 Pig-0.023
 Tweet-0.022
 Beth-0.021
 known-0.021
 Ally-0.021
Token and
Token ID290
Feature activation+1.32e-02

Pos logit contributions
five+0.213
agging+0.207
 cheek+0.200
 fourteen+0.188
 Deal+0.187
Neg logit contributions
 Pig-0.152
 Tweet-0.135
 Bunny-0.131
 Beth-0.130
gy-0.130
Token watched
Token ID7342
Feature activation-9.30e-01

Pos logit contributions
 Pig+0.000
wood+0.000
 Beth+0.000
 Bert+0.000
 Ally+0.000
Neg logit contributions
five-0.001
 cheek-0.001
 mine-0.000
 fourteen-0.000
agging-0.000
Token the
Token ID262
Feature activation+2.65e-03

Pos logit contributions
five+0.044
 cheek+0.042
agging+0.042
 mine+0.039
 fourteen+0.038
Neg logit contributions
 Pig-0.032
 known-0.029
gy-0.029
wood-0.029
 Beth-0.027
Token butterfly
Token ID35113
Feature activation+5.50e-01

Pos logit contributions
 Pig+0.000
 Tweet+0.000
 Bunny+0.000
 Beth+0.000
 Ally+0.000
Neg logit contributions
five-0.000
agging-0.000
 cheek-0.000
 fourteen-0.000
 Deal-0.000
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
 Pig+0.022
 known+0.020
 Beth+0.020
wood+0.019
 Tweet+0.019
Neg logit contributions
five-0.023
 cheek-0.022
agging-0.022
 mine-0.020
 la-0.019
Token Bang
Token ID9801
Feature activation-1.14e+00

Pos logit contributions
five+0.021
agging+0.020
 cheek+0.019
 fourteen+0.017
 mine+0.017
Neg logit contributions
 Pig-0.033
 Tweet-0.030
 Beth-0.030
 Bunny-0.029
 Ally-0.029
Token!
Token ID0
Feature activation-7.39e-01

Pos logit contributions
five+0.045
agging+0.043
 cheek+0.043
 Deal+0.039
 sidelines+0.038
Neg logit contributions
 Pig-0.049
 Tweet-0.045
 Beth-0.044
 Bunny-0.044
 Bert-0.043
Token You
Token ID921
Feature activation+2.34e-01

Pos logit contributions
five+0.025
agging+0.025
 cheek+0.023
 fourteen+0.021
 sidelines+0.021
Neg logit contributions
 Pig-0.036
 Tweet-0.033
 Beth-0.032
 Bunny-0.032
gy-0.032
Token're
Token ID821
Feature activation-1.54e+00

Pos logit contributions
 Pig+0.010
 Tweet+0.009
gy+0.009
 Bunny+0.009
 Beth+0.009
Neg logit contributions
five-0.009
agging-0.009
 cheek-0.009
 sidelines-0.008
 Deal-0.008
Token under
Token ID739
Feature activation-1.11e+00

Pos logit contributions
agging+0.065
five+0.065
 mine+0.062
 cheek+0.062
 fourteen+0.059
Neg logit contributions
 Pig-0.059
 Beth-0.052
 Ally-0.052
wood-0.052
 Tweet-0.051
Token arrest
Token ID3251
Feature activation-4.46e+00

Pos logit contributions
five+0.031
agging+0.029
 cheek+0.028
 Deal+0.026
arl+0.024
Neg logit contributions
 Pig-0.062
 Tweet-0.060
 Bunny-0.058
 Ch-0.057
 Beth-0.057
Token!"
Token ID2474
Feature activation-5.61e-01

Pos logit contributions
agging+0.135
five+0.133
 cheek+0.128
 Deal+0.124
leaf+0.117
Neg logit contributions
 Pig-0.218
 Tweet-0.210
 Beth-0.200
 Bunny-0.199
gy-0.199
Token
Token ID198
Feature activation+4.68e-01

Pos logit contributions
five+0.024
 cheek+0.023
agging+0.022
 fourteen+0.021
 la+0.020
Neg logit contributions
 Pig-0.021
 known-0.020
wood-0.020
gy-0.019
 increasingly-0.018
Token
Token ID198
Feature activation+2.30e-01

Pos logit contributions
 Pig+0.016
wood+0.014
gy+0.014
 Tweet+0.013
 known+0.013
Neg logit contributions
five-0.022
agging-0.022
 cheek-0.021
 fourteen-0.020
arl-0.020
TokenTheir
Token ID14574
Feature activation-6.05e-01

Pos logit contributions
 Pig+0.010
 Tweet+0.009
 Beth+0.009
 Bunny+0.009
 Ally+0.009
Neg logit contributions
five-0.009
agging-0.009
 cheek-0.009
 fourteen-0.008
 mine-0.008
Token mom
Token ID1995
Feature activation+5.20e-01

Pos logit contributions
five+0.025
agging+0.025
 cheek+0.024
 mine+0.023
 fourteen+0.022
Neg logit contributions
 Pig-0.024
 Tweet-0.021
 Beth-0.021
 Ally-0.021
 known-0.021
Token found
Token ID1043
Feature activation-9.37e-01

Pos logit contributions
five+0.021
 fourteen+0.018
agging+0.018
 mine+0.018
 cheek+0.018
Neg logit contributions
 Pig-0.020
 Beth-0.018
wood-0.018
 Ally-0.018
 Tweet-0.018
Token a
Token ID257
Feature activation-3.79e-01

Pos logit contributions
five+0.042
 mine+0.038
agging+0.038
 cheek+0.038
 goodness+0.037
Neg logit contributions
 Pig-0.033
gy-0.030
 Ally-0.029
wood-0.029
 Beth-0.029
Token big
Token ID1263
Feature activation+2.67e-02

Pos logit contributions
five+0.015
 cheek+0.015
agging+0.014
 mine+0.014
 sidelines+0.013
Neg logit contributions
 Pig-0.016
 Tweet-0.014
 Beth-0.014
wood-0.014
 Ally-0.014
Token l
Token ID300
Feature activation-1.95e+00

Pos logit contributions
 Pig+0.001
 Tweet+0.001
 Bunny+0.001
 Beth+0.001
 Ally+0.001
Neg logit contributions
five-0.001
agging-0.001
 cheek-0.001
 fourteen-0.001
 Deal-0.001
Tokenily
Token ID813
Feature activation-4.21e-01

Pos logit contributions
 cheek+0.076
five+0.075
 Deal+0.070
 sidelines+0.067
 mine+0.067
Neg logit contributions
 Pig-0.070
 called-0.069
 known-0.066
 Tweet-0.066
 dam-0.065
Token pad
Token ID14841
Feature activation-4.46e+00

Pos logit contributions
five+0.012
agging+0.011
 cheek+0.010
 Deal+0.009
arl+0.009
Neg logit contributions
 Pig-0.023
 Tweet-0.021
gy-0.021
 Bunny-0.021
 Beth-0.021
Token.
Token ID13
Feature activation-6.03e-01

Pos logit contributions
five+0.231
agging+0.223
 Deal+0.219
 sidelines+0.217
 cheek+0.212
Neg logit contributions
 Pig-0.127
gy-0.123
 Tweet-0.117
wood-0.113
house-0.109
Token He
Token ID679
Feature activation-2.55e-01

Pos logit contributions
five+0.027
 cheek+0.025
agging+0.025
 Deal+0.024
 mine+0.024
Neg logit contributions
 Pig-0.021
 known-0.019
wood-0.019
gy-0.019
 darker-0.018
Token quickly
Token ID2952
Feature activation-2.21e+00

Pos logit contributions
five+0.010
 mine+0.010
 cheek+0.010
 fourteen+0.009
ige+0.009
Neg logit contributions
 Pig-0.010
wood-0.009
 Beth-0.009
 Ally-0.009
gy-0.008
Token hopped
Token ID45230
Feature activation-2.58e-01

Pos logit contributions
five+0.083
agging+0.074
 cheek+0.073
 mine+0.070
 fourteen+0.069
Neg logit contributions
 Pig-0.096
wood-0.089
 Beth-0.088
 known-0.087
 Bert-0.086
Token on
Token ID319
Feature activation+2.98e-01

Pos logit contributions
five+0.012
agging+0.012
 cheek+0.011
 mine+0.011
 fourteen+0.011
Neg logit contributions
 Pig-0.009
 known-0.008
 Beth-0.008
gy-0.008
 Tweet-0.008
Token He
Token ID679
Feature activation+6.01e-02

Pos logit contributions
 Pig+0.002
 known+0.002
gy+0.001
 darker+0.001
wood+0.001
Neg logit contributions
five-0.002
 Deal-0.002
 cheek-0.002
agging-0.002
 goodness-0.002
Token found
Token ID1043
Feature activation-6.48e-01

Pos logit contributions
 Pig+0.002
wood+0.002
 Ally+0.002
 Beth+0.002
 Tweet+0.002
Neg logit contributions
five-0.002
 cheek-0.002
 mine-0.002
agging-0.002
 fourteen-0.002
Token a
Token ID257
Feature activation-1.87e-01

Pos logit contributions
five+0.028
 fourteen+0.024
 goodness+0.024
 mine+0.024
agging+0.024
Neg logit contributions
 Pig-0.023
gy-0.022
house-0.021
 Beth-0.021
 Ally-0.020
Token l
Token ID300
Feature activation-1.69e+00

Pos logit contributions
five+0.008
agging+0.007
 cheek+0.007
 mine+0.007
 sidelines+0.007
Neg logit contributions
 Pig-0.008
 Tweet-0.007
 Beth-0.007
gy-0.007
 Ally-0.007
Tokenily
Token ID813
Feature activation-3.31e-01

Pos logit contributions
 cheek+0.066
five+0.062
 mine+0.058
 sidelines+0.056
 Deal+0.056
Neg logit contributions
 Pig-0.068
 known-0.065
 Tweet-0.064
 Bunny-0.063
 Bert-0.061
Token pad
Token ID14841
Feature activation-4.45e+00

Pos logit contributions
five+0.012
agging+0.012
 cheek+0.011
 fourteen+0.010
 Deal+0.010
Neg logit contributions
 Pig-0.015
 Tweet-0.014
 Bunny-0.013
 Beth-0.013
gy-0.013
Token in
Token ID287
Feature activation-5.70e-01

Pos logit contributions
five+0.225
agging+0.222
 cheek+0.212
 Deal+0.210
 sidelines+0.206
Neg logit contributions
 Pig-0.134
 Tweet-0.121
gy-0.121
wood-0.115
 Bunny-0.115
Token the
Token ID262
Feature activation-2.78e-01

Pos logit contributions
five+0.026
 cheek+0.025
agging+0.024
 mine+0.024
 fourteen+0.024
Neg logit contributions
 Pig-0.020
wood-0.017
gy-0.017
 Ally-0.017
 Tweet-0.017
Token pond
Token ID16723
Feature activation-1.22e+00

Pos logit contributions
five+0.012
agging+0.012
 cheek+0.012
 fourteen+0.011
 Deal+0.011
Neg logit contributions
 Pig-0.011
 Tweet-0.010
 Bunny-0.009
 Beth-0.009
 Ally-0.009
Token and
Token ID290
Feature activation+4.03e-01

Pos logit contributions
five+0.054
agging+0.052
 cheek+0.051
 mine+0.047
 fourteen+0.047
Neg logit contributions
 Pig-0.046
 Beth-0.041
 Tweet-0.041
 Ally-0.040
 Bert-0.040
Token rested
Token ID29263
Feature activation+8.73e-01

Pos logit contributions
 Pig+0.015
wood+0.014
gy+0.013
 Ally+0.013
 Beth+0.013
Neg logit contributions
five-0.017
 cheek-0.016
 mine-0.015
 fourteen-0.014
 sidelines-0.014
Token,
Token ID11
Feature activation+5.45e-02

Pos logit contributions
five+0.017
agging+0.016
 cheek+0.016
 fourteen+0.015
 mine+0.015
Neg logit contributions
 Pig-0.013
wood-0.012
gy-0.012
 Beth-0.012
 Ally-0.012
Token "
Token ID366
Feature activation+5.86e-01

Pos logit contributions
 Pig+0.002
 Tweet+0.002
 Beth+0.002
 Bunny+0.002
 Ally+0.002
Neg logit contributions
five-0.002
agging-0.002
 cheek-0.002
 fourteen-0.002
 mine-0.002
TokenYou
Token ID1639
Feature activation-2.49e-01

Pos logit contributions
 Pig+0.026
 known+0.023
 Tweet+0.023
 Bunny+0.023
 Beth+0.022
Neg logit contributions
agging-0.023
five-0.022
 cheek-0.021
 mine-0.019
 fourteen-0.019
Token are
Token ID389
Feature activation+1.55e-01

Pos logit contributions
five+0.009
agging+0.009
 cheek+0.009
 fourteen+0.008
 mine+0.008
Neg logit contributions
 Pig-0.011
 Tweet-0.010
 Beth-0.010
 Bunny-0.010
 Ally-0.010
Token under
Token ID739
Feature activation-1.34e+00

Pos logit contributions
 Pig+0.005
 Tweet+0.004
 Bunny+0.004
 known+0.004
 Beth+0.004
Neg logit contributions
five-0.008
agging-0.008
 cheek-0.008
 fourteen-0.007
arl-0.007
Token arrest
Token ID3251
Feature activation-4.45e+00

Pos logit contributions
five+0.034
agging+0.032
 cheek+0.031
 Deal+0.026
 fourteen+0.026
Neg logit contributions
 Pig-0.077
 Tweet-0.071
 Bunny-0.070
 Beth-0.070
gy-0.069
Token for
Token ID329
Feature activation-7.40e-01

Pos logit contributions
five+0.191
agging+0.187
 cheek+0.182
 Deal+0.172
 fourteen+0.168
Neg logit contributions
 Pig-0.169
 Tweet-0.155
 Bunny-0.149
 Beth-0.147
gy-0.146
Token harassing
Token ID34110
Feature activation+1.32e+00

Pos logit contributions
five+0.037
agging+0.035
 cheek+0.034
 mine+0.033
 fourteen+0.033
Neg logit contributions
 Pig-0.024
 Tweet-0.021
wood-0.021
 Ally-0.021
 Beth-0.021
Token and
Token ID290
Feature activation-2.00e+00

Pos logit contributions
 Pig+0.051
 Tweet+0.046
 Beth+0.045
 Ally+0.045
 Bunny+0.044
Neg logit contributions
five-0.056
agging-0.056
 cheek-0.052
arl-0.050
 mine-0.049
Token stealing
Token ID16568
Feature activation-5.10e-01

Pos logit contributions
five+0.073
 cheek+0.071
agging+0.070
 mine+0.066
 sidelines+0.064
Neg logit contributions
 Pig-0.089
 Ally-0.080
 Tweet-0.080
 Beth-0.079
gy-0.079
Token from
Token ID422
Feature activation+9.23e-01

Pos logit contributions
five+0.022
agging+0.021
 cheek+0.020
 sidelines+0.019
 Deal+0.019
Neg logit contributions
 Pig-0.020
 Tweet-0.018
 Bunny-0.018
 Beth-0.018
wood-0.017
Token hopped
Token ID45230
Feature activation-5.38e-01

Pos logit contributions
 Pig+0.011
wood+0.011
 Beth+0.011
 Tweet+0.010
ained+0.010
Neg logit contributions
five-0.011
 cheek-0.011
 mine-0.010
 wo-0.010
agging-0.010
Token off
Token ID572
Feature activation-1.60e+00

Pos logit contributions
five+0.024
agging+0.023
 cheek+0.023
 mine+0.021
 fourteen+0.021
Neg logit contributions
 Pig-0.020
 known-0.018
gy-0.017
wood-0.017
 Tweet-0.017
Token the
Token ID262
Feature activation-3.87e-01

Pos logit contributions
five+0.068
 cheek+0.064
agging+0.064
 fourteen+0.059
 mine+0.059
Neg logit contributions
 Pig-0.061
wood-0.056
 known-0.054
gy-0.054
 Beth-0.052
Token l
Token ID300
Feature activation-2.13e+00

Pos logit contributions
five+0.018
agging+0.017
 Deal+0.017
ige+0.016
 fourteen+0.016
Neg logit contributions
 Pig-0.014
 Bunny-0.013
 Tweet-0.013
 shelter-0.012
 Beth-0.012
Tokenily
Token ID813
Feature activation-4.84e-01

Pos logit contributions
 cheek+0.076
five+0.074
 Deal+0.069
 mine+0.068
agging+0.067
Neg logit contributions
 Pig-0.092
 Tweet-0.087
 Bunny-0.083
 Ally-0.082
 Bert-0.081
Token pad
Token ID14841
Feature activation-4.43e+00

Pos logit contributions
five+0.014
agging+0.013
 cheek+0.013
 mine+0.011
 fourteen+0.011
Neg logit contributions
 Pig-0.026
 Tweet-0.024
 Beth-0.023
 known-0.023
 Bunny-0.023
Token,
Token ID11
Feature activation-7.94e-01

Pos logit contributions
five+0.213
agging+0.206
 cheek+0.199
 fourteen+0.189
 Deal+0.189
Neg logit contributions
 Pig-0.150
 Tweet-0.133
gy-0.129
 Bunny-0.128
 Beth-0.127
Token looked
Token ID3114
Feature activation-6.96e-01

Pos logit contributions
five+0.036
agging+0.035
 cheek+0.034
 fourteen+0.032
 mine+0.031
Neg logit contributions
 Pig-0.029
 Tweet-0.026
 Beth-0.025
 Bunny-0.025
wood-0.025
Token around
Token ID1088
Feature activation-6.83e-01

Pos logit contributions
five+0.033
agging+0.033
 cheek+0.032
 mine+0.030
 fourteen+0.029
Neg logit contributions
 Pig-0.024
 Tweet-0.021
 Beth-0.020
gy-0.020
wood-0.020
Token,
Token ID11
Feature activation-2.72e-01

Pos logit contributions
five+0.030
agging+0.030
 cheek+0.029
 mine+0.027
 fourteen+0.026
Neg logit contributions
 Pig-0.025
 Tweet-0.022
wood-0.022
gy-0.022
 Beth-0.022
Token and
Token ID290
Feature activation+2.29e-01

Pos logit contributions
five+0.012
agging+0.012
 cheek+0.012
 fourteen+0.011
 mine+0.011
Neg logit contributions
 Pig-0.010
 Tweet-0.009
 Beth-0.009
 Bunny-0.009
wood-0.009
Token.
Token ID13
Feature activation-4.13e-01

Pos logit contributions
 Pig+0.027
 Tweet+0.024
 Bunny+0.023
gy+0.023
 Beth+0.023
Neg logit contributions
five-0.041
agging-0.039
 cheek-0.038
 Deal-0.036
 fourteen-0.036
Token The
Token ID383
Feature activation+8.11e-02

Pos logit contributions
five+0.019
 cheek+0.018
agging+0.017
 la+0.017
 fourteen+0.017
Neg logit contributions
 known-0.013
 Pig-0.012
gy-0.012
wood-0.012
 darker-0.011
Token bird
Token ID6512
Feature activation+4.25e-01

Pos logit contributions
 Pig+0.003
 Tweet+0.003
 Bunny+0.002
 Beth+0.002
 Ally+0.002
Neg logit contributions
five-0.004
agging-0.004
 cheek-0.004
 fourteen-0.003
 Deal-0.003
Token saw
Token ID2497
Feature activation-8.34e-01

Pos logit contributions
 Pig+0.013
wood+0.011
 Beth+0.011
 known+0.011
 Tweet+0.011
Neg logit contributions
five-0.021
agging-0.021
 cheek-0.021
 mine-0.019
 fourteen-0.019
Token O
Token ID440
Feature activation-8.22e-01

Pos logit contributions
five+0.039
 goodness+0.038
 fourteen+0.038
 mine+0.037
agging+0.036
Neg logit contributions
 Pig-0.024
 known-0.023
wood-0.023
gy-0.023
house-0.023
Tokenll
Token ID297
Feature activation-4.40e+00

Pos logit contributions
five+0.025
agging+0.022
 cheek+0.022
 Deal+0.019
 fourteen+0.019
Neg logit contributions
 Pig-0.044
 Tweet-0.040
gy-0.039
 Bunny-0.039
 Beth-0.039
Tokenie
Token ID494
Feature activation-4.36e-01

Pos logit contributions
five+0.287
agging+0.274
 Deal+0.274
 fourteen+0.266
arl+0.265
Neg logit contributions
 Pig-0.075
 Tweet-0.069
gy-0.063
 Ally-0.058
 Bunny-0.057
Token and
Token ID290
Feature activation-3.22e-01

Pos logit contributions
 cheek+0.018
agging+0.017
five+0.016
 mine+0.016
 liking+0.015
Neg logit contributions
 Pig-0.017
 known-0.017
 Beth-0.016
wood-0.016
 Ally-0.016
Token wanted
Token ID2227
Feature activation-8.74e-01

Pos logit contributions
five+0.013
 cheek+0.013
 wo+0.012
 mine+0.012
 la+0.012
Neg logit contributions
wood-0.011
 Pig-0.011
 darker-0.010
house-0.010
gy-0.010
Token to
Token ID284
Feature activation+8.94e-02

Pos logit contributions
five+0.032
 mine+0.030
 cheek+0.029
agging+0.027
 fourteen+0.027
Neg logit contributions
 Pig-0.036
gy-0.035
house-0.034
 Ally-0.034
wood-0.033
Token eat
Token ID4483
Feature activation-6.61e-01

Pos logit contributions
 Pig+0.004
 Tweet+0.004
 Bunny+0.003
 Beth+0.003
gy+0.003
Neg logit contributions
agging-0.004
five-0.004
 cheek-0.003
 fourteen-0.003
 Deal-0.003
Token him
Token ID683
Feature activation+1.64e-02

Pos logit contributions
 Pig+0.009
 known+0.009
gy+0.008
wood+0.008
 Tweet+0.008
Neg logit contributions
agging-0.010
five-0.009
 cheek-0.009
 mine-0.009
 goodness-0.008
Token on
Token ID319
Feature activation-4.17e-01

Pos logit contributions
 Pig+0.001
 known+0.001
 Ally+0.001
 Beth+0.001
 Tweet+0.001
Neg logit contributions
five-0.001
 cheek-0.001
agging-0.001
 mine-0.001
 la-0.001
Token the
Token ID262
Feature activation-4.81e-01

Pos logit contributions
 mine+0.017
agging+0.016
five+0.015
 fourteen+0.015
 arrest+0.015
Neg logit contributions
 Pig-0.015
 known-0.014
wood-0.014
gy-0.014
 Ally-0.014
Token l
Token ID300
Feature activation-2.05e+00

Pos logit contributions
five+0.022
agging+0.021
 Deal+0.020
 cheek+0.019
arl+0.019
Neg logit contributions
 Pig-0.018
 Tweet-0.016
 Bunny-0.016
 Ally-0.015
 Beth-0.015
Tokenily
Token ID813
Feature activation-4.62e-01

Pos logit contributions
 cheek+0.071
five+0.067
 mine+0.060
 Deal+0.059
agging+0.059
Neg logit contributions
 Pig-0.093
 Tweet-0.088
 Bunny-0.086
 known-0.084
 dam-0.083
Token pad
Token ID14841
Feature activation-4.37e+00

Pos logit contributions
five+0.018
 cheek+0.017
agging+0.017
 mine+0.015
 la+0.015
Neg logit contributions
 Pig-0.020
 known-0.018
 Tweet-0.018
 Beth-0.018
 Ally-0.018
Token.
Token ID13
Feature activation-2.43e-01

Pos logit contributions
five+0.212
agging+0.206
 cheek+0.200
 fourteen+0.188
 Deal+0.186
Neg logit contributions
 Pig-0.146
 Tweet-0.129
 Beth-0.125
 Bunny-0.125
gy-0.123
Token They
Token ID1119
Feature activation-7.63e-02

Pos logit contributions
five+0.011
agging+0.010
 cheek+0.010
 mine+0.010
 fourteen+0.010
Neg logit contributions
 Pig-0.008
 known-0.008
gy-0.008
wood-0.007
 Beth-0.007
Token all
Token ID477
Feature activation-2.30e+00

Pos logit contributions
five+0.003
agging+0.003
 cheek+0.003
 fourteen+0.003
 mine+0.003
Neg logit contributions
 Pig-0.003
wood-0.003
gy-0.003
 Tweet-0.003
house-0.002
Token rested
Token ID29263
Feature activation-4.05e-02

Pos logit contributions
five+0.088
agging+0.081
 cheek+0.080
 mine+0.073
 fourteen+0.073
Neg logit contributions
 Pig-0.098
wood-0.089
 Tweet-0.087
gy-0.086
 Ally-0.084
Token together
Token ID1978
Feature activation-4.28e-01

Pos logit contributions
agging+0.002
five+0.002
 cheek+0.002
 fourteen+0.002
 mine+0.002
Neg logit contributions
 Pig-0.001
 Tweet-0.001
 Beth-0.001
wood-0.001
 Ally-0.001
Token giant
Token ID6175
Feature activation-1.24e+00

Pos logit contributions
agging+0.044
five+0.040
 cheek+0.038
ater+0.037
arest+0.036
Neg logit contributions
 Pig-0.035
 Tweet-0.035
 Bunny-0.033
 Beth-0.033
 Bert-0.032
Token!
Token ID0
Feature activation-1.84e+00

Pos logit contributions
five+0.057
agging+0.055
 cheek+0.054
 fourteen+0.050
 mine+0.049
Neg logit contributions
 Pig-0.045
 Tweet-0.040
 Beth-0.039
 Bunny-0.039
 Ally-0.038
Token You
Token ID921
Feature activation-1.43e-01

Pos logit contributions
agging+0.067
five+0.063
 cheek+0.061
 sidelines+0.056
ige+0.054
Neg logit contributions
 Pig-0.088
 Tweet-0.080
 Bunny-0.079
 Beth-0.078
gy-0.077
Token are
Token ID389
Feature activation-2.64e-01

Pos logit contributions
five+0.005
agging+0.005
 cheek+0.005
 fourteen+0.004
 sidelines+0.004
Neg logit contributions
 Pig-0.007
 Tweet-0.006
 Bunny-0.006
 Beth-0.006
gy-0.006
Token under
Token ID739
Feature activation-1.61e+00

Pos logit contributions
five+0.013
agging+0.012
 cheek+0.012
arl+0.011
 fourteen+0.011
Neg logit contributions
 Pig-0.010
 Tweet-0.009
 Bunny-0.008
 Beth-0.008
 known-0.008
Token arrest
Token ID3251
Feature activation-4.36e+00

Pos logit contributions
five+0.036
agging+0.033
 cheek+0.032
 Deal+0.028
ige+0.025
Neg logit contributions
 Pig-0.100
 Tweet-0.095
 Bunny-0.092
 Beth-0.091
gy-0.090
Token!
Token ID0
Feature activation-1.50e+00

Pos logit contributions
five+0.170
agging+0.168
 cheek+0.163
 Deal+0.156
leaf+0.151
Neg logit contributions
 Pig-0.179
 Tweet-0.168
 Bunny-0.160
 Beth-0.158
gy-0.157
Token You
Token ID921
Feature activation-6.24e-02

Pos logit contributions
agging+0.046
five+0.045
 cheek+0.044
 sidelines+0.038
 fourteen+0.037
Neg logit contributions
 Pig-0.078
 Tweet-0.072
 Beth-0.071
 Bunny-0.070
 Bert-0.069
Token can
Token ID460
Feature activation+5.42e-01

Pos logit contributions
five+0.002
agging+0.002
 cheek+0.002
 fourteen+0.002
 sidelines+0.002
Neg logit contributions
 Pig-0.003
 Tweet-0.003
 Bunny-0.003
 Beth-0.002
gy-0.002
Token't
Token ID470
Feature activation-1.13e+00

Pos logit contributions
 Pig+0.024
 Tweet+0.023
gy+0.022
 Bunny+0.022
 Beth+0.022
Neg logit contributions
five-0.020
agging-0.020
 cheek-0.019
 Deal-0.017
arl-0.017
Token take
Token ID1011
Feature activation-6.68e-01

Pos logit contributions
five+0.049
agging+0.049
 cheek+0.047
 Deal+0.044
 fourteen+0.044
Neg logit contributions
 Pig-0.044
 Tweet-0.041
gy-0.039
 Bunny-0.039
 Beth-0.038
Token,
Token ID11
Feature activation-1.93e-01

Pos logit contributions
five+0.023
agging+0.022
 cheek+0.022
 fourteen+0.020
 mine+0.020
Neg logit contributions
 Pig-0.019
 Tweet-0.017
 Beth-0.017
 Bunny-0.017
 Ally-0.016
Token I
Token ID314
Feature activation-1.74e-01

Pos logit contributions
five+0.008
agging+0.008
 cheek+0.007
 mine+0.007
 fourteen+0.007
Neg logit contributions
 Pig-0.008
gy-0.007
 Tweet-0.007
 known-0.007
wood-0.007
Tokenâ
Token ID22940
Feature activation+1.36e-01

Pos logit contributions
five+0.007
agging+0.006
 cheek+0.006
 la+0.006
 Deal+0.005
Neg logit contributions
 Pig-0.007
 Tweet-0.007
 Beth-0.007
 Ally-0.007
 Bunny-0.007
Token
Token ID26391
Feature activation+5.84e-01

Pos logit contributions
 Pig+0.006
 Tweet+0.006
 Bunny+0.006
 Beth+0.006
 Ally+0.006
Neg logit contributions
five-0.005
agging-0.005
 cheek-0.005
 fourteen-0.004
 sidelines-0.004
Token
Token ID8151
Feature activation+1.01e+00

Pos logit contributions
 Pig+0.024
 Tweet+0.022
 Bunny+0.021
 Beth+0.021
wood+0.021
Neg logit contributions
five-0.024
agging-0.023
 cheek-0.022
 la-0.021
 fourteen-0.021
Tokenll
Token ID297
Feature activation-4.35e+00

Pos logit contributions
 Pig+0.041
 Tweet+0.038
 Beth+0.037
 Bunny+0.037
gy+0.036
Neg logit contributions
five-0.041
agging-0.039
 cheek-0.038
 fourteen-0.035
 sidelines-0.035
Token allow
Token ID1249
Feature activation-6.84e-01

Pos logit contributions
five+0.178
agging+0.171
 cheek+0.165
 fourteen+0.155
 Deal+0.153
Neg logit contributions
 Pig-0.180
 Tweet-0.160
 Beth-0.160
gy-0.158
 Ally-0.158
Token you
Token ID345
Feature activation+1.36e-01

Pos logit contributions
five+0.018
agging+0.017
 cheek+0.016
 mine+0.015
 fourteen+0.015
Neg logit contributions
 Pig-0.037
 Tweet-0.035
gy-0.035
 Beth-0.034
wood-0.034
Token to
Token ID284
Feature activation-2.06e-01

Pos logit contributions
 Pig+0.004
 Tweet+0.004
 Bunny+0.004
 Beth+0.004
wood+0.004
Neg logit contributions
five-0.007
agging-0.007
 cheek-0.007
 sidelines-0.006
 fourteen-0.006
Token take
Token ID1011
Feature activation-3.86e-01

Pos logit contributions
five+0.008
agging+0.007
 cheek+0.007
 mine+0.007
 fourteen+0.006
Neg logit contributions
 Pig-0.009
 Tweet-0.008
 Beth-0.008
 Bunny-0.008
 Ally-0.008
Token it
Token ID340
Feature activation+2.82e-01

Pos logit contributions
five+0.018
agging+0.017
 cheek+0.016
 mine+0.016
 fourteen+0.015
Neg logit contributions
 Pig-0.014
gy-0.013
 Tweet-0.012
wood-0.012
 known-0.012
Token.
Token ID13
Feature activation-1.36e+00

Pos logit contributions
 Pig+0.009
 Tweet+0.008
 Bunny+0.008
 Beth+0.008
gy+0.008
Neg logit contributions
five-0.008
agging-0.008
 cheek-0.007
 fourteen-0.007
 sidelines-0.007
Token We
Token ID775
Feature activation-4.98e-02

Pos logit contributions
five+0.052
agging+0.049
 cheek+0.048
 fourteen+0.044
 Deal+0.043
Neg logit contributions
 Pig-0.059
 Tweet-0.054
 Beth-0.053
 Bunny-0.053
 known-0.053
Token need
Token ID761
Feature activation+2.17e-01

Pos logit contributions
five+0.002
agging+0.002
 cheek+0.002
 fourteen+0.002
 mine+0.002
Neg logit contributions
 Pig-0.002
 Tweet-0.002
 Beth-0.002
 Bunny-0.002
 Ally-0.002
Token a
Token ID257
Feature activation+5.51e-01

Pos logit contributions
 Pig+0.007
 Tweet+0.006
 Bunny+0.006
 Beth+0.006
 Ally+0.005
Neg logit contributions
agging-0.011
five-0.011
 cheek-0.011
 Deal-0.010
arl-0.010
Token grown
Token ID7334
Feature activation+4.72e-01

Pos logit contributions
 Pig+0.025
 Tweet+0.023
 Bunny+0.023
 Ally+0.022
 Beth+0.022
Neg logit contributions
five-0.020
agging-0.020
 cheek-0.018
 fourteen-0.017
 Deal-0.017
Token-
Token ID12
Feature activation+3.30e+00

Pos logit contributions
 Pig+0.020
 Tweet+0.019
 Bunny+0.019
 Beth+0.019
 Ally+0.018
Neg logit contributions
five-0.020
agging-0.019
 cheek-0.018
ater-0.018
 mine-0.017
Tokenup
Token ID929
Feature activation+8.65e-01

Pos logit contributions
 Pig+0.128
 Tweet+0.115
 Bunny+0.114
 Beth+0.113
 Ally+0.110
Neg logit contributions
five-0.150
agging-0.137
 cheek-0.134
 fourteen-0.127
 mine-0.124
Token to
Token ID284
Feature activation-7.64e-01

Pos logit contributions
 Pig+0.033
 Tweet+0.030
 Beth+0.029
 Bunny+0.029
 Ally+0.028
Neg logit contributions
five-0.038
agging-0.037
 cheek-0.036
 fourteen-0.033
 mine-0.033
Token help
Token ID1037
Feature activation+1.53e-01

Pos logit contributions
five+0.030
agging+0.028
 cheek+0.028
 mine+0.025
 fourteen+0.025
Neg logit contributions
 Pig-0.033
 Tweet-0.030
 Beth-0.029
 Bunny-0.029
wood-0.029
Token us
Token ID514
Feature activation+5.92e-01

Pos logit contributions
 Pig+0.007
 Tweet+0.006
 Beth+0.006
 Bunny+0.006
 known+0.006
Neg logit contributions
five-0.006
agging-0.005
 cheek-0.005
 mine-0.005
 fourteen-0.005
Token read
Token ID1100
Feature activation+1.79e-01

Pos logit contributions
 Pig+0.025
 Beth+0.023
 Tweet+0.023
 Ally+0.023
 known+0.023
Neg logit contributions
five-0.023
 cheek-0.022
agging-0.021
 mine-0.020
 fourteen-0.019
Token dress
Token ID6576
Feature activation+7.94e-01

Pos logit contributions
five+0.008
 cheek+0.007
agging+0.007
 fourteen+0.007
 Deal+0.007
Neg logit contributions
 Pig-0.004
 Tweet-0.004
 Bunny-0.003
 Beth-0.003
 Ally-0.003
Token-
Token ID12
Feature activation+3.88e+00

Pos logit contributions
 Pig+0.026
 Tweet+0.022
 known+0.022
 Bunny+0.022
 Beth+0.022
Neg logit contributions
five-0.040
agging-0.039
 cheek-0.038
 mine-0.035
 fourteen-0.035
Tokenup
Token ID929
Feature activation+1.23e+00

Pos logit contributions
 Pig+0.146
 Tweet+0.128
 Bunny+0.128
 Beth+0.125
 Ally+0.124
Neg logit contributions
five-0.176
agging-0.167
 cheek-0.163
 fourteen-0.149
 mine-0.149
Token and
Token ID290
Feature activation-4.23e-02

Pos logit contributions
 Pig+0.045
 Tweet+0.040
 Bunny+0.039
 known+0.039
 Beth+0.039
Neg logit contributions
five-0.057
agging-0.057
 cheek-0.055
 mine-0.051
 la-0.049
Token make
Token ID787
Feature activation+7.82e-01

Pos logit contributions
five+0.002
agging+0.002
 cheek+0.002
 fourteen+0.002
 Deal+0.002
Neg logit contributions
 Pig-0.002
 Tweet-0.002
 Beth-0.002
 Ally-0.002
 Bunny-0.002
Token-
Token ID12
Feature activation+3.85e+00

Pos logit contributions
 Pig+0.036
wood+0.034
gy+0.034
 Bunny+0.033
 known+0.032
Neg logit contributions
agging-0.027
five-0.026
 cheek-0.025
 mine-0.024
 goodness-0.024
Tokenbel
Token ID6667
Feature activation+1.88e+00

Pos logit contributions
 Pig+0.128
 Tweet+0.112
 Bunny+0.111
 Beth+0.108
 Ally+0.107
Neg logit contributions
five-0.191
agging-0.182
 cheek-0.179
 fourteen-0.165
 mine-0.164
Tokenieve
Token ID12311
Feature activation+1.62e+00

Pos logit contributions
 Pig+0.074
 Tweet+0.068
 known+0.067
 Beth+0.066
 Bert+0.064
Neg logit contributions
five-0.077
agging-0.074
 cheek-0.073
 fourteen-0.068
arl-0.067
Token.
Token ID13
Feature activation+2.35e-01

Pos logit contributions
 Pig+0.062
 Tweet+0.054
 Bunny+0.053
 known+0.053
gy+0.053
Neg logit contributions
five-0.072
agging-0.071
 cheek-0.069
 mine-0.065
 la-0.063
Token One
Token ID1881
Feature activation-6.94e-02

Pos logit contributions
 Pig+0.006
 Tweet+0.005
 Beth+0.005
 Bunny+0.005
 Ally+0.005
Neg logit contributions
five-0.014
agging-0.013
 cheek-0.013
 fourteen-0.012
 sidelines-0.012
Token day
Token ID1110
Feature activation+2.83e-01

Pos logit contributions
five+0.004
agging+0.004
 cheek+0.004
 fourteen+0.003
 mine+0.003
Neg logit contributions
 Pig-0.002
 Tweet-0.002
 Beth-0.002
 Bunny-0.002
 Ally-0.002
Token Do
Token ID2141
Feature activation+2.48e-01

Pos logit contributions
five+0.007
 cheek+0.006
agging+0.006
 Deal+0.005
 fourteen+0.005
Neg logit contributions
 Pig-0.012
 known-0.011
 Tweet-0.011
gy-0.011
 Beth-0.011
Token you
Token ID345
Feature activation-1.08e+00

Pos logit contributions
 Pig+0.013
 Tweet+0.013
 Bunny+0.012
 Ally+0.012
 Beth+0.012
Neg logit contributions
five-0.008
agging-0.007
 cheek-0.007
arl-0.006
 sidelines-0.006
Token know
Token ID760
Feature activation-9.63e-01

Pos logit contributions
five+0.043
agging+0.043
 cheek+0.041
 sidelines+0.040
 fourteen+0.039
Neg logit contributions
 Pig-0.045
 known-0.040
 Tweet-0.040
 Bunny-0.039
gy-0.039
Token how
Token ID703
Feature activation+1.37e-01

Pos logit contributions
five+0.046
agging+0.044
 cheek+0.043
 sidelines+0.040
 fourteen+0.040
Neg logit contributions
 Pig-0.034
 Tweet-0.030
 Bunny-0.029
 Beth-0.029
 Ally-0.029
Token to
Token ID284
Feature activation+2.38e-01

Pos logit contributions
 Pig+0.005
 Tweet+0.004
 Bunny+0.004
 Beth+0.004
 Ally+0.004
Neg logit contributions
five-0.007
agging-0.007
 cheek-0.006
 fourteen-0.006
 Deal-0.006
Token stitch
Token ID24695
Feature activation+3.44e+00

Pos logit contributions
 Pig+0.009
 Tweet+0.008
 Bunny+0.008
gy+0.008
 Beth+0.008
Neg logit contributions
five-0.010
agging-0.010
 cheek-0.010
 fourteen-0.009
 Deal-0.009
Token?"
Token ID1701
Feature activation+6.22e-01

Pos logit contributions
 Pig+0.146
 Tweet+0.133
 known+0.132
 Beth+0.131
gy+0.130
Neg logit contributions
five-0.130
agging-0.128
 cheek-0.127
 mine-0.117
 fourteen-0.115
Token
Token ID198
Feature activation+6.69e-01

Pos logit contributions
 Pig+0.023
wood+0.022
gy+0.022
 known+0.022
 darker+0.021
Neg logit contributions
five-0.028
 cheek-0.024
 goodness-0.023
agging-0.023
 la-0.023
Token
Token ID198
Feature activation+4.06e-01

Pos logit contributions
 Pig+0.020
 Tweet+0.017
 Beth+0.016
 Bunny+0.016
 Ally+0.016
Neg logit contributions
five-0.035
agging-0.034
 cheek-0.034
 fourteen-0.032
 mine-0.031
TokenThe
Token ID464
Feature activation+6.29e-01

Pos logit contributions
 Pig+0.017
 Tweet+0.015
 Ally+0.015
 Bunny+0.015
 Beth+0.015
Neg logit contributions
agging-0.017
five-0.017
 cheek-0.016
 fourteen-0.015
 mine-0.015
Token tree
Token ID5509
Feature activation-1.25e+00

Pos logit contributions
 Pig+0.020
 Tweet+0.019
 Bunny+0.018
house+0.017
 Ally+0.017
Neg logit contributions
five-0.032
agging-0.031
 fourteen-0.030
ige-0.028
leaf-0.028
Token and
Token ID290
Feature activation-1.14e+00

Pos logit contributions
five+0.030
agging+0.029
 cheek+0.029
 sidelines+0.027
 Deal+0.026
Neg logit contributions
 Pig-0.021
 Tweet-0.019
 Bunny-0.018
gy-0.018
wood-0.018
Token Mia
Token ID32189
Feature activation-3.61e-02

Pos logit contributions
five+0.046
 cheek+0.041
agging+0.038
 mine+0.038
 la+0.038
Neg logit contributions
 Pig-0.050
wood-0.044
 known-0.044
gy-0.043
 Tweet-0.042
Token lick
Token ID36728
Feature activation-1.03e+00

Pos logit contributions
agging+0.001
 cheek+0.001
five+0.001
arl+0.001
 mine+0.001
Neg logit contributions
 Pig-0.002
 Bunny-0.001
 known-0.001
gy-0.001
 Tweet-0.001
Token their
Token ID511
Feature activation+1.54e+00

Pos logit contributions
five+0.049
agging+0.045
 cheek+0.043
 fourteen+0.042
 mine+0.041
Neg logit contributions
 Pig-0.037
gy-0.034
 known-0.033
wood-0.033
 Bert-0.033
Token ice
Token ID4771
Feature activation+3.15e-01

Pos logit contributions
 Pig+0.063
 Bunny+0.058
 Tweet+0.057
wood+0.057
gy+0.056
Neg logit contributions
agging-0.060
five-0.058
arl-0.054
 la-0.054
 fourteen-0.053
Token-
Token ID12
Feature activation+4.10e+00

Pos logit contributions
 Pig+0.012
 Tweet+0.011
 Beth+0.011
 Ally+0.010
 Bunny+0.010
Neg logit contributions
five-0.014
agging-0.013
 cheek-0.013
 fourteen-0.012
 mine-0.012
Tokencream
Token ID36277
Feature activation-1.14e+00

Pos logit contributions
 Pig+0.182
 Tweet+0.164
 Beth+0.163
 Ally+0.162
 Bunny+0.162
Neg logit contributions
five-0.160
agging-0.149
 cheek-0.146
 fourteen-0.135
 mine-0.129
Token.
Token ID13
Feature activation-4.81e-01

Pos logit contributions
five+0.051
agging+0.050
 cheek+0.048
 fourteen+0.045
 mine+0.044
Neg logit contributions
 Pig-0.043
 Tweet-0.038
 Beth-0.037
 Bunny-0.037
 Ally-0.037
Token It
Token ID632
Feature activation+9.96e-01

Pos logit contributions
five+0.023
 fourteen+0.021
 cheek+0.020
agging+0.020
 mine+0.020
Neg logit contributions
 Pig-0.018
 known-0.016
 Beth-0.015
gy-0.015
 Ally-0.015
Token is
Token ID318
Feature activation+4.94e-01

Pos logit contributions
 Pig+0.048
 Tweet+0.044
 Beth+0.043
 Ally+0.043
 Bunny+0.043
Neg logit contributions
five-0.035
agging-0.033
 cheek-0.032
 fourteen-0.029
 mine-0.029
Token cold
Token ID4692
Feature activation+3.49e-01

Pos logit contributions
 Pig+0.021
 Ally+0.019
gy+0.019
 Beth+0.019
 Bert+0.019
Neg logit contributions
 mine-0.019
 cheek-0.019
agging-0.019
 fourteen-0.018
five-0.018
Token They
Token ID1119
Feature activation-1.90e-01

Pos logit contributions
five+0.017
 Deal+0.016
agging+0.016
 cheek+0.016
arl+0.016
Neg logit contributions
 Pig-0.012
gy-0.011
wood-0.011
 known-0.011
 Tweet-0.011
Token like
Token ID588
Feature activation-1.85e-01

Pos logit contributions
agging+0.007
five+0.007
 cheek+0.006
 fourteen+0.006
 sidelines+0.006
Neg logit contributions
 Pig-0.009
 Tweet-0.008
 Bunny-0.008
 known-0.008
 Beth-0.008
Token to
Token ID284
Feature activation-2.86e-01

Pos logit contributions
five+0.007
 cheek+0.007
 mine+0.007
agging+0.007
 liking+0.007
Neg logit contributions
 Pig-0.007
gy-0.007
 Ally-0.007
wood-0.007
 Beth-0.007
Token play
Token ID711
Feature activation+3.52e-01

Pos logit contributions
five+0.011
agging+0.011
 cheek+0.011
 fourteen+0.010
 Deal+0.010
Neg logit contributions
 Pig-0.012
 Tweet-0.011
 Beth-0.011
 Bunny-0.011
gy-0.011
Token dress
Token ID6576
Feature activation+1.27e+00

Pos logit contributions
 Pig+0.013
 Tweet+0.011
 Beth+0.011
 known+0.011
wood+0.011
Neg logit contributions
five-0.016
agging-0.016
 cheek-0.015
 mine-0.014
 fourteen-0.014
Token-
Token ID12
Feature activation+4.24e+00

Pos logit contributions
 Pig+0.054
 known+0.053
 Tweet+0.047
wood+0.047
 Bunny+0.047
Neg logit contributions
agging-0.052
five-0.051
 cheek-0.049
 mine-0.045
 goodness-0.043
Tokenup
Token ID929
Feature activation+1.63e+00

Pos logit contributions
 Pig+0.178
 Bunny+0.158
 Tweet+0.155
 Ally+0.154
 Bert+0.154
Neg logit contributions
five-0.185
agging-0.162
 cheek-0.159
 fourteen-0.147
leaf-0.146
Token.
Token ID13
Feature activation-3.46e-01

Pos logit contributions
 Pig+0.064
 Tweet+0.057
 Beth+0.056
 known+0.056
 Ally+0.056
Neg logit contributions
five-0.073
agging-0.070
 cheek-0.069
 mine-0.063
 fourteen-0.061
Token They
Token ID1119
Feature activation-2.65e-01

Pos logit contributions
five+0.016
 Deal+0.015
arl+0.015
agging+0.015
 cheek+0.015
Neg logit contributions
 Pig-0.011
gy-0.010
wood-0.010
 known-0.010
 Tweet-0.010
Token like
Token ID588
Feature activation-2.39e-01

Pos logit contributions
agging+0.010
five+0.010
 cheek+0.009
 fourteen+0.008
 sidelines+0.008
Neg logit contributions
 Pig-0.012
 Tweet-0.011
 known-0.011
 Bunny-0.011
 Beth-0.010
Token to
Token ID284
Feature activation-2.35e-01

Pos logit contributions
five+0.010
 cheek+0.009
agging+0.009
 mine+0.009
 liking+0.009
Neg logit contributions
 Pig-0.009
gy-0.009
wood-0.009
 Ally-0.009
 Tweet-0.008
Token big
Token ID1263
Feature activation-7.75e-02

Pos logit contributions
five+0.008
agging+0.008
 cheek+0.007
 mine+0.007
 sidelines+0.007
Neg logit contributions
 Pig-0.007
 Beth-0.006
 Tweet-0.006
gy-0.006
 Bunny-0.006
Token tree
Token ID5509
Feature activation-3.15e-01

Pos logit contributions
five+0.003
 mine+0.003
agging+0.003
 cheek+0.003
 sidelines+0.003
Neg logit contributions
 Pig-0.003
 known-0.003
 Beth-0.003
gy-0.003
wood-0.003
Token."
Token ID526
Feature activation-1.78e-01

Pos logit contributions
five+0.010
agging+0.009
 cheek+0.009
 mine+0.008
 fourteen+0.008
Neg logit contributions
 Pig-0.016
 Beth-0.015
 Tweet-0.015
 Bunny-0.015
 known-0.015
Token
Token ID198
Feature activation+3.20e-01

Pos logit contributions
five+0.009
 cheek+0.008
agging+0.008
 fourteen+0.007
 Deal+0.007
Neg logit contributions
 Pig-0.006
 known-0.006
 Beth-0.005
 Ally-0.005
 Tweet-0.005
Token
Token ID198
Feature activation+1.25e-01

Pos logit contributions
 Pig+0.010
 Tweet+0.009
 Beth+0.009
wood+0.009
gy+0.008
Neg logit contributions
five-0.016
agging-0.016
 cheek-0.015
 fourteen-0.014
arl-0.014
TokenThe
Token ID464
Feature activation+6.54e-01

Pos logit contributions
 Pig+0.005
 Tweet+0.004
 Bunny+0.004
gy+0.004
 known+0.004
Neg logit contributions
five-0.005
 cheek-0.005
agging-0.005
 Deal-0.005
 sidelines-0.005
Token race
Token ID3234
Feature activation-6.62e-01

Pos logit contributions
 Pig+0.027
 Tweet+0.024
 Bunny+0.023
 Ally+0.023
 known+0.023
Neg logit contributions
five-0.028
agging-0.027
 cheek-0.026
 fourteen-0.025
 Deal-0.024
Token began
Token ID2540
Feature activation+3.82e-01

Pos logit contributions
five+0.029
affe+0.025
 mine+0.024
agging+0.024
 cheek+0.023
Neg logit contributions
 Pig-0.025
 Chick-0.024
 Ang-0.022
 darker-0.022
 known-0.022
Token,
Token ID11
Feature activation-2.88e-01

Pos logit contributions
 Pig+0.019
 Chick+0.017
 Bunny+0.017
 Ally+0.017
 Beth+0.016
Neg logit contributions
five-0.012
agging-0.010
 liking-0.010
 arrest-0.010
 fourteen-0.009
Token and
Token ID290
Feature activation-1.64e-01

Pos logit contributions
five+0.011
 cheek+0.010
agging+0.010
 fourteen+0.010
 mine+0.010
Neg logit contributions
 Pig-0.012
 Beth-0.011
 known-0.011
wood-0.011
gy-0.011
Token Remy
Token ID32912
Feature activation-3.83e-01

Pos logit contributions
 fourteen+0.006
five+0.005
 mine+0.005
 cheek+0.005
 sidelines+0.005
Neg logit contributions
 Beth-0.007
bul-0.007
 Pig-0.006
 known-0.006
house-0.006
Token said
Token ID531
Feature activation-2.31e-01

Pos logit contributions
agging+0.023
five+0.022
 cheek+0.022
 sidelines+0.021
 Deal+0.020
Neg logit contributions
 Pig-0.023
 Tweet-0.020
 known-0.020
 Beth-0.020
gy-0.020
Token that
Token ID326
Feature activation+6.62e-01

Pos logit contributions
five+0.009
 cheek+0.009
agging+0.009
 mine+0.009
 la+0.008
Neg logit contributions
 Pig-0.009
 known-0.008
wood-0.008
 Tweet-0.008
gy-0.008
Token?"
Token ID1701
Feature activation+6.47e-01

Pos logit contributions
 Pig+0.030
 Tweet+0.027
 Beth+0.027
 Bunny+0.027
gy+0.026
Neg logit contributions
five-0.024
 cheek-0.023
agging-0.023
 mine-0.021
 fourteen-0.020
Token he
Token ID339
Feature activation+3.75e-01

Pos logit contributions
gy+0.027
 Pig+0.027
wood+0.026
 dam+0.026
 Tweet+0.025
Neg logit contributions
five-0.025
 cheek-0.021
 goodness-0.020
 Deal-0.019
Tom-0.019
Token asked
Token ID1965
Feature activation+9.66e-01

Pos logit contributions
wood+0.015
 Pig+0.014
 dam+0.014
 Tweet+0.014
 shelters+0.014
Neg logit contributions
 cheek-0.014
agging-0.013
 la-0.013
 mine-0.012
 wig-0.012
Token.
Token ID13
Feature activation+9.84e-01

Pos logit contributions
 Pig+0.042
 dam+0.042
wood+0.039
 known+0.038
 Tweet+0.038
Neg logit contributions
five-0.034
 cheek-0.034
agging-0.031
 goodness-0.027
 mine-0.026
Token
Token ID198
Feature activation+7.26e-01

Pos logit contributions
 Pig+0.036
gy+0.034
wood+0.034
 Tweet+0.033
 Beth+0.033
Neg logit contributions
five-0.042
 cheek-0.039
agging-0.037
 Deal-0.036
 fourteen-0.036
Token
Token ID198
Feature activation+5.66e-01

Pos logit contributions
 Pig+0.023
 Tweet+0.021
wood+0.020
gy+0.020
 Beth+0.020
Neg logit contributions
five-0.036
agging-0.035
 cheek-0.034
 fourteen-0.032
 Deal-0.031
TokenThere
Token ID1858
Feature activation+7.11e-01

Pos logit contributions
 Pig+0.027
 Tweet+0.025
 known+0.024
 Beth+0.024
 Bunny+0.024
Neg logit contributions
agging-0.019
five-0.019
 cheek-0.018
 mine-0.016
 sidelines-0.016
Token was
Token ID373
Feature activation+7.19e-01

Pos logit contributions
wood+0.026
 Pig+0.025
 dam+0.025
gy+0.025
 Tweet+0.023
Neg logit contributions
agging-0.028
five-0.027
 cheek-0.026
 goodness-0.026
Tom-0.025
Token a
Token ID257
Feature activation+3.46e-02

Pos logit contributions
 Pig+0.027
wood+0.025
gy+0.024
 Ally+0.023
 Beth+0.022
Neg logit contributions
five-0.030
 fourteen-0.030
 mine-0.028
agging-0.027
 arrest-0.027
Token They
Token ID1119
Feature activation-5.96e-02

Pos logit contributions
 Pig+0.000
 known+0.000
wood+0.000
 darker+0.000
gy+0.000
Neg logit contributions
five-0.000
 cheek-0.000
 Deal-0.000
 fourteen-0.000
 la-0.000
Token hugged
Token ID41130
Feature activation-1.77e-01

Pos logit contributions
five+0.002
ige+0.002
 cheek+0.002
 mine+0.002
agging+0.002
Neg logit contributions
 Pig-0.002
wood-0.002
 Tweet-0.002
 Bert-0.002
 dam-0.002
Token each
Token ID1123
Feature activation-1.07e+00

Pos logit contributions
five+0.007
 cheek+0.007
agging+0.007
 mine+0.006
 goodness+0.006
Neg logit contributions
 Pig-0.007
 known-0.007
wood-0.007
 Tweet-0.006
gy-0.006
Token other
Token ID584
Feature activation-1.08e+00

Pos logit contributions
agging+0.050
ider+0.048
 cheek+0.048
 fourteen+0.048
arl+0.048
Neg logit contributions
 Pig-0.034
 Bunny-0.031
 Ally-0.030
 Beth-0.028
 called-0.028
Token and
Token ID290
Feature activation+4.89e-01

Pos logit contributions
five+0.044
 cheek+0.042
agging+0.041
 mine+0.037
 fourteen+0.036
Neg logit contributions
 Pig-0.045
 Tweet-0.041
 known-0.041
 Ally-0.040
 Beth-0.040
Token played
Token ID2826
Feature activation+7.84e-01

Pos logit contributions
wood+0.021
 Pig+0.021
gy+0.020
 dam+0.020
 Bert+0.019
Neg logit contributions
five-0.017
 cheek-0.016
 mine-0.014
ige-0.013
 sidelines-0.013
Token together
Token ID1978
Feature activation+1.53e-02

Pos logit contributions
 Pig+0.024
wood+0.021
 Tweet+0.020
 known+0.020
 Bunny+0.020
Neg logit contributions
five-0.041
agging-0.040
 cheek-0.039
 mine-0.036
 sidelines-0.036
Token happily
Token ID18177
Feature activation-1.06e+00

Pos logit contributions
 Pig+0.001
 Tweet+0.000
 Beth+0.000
 Bunny+0.000
wood+0.000
Neg logit contributions
five-0.001
agging-0.001
 cheek-0.001
 mine-0.001
 fourteen-0.001
Token.
Token ID13
Feature activation+2.24e-01

Pos logit contributions
five+0.050
agging+0.048
 cheek+0.047
 fourteen+0.043
 mine+0.043
Neg logit contributions
 Pig-0.039
 Tweet-0.034
 Beth-0.034
 Bunny-0.033
 Ally-0.033
Token From
Token ID3574
Feature activation-5.44e-01

Pos logit contributions
 Pig+0.008
wood+0.007
 known+0.007
gy+0.007
 darker+0.007
Neg logit contributions
five-0.010
 cheek-0.009
agging-0.009
 Deal-0.009
 fourteen-0.009
Token that
Token ID326
Feature activation+9.48e-01

Pos logit contributions
five+0.020
agging+0.020
 cheek+0.019
 mine+0.018
 fourteen+0.018
Neg logit contributions
 Pig-0.024
wood-0.022
 known-0.022
 Tweet-0.022
gy-0.021
Token.
Token ID13
Feature activation+5.75e-03

Pos logit contributions
 Pig+0.061
 Tweet+0.053
 Beth+0.052
 Bunny+0.052
 Ally+0.052
Neg logit contributions
five-0.083
agging-0.080
 cheek-0.078
 fourteen-0.074
 mine-0.073
Token They
Token ID1119
Feature activation-1.24e-01

Pos logit contributions
 Pig+0.000
wood+0.000
 known+0.000
gy+0.000
 Ally+0.000
Neg logit contributions
five-0.000
 Deal-0.000
 cheek-0.000
agging-0.000
 fourteen-0.000
Token have
Token ID423
Feature activation-1.86e-01

Pos logit contributions
five+0.004
agging+0.004
 cheek+0.004
 fourteen+0.003
 mine+0.003
Neg logit contributions
 Pig-0.006
 Tweet-0.006
 Beth-0.005
 Bunny-0.005
 Ally-0.005
Token fun
Token ID1257
Feature activation+8.95e-01

Pos logit contributions
five+0.008
agging+0.008
 mine+0.008
 fourteen+0.007
 cheek+0.007
Neg logit contributions
 Pig-0.007
 Ally-0.006
 Bert-0.006
 Beth-0.006
 Bunny-0.006
Token and
Token ID290
Feature activation-2.57e-01

Pos logit contributions
 Pig+0.024
 Tweet+0.021
 Beth+0.020
gy+0.020
 Ch+0.020
Neg logit contributions
five-0.048
 cheek-0.046
agging-0.046
 Deal-0.045
ige-0.044
Token are
Token ID389
Feature activation+8.18e-01

Pos logit contributions
five+0.010
 cheek+0.009
agging+0.009
 mine+0.008
 sidelines+0.008
Neg logit contributions
 Pig-0.012
 Tweet-0.011
 Bunny-0.011
 Ally-0.011
 Beth-0.011
Token happy
Token ID3772
Feature activation-6.59e-01

Pos logit contributions
 Pig+0.037
wood+0.035
 Ally+0.034
 Bert+0.033
 Beth+0.033
Neg logit contributions
agging-0.031
 mine-0.030
 cheek-0.028
five-0.028
 fourteen-0.026
Token.
Token ID13
Feature activation-2.92e-01

Pos logit contributions
five+0.031
agging+0.030
 cheek+0.029
 fourteen+0.027
 mine+0.027
Neg logit contributions
 Pig-0.024
 Tweet-0.020
 Ally-0.020
 Beth-0.020
 known-0.020
Token<|endoftext|>
Token ID50256
Feature activation-3.82e-01

Pos logit contributions
five+0.014
agging+0.013
 cheek+0.013
 Deal+0.013
 fourteen+0.013
Neg logit contributions
 Pig-0.010
wood-0.008
gy-0.008
 Tweet-0.008
 known-0.008
TokenL
Token ID43
Feature activation+1.46e+00

Pos logit contributions
five+0.017
agging+0.016
 cheek+0.015
arl+0.015
 fourteen+0.015
Neg logit contributions
 Pig-0.014
 Beth-0.013
 Ally-0.013
 Tweet-0.013
gy-0.012
Tokenily
Token ID813
Feature activation+1.53e-01

Pos logit contributions
 Pig+0.059
 Bunny+0.051
 Beth+0.051
 called+0.051
 Tweet+0.050
Neg logit contributions
five-0.061
 cheek-0.060
 sidelines-0.058
agging-0.057
 Deal-0.054
Token,
Token ID11
Feature activation+1.05e-01

Pos logit contributions
 Pig+0.027
 known+0.024
 Ally+0.024
 Beth+0.024
 Bert+0.023
Neg logit contributions
five-0.030
 cheek-0.030
agging-0.029
 mine-0.028
arl-0.026
Token we
Token ID356
Feature activation-4.38e-01

Pos logit contributions
 Pig+0.006
gy+0.006
wood+0.006
 known+0.005
 increasingly+0.005
Neg logit contributions
 cheek-0.002
 mine-0.002
five-0.002
agging-0.002
 goodness-0.002
Token will
Token ID481
Feature activation+3.72e-01

Pos logit contributions
five+0.018
agging+0.017
 cheek+0.016
 mine+0.015
 fourteen+0.015
Neg logit contributions
 Pig-0.018
 Tweet-0.017
 Beth-0.016
 Ally-0.016
 Bunny-0.016
Token have
Token ID423
Feature activation-5.04e-01

Pos logit contributions
 Pig+0.016
 Tweet+0.014
 Beth+0.014
 Ally+0.014
 Bunny+0.014
Neg logit contributions
five-0.015
agging-0.014
 cheek-0.014
 fourteen-0.013
 mine-0.013
Token to
Token ID284
Feature activation-3.65e-01

Pos logit contributions
five+0.022
agging+0.021
 cheek+0.021
 mine+0.021
 fourteen+0.020
Neg logit contributions
 Pig-0.019
gy-0.017
 Ally-0.016
wood-0.016
 Bert-0.016
Token punish
Token ID6878
Feature activation+1.44e+00

Pos logit contributions
five+0.013
agging+0.013
 cheek+0.013
 mine+0.011
 fourteen+0.011
Neg logit contributions
 Pig-0.016
 Tweet-0.015
 Beth-0.015
 Ally-0.015
 Bunny-0.015
Token you
Token ID345
Feature activation+1.10e-01

Pos logit contributions
 Pig+0.088
 known+0.081
wood+0.081
 Tweet+0.081
gy+0.081
Neg logit contributions
five-0.029
 cheek-0.028
agging-0.027
 mine-0.023
 la-0.021
Token."
Token ID526
Feature activation+1.04e-01

Pos logit contributions
 Pig+0.005
 Tweet+0.005
 Bunny+0.004
gy+0.004
 Beth+0.004
Neg logit contributions
five-0.004
agging-0.004
 cheek-0.004
 sidelines-0.003
 fourteen-0.003
Token
Token ID220
Feature activation+6.45e-01

Pos logit contributions
 known+0.003
 Pig+0.003
 darker+0.003
 increasingly+0.003
 rou+0.003
Neg logit contributions
 cheek-0.005
five-0.005
 goodness-0.004
agging-0.004
 Deal-0.004
Token
Token ID198
Feature activation+3.13e-01

Pos logit contributions
 Pig+0.023
wood+0.021
 known+0.020
gy+0.020
 Tweet+0.020
Neg logit contributions
five-0.028
agging-0.027
 cheek-0.027
 Deal-0.026
arl-0.025
Token
Token ID198
Feature activation+7.26e-02

Pos logit contributions
 Pig+0.011
wood+0.009
 Tweet+0.009
gy+0.009
 Bunny+0.009
Neg logit contributions
five-0.015
agging-0.014
 cheek-0.014
arl-0.013
 Deal-0.013
Token her
Token ID607
Feature activation-7.05e-01

Pos logit contributions
five+0.030
agging+0.029
 cheek+0.029
 mine+0.027
 fourteen+0.027
Neg logit contributions
 Pig-0.021
 Tweet-0.018
wood-0.017
gy-0.017
 Bunny-0.017
Token fingers
Token ID9353
Feature activation-1.64e+00

Pos logit contributions
five+0.029
agging+0.027
 fourteen+0.026
 cheek+0.026
arl+0.025
Neg logit contributions
 Pig-0.029
 Tweet-0.026
 Beth-0.026
 Bunny-0.026
gy-0.026
Token and
Token ID290
Feature activation+3.28e-01

Pos logit contributions
five+0.078
agging+0.076
 cheek+0.074
 fourteen+0.069
 mine+0.068
Neg logit contributions
 Pig-0.057
 Tweet-0.050
 Beth-0.048
 Bunny-0.048
 Ally-0.048
Token before
Token ID878
Feature activation+7.30e-01

Pos logit contributions
 Pig+0.013
wood+0.012
gy+0.011
 Bunny+0.011
 Tweet+0.011
Neg logit contributions
five-0.014
 cheek-0.013
 mine-0.013
 la-0.012
 goodness-0.012
Token long
Token ID890
Feature activation+1.22e+00

Pos logit contributions
wood+0.032
gy+0.031
 Pig+0.030
 known+0.028
house+0.028
Neg logit contributions
 cheek-0.025
agging-0.024
 sidelines-0.024
five-0.023
 liking-0.023
Token,
Token ID11
Feature activation+1.65e-01

Pos logit contributions
 Pig+0.043
wood+0.040
 known+0.039
gy+0.038
 Tweet+0.037
Neg logit contributions
five-0.055
agging-0.053
 cheek-0.052
 fourteen-0.050
 mine-0.049
Token the
Token ID262
Feature activation-1.87e-01

Pos logit contributions
gy+0.008
wood+0.007
 Pig+0.007
 dam+0.006
bank+0.006
Neg logit contributions
five-0.006
 cheek-0.005
 goodness-0.005
 mine-0.005
 la-0.005
Token magic
Token ID5536
Feature activation+2.49e-01

Pos logit contributions
five+0.009
agging+0.008
 fourteen+0.008
 cheek+0.008
 Deal+0.008
Neg logit contributions
 Pig-0.007
 Tweet-0.006
 Beth-0.006
 Bunny-0.006
 Bert-0.006
Token had
Token ID550
Feature activation-2.14e-01

Pos logit contributions
 Pig+0.010
 known+0.009
 Tweet+0.009
gy+0.009
wood+0.009
Neg logit contributions
five-0.010
 cheek-0.010
agging-0.009
 mine-0.008
 fourteen-0.008
Token made
Token ID925
Feature activation+6.98e-01

Pos logit contributions
five+0.009
agging+0.009
 cheek+0.009
 fourteen+0.009
 mine+0.009
Neg logit contributions
 Pig-0.008
gy-0.007
wood-0.007
 Bunny-0.007
 Tweet-0.007
Token something
Token ID1223
Feature activation-2.38e-01

Pos logit contributions
gy+0.033
 Pig+0.032
wood+0.031
 dam+0.029
 Kang+0.028
Neg logit contributions
five-0.023
 goodness-0.020
 cheek-0.020
 mine-0.019
 icing-0.018
Token brave
Token ID14802
Feature activation-7.40e-01

Pos logit contributions
 Pig+0.022
wood+0.021
 Tweet+0.020
 Beth+0.019
 Bert+0.019
Neg logit contributions
five-0.022
 cheek-0.019
agging-0.018
 la-0.018
 mine-0.018
Tokenly
Token ID306
Feature activation-9.77e-01

Pos logit contributions
five+0.015
agging+0.014
 cheek+0.013
 fourteen+0.011
 mine+0.010
Neg logit contributions
 Pig-0.046
 Tweet-0.043
 Beth-0.042
 Bunny-0.042
 Ally-0.042
Token reached
Token ID4251
Feature activation-1.44e+00

Pos logit contributions
five+0.041
ige+0.036
 cheek+0.036
agging+0.036
 fourteen+0.035
Neg logit contributions
 Pig-0.037
 Tweet-0.036
wood-0.035
 Bert-0.034
 Beth-0.034
Token out
Token ID503
Feature activation-1.73e-02

Pos logit contributions
five+0.066
 cheek+0.060
agging+0.059
 mine+0.058
 fourteen+0.056
Neg logit contributions
 Pig-0.051
 known-0.046
gy-0.044
 Tweet-0.044
wood-0.043
Token and
Token ID290
Feature activation-1.35e-01

Pos logit contributions
five+0.001
agging+0.001
 cheek+0.001
 fourteen+0.001
 liking+0.001
Neg logit contributions
 Pig-0.001
wood-0.001
 known-0.001
gy-0.001
 Tweet-0.001
Token touched
Token ID12615
Feature activation+3.74e-01

Pos logit contributions
five+0.006
 cheek+0.005
leaf+0.005
 mine+0.005
 fourteen+0.004
Neg logit contributions
 Pig-0.006
wood-0.005
 known-0.005
gy-0.005
 Tweet-0.005
Token the
Token ID262
Feature activation+6.09e-01

Pos logit contributions
 Pig+0.015
gy+0.015
wood+0.015
 dam+0.014
 known+0.014
Neg logit contributions
five-0.014
 goodness-0.012
 mine-0.012
 fourteen-0.012
 cheek-0.012
Token ancient
Token ID6156
Feature activation+4.72e-01

Pos logit contributions
 Tweet+0.022
 Pig+0.022
 H+0.021
 Bunny+0.021
gy+0.020
Neg logit contributions
agging-0.025
five-0.025
 fourteen-0.024
arl-0.023
 Deal-0.022
Token skeleton
Token ID18328
Feature activation-2.57e-02

Pos logit contributions
 Pig+0.019
 Tweet+0.019
gy+0.018
 Bunny+0.018
 Bert+0.017
Neg logit contributions
agging-0.019
five-0.018
 Deal-0.018
 fourteen-0.017
arl-0.017
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
five+0.001
 cheek+0.001
agging+0.001
 mine+0.001
 fourteen+0.001
Neg logit contributions
 Pig-0.001
 known-0.001
 Tweet-0.001
 Beth-0.001
 Ally-0.001
Token She
Token ID1375
Feature activation+5.42e-01

Pos logit contributions
 Pig+0.006
 Tweet+0.005
 Beth+0.005
 Bunny+0.005
 Ally+0.005
Neg logit contributions
five-0.008
agging-0.008
 cheek-0.008
 fourteen-0.007
 mine-0.007
Token an
Token ID281
Feature activation-1.02e+00

Pos logit contributions
five+0.040
agging+0.039
 cheek+0.037
 mine+0.037
 fourteen+0.037
Neg logit contributions
 Pig-0.018
wood-0.015
 Ally-0.015
 Beth-0.015
gy-0.015
Token idea
Token ID2126
Feature activation-6.23e-01

Pos logit contributions
five+0.061
agging+0.061
 cheek+0.059
 mine+0.056
 fourteen+0.055
Neg logit contributions
 Pig-0.022
 Tweet-0.018
 Beth-0.018
 Bunny-0.017
gy-0.017
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
five+0.033
agging+0.032
 cheek+0.031
 fourteen+0.030
 Deal+0.030
Neg logit contributions
 Pig-0.019
 Tweet-0.016
 Beth-0.016
 Bunny-0.016
 Bert-0.015
Token He
Token ID679
Feature activation+2.14e-01

Pos logit contributions
five+0.011
 cheek+0.011
arl+0.010
agging+0.010
 Deal+0.010
Neg logit contributions
 known-0.012
 Pig-0.012
wood-0.011
gy-0.011
 Ally-0.010
Token ran
Token ID4966
Feature activation-1.07e+00

Pos logit contributions
 Pig+0.008
wood+0.007
 Beth+0.007
 Tweet+0.007
 known+0.007
Neg logit contributions
five-0.009
 cheek-0.009
agging-0.009
 mine-0.008
 fourteen-0.008
Token to
Token ID284
Feature activation-4.61e-01

Pos logit contributions
five+0.047
agging+0.042
 mine+0.041
 cheek+0.040
 sidelines+0.039
Neg logit contributions
 Pig-0.044
 known-0.038
wood-0.036
 Bunny-0.036
 Ally-0.036
Token get
Token ID651
Feature activation+4.15e-01

Pos logit contributions
five+0.023
 cheek+0.022
agging+0.022
 mine+0.020
 sidelines+0.020
Neg logit contributions
 Pig-0.015
wood-0.013
 Tweet-0.013
 known-0.012
gy-0.012
Token his
Token ID465
Feature activation+8.23e-02

Pos logit contributions
 Pig+0.016
gy+0.016
wood+0.015
 dam+0.015
house+0.015
Neg logit contributions
five-0.016
 mine-0.015
 cheek-0.014
leaf-0.014
 Deal-0.013
Token dad
Token ID9955
Feature activation+6.10e-01

Pos logit contributions
 Pig+0.004
 Tweet+0.003
 Beth+0.003
 Bunny+0.003
 Ally+0.003
Neg logit contributions
five-0.003
agging-0.003
 cheek-0.003
 fourteen-0.003
 mine-0.003
Token's
Token ID338
Feature activation+2.59e-01

Pos logit contributions
 Pig+0.024
 Tweet+0.021
 known+0.021
 Ally+0.021
 Beth+0.021
Neg logit contributions
five-0.026
agging-0.025
 cheek-0.025
 mine-0.023
 fourteen-0.022
Token ladder
Token ID18002
Feature activation-8.01e-01

Pos logit contributions
 Pig+0.012
 Tweet+0.011
 Beth+0.011
 Bunny+0.011
gy+0.011
Neg logit contributions
five-0.009
agging-0.009
 cheek-0.008
 fourteen-0.008
 Deal-0.007
Token Jack
Token ID3619
Feature activation-1.76e+00

Pos logit contributions
 Pig+0.015
 known+0.013
gy+0.013
wood+0.013
 Tweet+0.013
Neg logit contributions
five-0.021
agging-0.019
 cheek-0.019
 fourteen-0.019
 Deal-0.018
Token found
Token ID1043
Feature activation-1.01e+00

Pos logit contributions
five+0.084
agging+0.079
 cheek+0.079
 fourteen+0.074
 mine+0.073
Neg logit contributions
 Pig-0.061
 Tweet-0.054
wood-0.052
 Beth-0.052
 Ally-0.052
Token an
Token ID281
Feature activation-1.34e+00

Pos logit contributions
five+0.047
 fourteen+0.041
 mine+0.041
agging+0.041
 goodness+0.040
Neg logit contributions
 Pig-0.036
gy-0.034
wood-0.031
 Tweet-0.031
 Ally-0.030
Token old
Token ID1468
Feature activation+5.69e-01

Pos logit contributions
five+0.062
agging+0.060
 cheek+0.058
 fourteen+0.054
 mine+0.053
Neg logit contributions
 Pig-0.049
 Tweet-0.043
 Beth-0.042
 Bunny-0.042
 Ally-0.042
Token anchor
Token ID18021
Feature activation-1.72e+00

Pos logit contributions
 Pig+0.026
 Tweet+0.024
 Beth+0.024
 Bunny+0.024
 Ally+0.023
Neg logit contributions
five-0.020
agging-0.019
 cheek-0.019
 mine-0.017
 fourteen-0.017
Token and
Token ID290
Feature activation+1.85e-01

Pos logit contributions
five+0.071
agging+0.069
 cheek+0.068
 mine+0.063
 fourteen+0.062
Neg logit contributions
 Pig-0.069
 Tweet-0.062
 Beth-0.061
 known-0.061
 Ally-0.061
Token said
Token ID531
Feature activation+1.73e-01

Pos logit contributions
 Pig+0.007
gy+0.006
wood+0.006
 Tweet+0.006
 known+0.006
Neg logit contributions
five-0.008
 mine-0.007
 cheek-0.007
 fourteen-0.007
agging-0.007
Token:
Token ID25
Feature activation+6.95e-01

Pos logit contributions
 Pig+0.006
gy+0.005
wood+0.005
 Tweet+0.005
 Beth+0.005
Neg logit contributions
five-0.008
agging-0.008
 cheek-0.008
 mine-0.007
 fourteen-0.007
Token "
Token ID366
Feature activation+1.16e+00

Pos logit contributions
 Pig+0.026
 Tweet+0.023
 Bunny+0.022
 Beth+0.022
 Ally+0.022
Neg logit contributions
five-0.031
agging-0.031
 cheek-0.029
 fourteen-0.027
 mine-0.027
TokenThis
Token ID1212
Feature activation-9.69e-02

Pos logit contributions
 Pig+0.056
 Tweet+0.051
 Beth+0.050
 Bunny+0.050
 Ally+0.050
Neg logit contributions
five-0.039
agging-0.038
 cheek-0.037
 fourteen-0.033
 mine-0.032
Token will
Token ID481
Feature activation+6.31e-01

Pos logit contributions
five+0.004
agging+0.004
 cheek+0.004
 fourteen+0.003
 mine+0.003
Neg logit contributions
 Pig-0.004
 Tweet-0.004
 Beth-0.004
 Bunny-0.004
 Ally-0.004
Token castle
Token ID16669
Feature activation-6.20e-01

Pos logit contributions
 Pig+0.019
 Tweet+0.018
gy+0.017
 Bunny+0.017
 Beth+0.017
Neg logit contributions
five-0.020
agging-0.019
 cheek-0.018
 fourteen-0.018
 Deal-0.017
Token was
Token ID373
Feature activation+4.44e-01

Pos logit contributions
 cheek+0.028
five+0.027
agging+0.026
 mine+0.024
EEP+0.024
Neg logit contributions
 Pig-0.024
 Ally-0.022
wood-0.021
 Bunny-0.021
 Beth-0.021
Token safe
Token ID3338
Feature activation-4.84e-01

Pos logit contributions
 Pig+0.018
wood+0.017
 Ally+0.016
 Bert+0.016
 Beth+0.016
Neg logit contributions
agging-0.018
 cheek-0.017
 mine-0.017
five-0.016
 liking-0.015
Token.
Token ID13
Feature activation-1.89e-01

Pos logit contributions
agging+0.018
 cheek+0.018
five+0.017
 mine+0.016
 fourteen+0.015
Neg logit contributions
 Pig-0.021
 Ally-0.020
 known-0.019
 Beth-0.019
 Tweet-0.019
Token
Token ID198
Feature activation-4.15e-01

Pos logit contributions
five+0.009
 cheek+0.008
agging+0.008
 mine+0.008
EEP+0.008
Neg logit contributions
 Pig-0.007
 known-0.006
wood-0.006
 Ally-0.006
 Beth-0.005
Token
Token ID198
Feature activation-4.86e-01

Pos logit contributions
five+0.023
agging+0.022
 cheek+0.022
 fourteen+0.021
 mine+0.021
Neg logit contributions
 Pig-0.011
 Tweet-0.010
 Bunny-0.009
 Beth-0.009
 Ally-0.009
TokenLater
Token ID18602
Feature activation-2.61e-01

Pos logit contributions
five+0.021
agging+0.021
 cheek+0.021
 Deal+0.020
 la+0.019
Neg logit contributions
 Pig-0.019
 Tweet-0.018
house-0.017
gy-0.017
 Beth-0.017
Token that
Token ID326
Feature activation+1.33e+00

Pos logit contributions
five+0.011
agging+0.011
 cheek+0.010
 fourteen+0.009
 mine+0.009
Neg logit contributions
 Pig-0.011
 Tweet-0.010
 Beth-0.009
 Bunny-0.009
 Ally-0.009
Token day
Token ID1110
Feature activation+3.20e-01

Pos logit contributions
 Pig+0.038
 Tweet+0.032
 Beth+0.031
 Bunny+0.031
 Ally+0.030
Neg logit contributions
five-0.072
agging-0.070
 cheek-0.069
 fourteen-0.064
 mine-0.064
Token,
Token ID11
Feature activation+2.67e-01

Pos logit contributions
 Pig+0.009
wood+0.008
 Tweet+0.008
 known+0.008
 Ally+0.008
Neg logit contributions
five-0.017
agging-0.017
 cheek-0.016
 fourteen-0.015
 mine-0.015
Token Tim
Token ID5045
Feature activation-9.73e-01

Pos logit contributions
 Pig+0.009
wood+0.008
 known+0.007
 Ally+0.007
gy+0.007
Neg logit contributions
five-0.013
 mine-0.012
 cheek-0.012
 fourteen-0.012
agging-0.012
Token nice
Token ID3621
Feature activation+1.60e-01

Pos logit contributions
 Pig+0.017
 Beth+0.016
 Tweet+0.015
 Ally+0.015
 Bunny+0.015
Neg logit contributions
five-0.021
agging-0.021
 Deal-0.020
 fourteen-0.019
 cheek-0.019
Token tune
Token ID14009
Feature activation+6.24e-01

Pos logit contributions
 Pig+0.006
 Beth+0.006
 Ally+0.006
 Tweet+0.006
 Bunny+0.006
Neg logit contributions
five-0.007
agging-0.006
 cheek-0.006
 Deal-0.006
 fourteen-0.006
Token,
Token ID11
Feature activation+1.94e-02

Pos logit contributions
 Pig+0.023
 Tweet+0.020
 known+0.020
 Bunny+0.020
wood+0.020
Neg logit contributions
five-0.029
agging-0.028
 cheek-0.027
 fourteen-0.025
 mine-0.025
Token she
Token ID673
Feature activation-2.01e-01

Pos logit contributions
gy+0.001
 Pig+0.001
wood+0.001
 known+0.001
 Tweet+0.001
Neg logit contributions
five-0.001
 cheek-0.001
 goodness-0.001
 fourteen-0.001
agging-0.001
Token made
Token ID925
Feature activation+6.76e-01

Pos logit contributions
five+0.008
 cheek+0.008
agging+0.008
 la+0.008
 fourteen+0.007
Neg logit contributions
 Pig-0.008
wood-0.007
 Tweet-0.007
 Ally-0.007
 Bunny-0.007
Token lots
Token ID6041
Feature activation-2.71e+00

Pos logit contributions
 Pig+0.027
gy+0.026
wood+0.025
 Tweet+0.024
 Ally+0.023
Neg logit contributions
five-0.029
agging-0.026
 cheek-0.026
 goodness-0.025
 sidelines-0.024
Token of
Token ID286
Feature activation+5.42e-01

Pos logit contributions
five+0.098
agging+0.091
 cheek+0.086
 sidelines+0.078
 fourteen+0.077
Neg logit contributions
 Pig-0.134
gy-0.126
wood-0.121
 known-0.120
 Ally-0.119
Token strange
Token ID6283
Feature activation+1.63e+00

Pos logit contributions
 Pig+0.022
 Tweet+0.020
gy+0.019
 Bunny+0.019
wood+0.019
Neg logit contributions
five-0.023
agging-0.022
 cheek-0.022
 sidelines-0.020
 fourteen-0.019
Token noises
Token ID26782
Feature activation+8.36e-01

Pos logit contributions
 Pig+0.068
 Tweet+0.062
 Bunny+0.060
 known+0.059
gy+0.059
Neg logit contributions
five-0.069
agging-0.066
 cheek-0.064
 mine-0.057
 goodness-0.057
Token.
Token ID13
Feature activation+3.58e-01

Pos logit contributions
 Pig+0.033
 Tweet+0.029
gy+0.029
 known+0.029
 Ally+0.029
Neg logit contributions
five-0.036
agging-0.035
 cheek-0.033
 fourteen-0.032
 mine-0.031
Token
Token ID198
Feature activation-1.75e-01

Pos logit contributions
 Pig+0.012
gy+0.011
 Tweet+0.011
wood+0.011
 known+0.011
Neg logit contributions
five-0.016
 cheek-0.015
agging-0.015
 Deal-0.015
 goodness-0.014
Token of
Token ID286
Feature activation+9.04e-01

Pos logit contributions
 Pig+0.016
 known+0.016
wood+0.016
gy+0.016
 increasingly+0.015
Neg logit contributions
five-0.007
agging-0.006
 mine-0.006
 cheek-0.005
 la-0.005
Token the
Token ID262
Feature activation-7.72e-03

Pos logit contributions
wood+0.034
 Pig+0.033
 increasingly+0.029
 known+0.029
 rou+0.028
Neg logit contributions
five-0.035
 fourteen-0.035
agging-0.035
 mine-0.034
 cheek-0.033
Token day
Token ID1110
Feature activation-8.01e-01

Pos logit contributions
five+0.000
agging+0.000
 cheek+0.000
 Deal+0.000
arl+0.000
Neg logit contributions
 Pig-0.000
 Tweet-0.000
 Ally-0.000
 Bunny-0.000
 Beth-0.000
Token,
Token ID11
Feature activation-1.49e-01

Pos logit contributions
five+0.032
agging+0.029
 goodness+0.028
 la+0.028
 mine+0.028
Neg logit contributions
 Pig-0.032
wood-0.031
gy-0.031
 known-0.030
 increasingly-0.028
Token they
Token ID484
Feature activation-6.78e-01

Pos logit contributions
five+0.006
 mine+0.006
 cheek+0.005
 la+0.005
 fourteen+0.005
Neg logit contributions
wood-0.006
 Pig-0.006
 known-0.005
gy-0.005
 dam-0.005
Token both
Token ID1111
Feature activation-3.35e+00

Pos logit contributions
five+0.029
agging+0.027
 cheek+0.027
ige+0.026
 mine+0.025
Neg logit contributions
 Pig-0.025
wood-0.024
gy-0.023
 Tweet-0.022
 Beth-0.022
Token knew
Token ID2993
Feature activation-1.54e+00

Pos logit contributions
five+0.134
 cheek+0.119
agging+0.114
ige+0.113
 la+0.113
Neg logit contributions
 Pig-0.140
wood-0.135
 Tweet-0.127
 Bert-0.125
gy-0.124
Token they
Token ID484
Feature activation-5.40e-01

Pos logit contributions
 mine+0.046
five+0.043
agging+0.043
 cheek+0.043
 fourteen+0.041
Neg logit contributions
 Pig-0.070
gy-0.068
wood-0.067
 known-0.065
 increasingly-0.063
Token would
Token ID561
Feature activation-1.15e-01

Pos logit contributions
five+0.025
agging+0.024
 cheek+0.023
 mine+0.022
 fourteen+0.021
Neg logit contributions
 Pig-0.020
 Tweet-0.017
wood-0.017
 Beth-0.017
 Bunny-0.017
Token be
Token ID307
Feature activation-1.14e-01

Pos logit contributions
five+0.004
agging+0.004
 cheek+0.004
 mine+0.004
 fourteen+0.004
Neg logit contributions
 Pig-0.005
 Beth-0.004
wood-0.004
 Tweet-0.004
 Bunny-0.004
Token best
Token ID1266
Feature activation+1.03e+00

Pos logit contributions
agging+0.004
 mine+0.004
five+0.004
 cheek+0.004
ige+0.004
Neg logit contributions
wood-0.005
 Pig-0.005
 Bert-0.004
 Beth-0.004
stal-0.004
Token he
Token ID339
Feature activation-3.13e-01

Pos logit contributions
five+0.014
 cheek+0.014
agging+0.014
 mine+0.013
 fourteen+0.013
Neg logit contributions
 Pig-0.014
gy-0.013
wood-0.013
 known-0.013
 Beth-0.013
Token had
Token ID550
Feature activation-6.00e-01

Pos logit contributions
five+0.014
agging+0.013
 cheek+0.013
 mine+0.012
 fourteen+0.012
Neg logit contributions
 Pig-0.012
 Tweet-0.010
 Beth-0.010
wood-0.010
gy-0.010
Token never
Token ID1239
Feature activation-1.25e+00

Pos logit contributions
five+0.031
agging+0.030
 cheek+0.029
arl+0.028
 Deal+0.027
Neg logit contributions
 Pig-0.019
 Tweet-0.016
 known-0.016
 Bunny-0.016
 Beth-0.016
Token seen
Token ID1775
Feature activation-1.00e+00

Pos logit contributions
five+0.047
agging+0.045
 cheek+0.044
 mine+0.040
 fourteen+0.040
Neg logit contributions
 Pig-0.055
 Beth-0.050
 Tweet-0.050
 Ally-0.049
 Bunny-0.049
Token this
Token ID428
Feature activation-8.25e-01

Pos logit contributions
five+0.043
 fourteen+0.042
 mine+0.041
agging+0.041
 cheek+0.039
Neg logit contributions
 Pig-0.035
gy-0.034
wood-0.032
house-0.032
 Ally-0.031
Token many
Token ID867
Feature activation-2.64e+00

Pos logit contributions
five+0.033
 cheek+0.032
agging+0.032
 mine+0.032
 fourteen+0.030
Neg logit contributions
 Pig-0.032
 Beth-0.030
 known-0.029
gy-0.029
wood-0.029
Token fish
Token ID5916
Feature activation-5.90e-01

Pos logit contributions
five+0.105
agging+0.103
 cheek+0.098
 mine+0.092
 fourteen+0.090
Neg logit contributions
 Pig-0.112
 Tweet-0.100
gy-0.100
 Beth-0.099
wood-0.098
Token before
Token ID878
Feature activation+3.41e-01

Pos logit contributions
five+0.028
agging+0.027
 cheek+0.026
 fourteen+0.025
 Deal+0.025
Neg logit contributions
 Pig-0.021
 Tweet-0.018
 Bunny-0.018
 Beth-0.018
gy-0.017
Token.
Token ID13
Feature activation+2.76e-01

Pos logit contributions
 Pig+0.013
 Beth+0.012
 Tweet+0.012
 known+0.012
gy+0.012
Neg logit contributions
agging-0.014
five-0.014
 cheek-0.014
 mine-0.013
 fourteen-0.012
Token He
Token ID679
Feature activation+3.51e-01

Pos logit contributions
 Pig+0.010
 known+0.010
gy+0.009
 Ally+0.009
 Beth+0.009
Neg logit contributions
five-0.012
 cheek-0.011
agging-0.011
 Deal-0.010
 fourteen-0.010
Token was
Token ID373
Feature activation+2.34e-01

Pos logit contributions
 Pig+0.013
 Beth+0.012
wood+0.012
 Tweet+0.012
 Ally+0.011
Neg logit contributions
five-0.015
 cheek-0.014
agging-0.014
 mine-0.013
 fourteen-0.013
Token little
Token ID1310
Feature activation+7.05e-01

Pos logit contributions
 Pig+0.006
 Ally+0.005
 known+0.005
 Tweet+0.005
 Beth+0.005
Neg logit contributions
 cheek-0.007
five-0.006
agging-0.006
 mine-0.006
 goodness-0.006
Token boy
Token ID2933
Feature activation+1.92e+00

Pos logit contributions
 known+0.033
ained+0.032
 Ally+0.031
 Days+0.030
 Pig+0.030
Neg logit contributions
 cheek-0.025
five-0.022
 mine-0.019
 fork-0.019
 goodness-0.019
Token some
Token ID617
Feature activation-1.05e+00

Pos logit contributions
 Pig+0.065
 Beth+0.056
 Ally+0.056
 Tweet+0.055
 Bert+0.053
Neg logit contributions
five-0.099
agging-0.087
 cheek-0.086
 mine-0.083
 fourteen-0.083
Token of
Token ID286
Feature activation+6.46e-01

Pos logit contributions
five+0.040
agging+0.039
 cheek+0.038
 fourteen+0.035
 Deal+0.034
Neg logit contributions
 Pig-0.046
 Tweet-0.042
 Bunny-0.041
 Beth-0.040
 Ally-0.040
Token his
Token ID465
Feature activation-2.91e-01

Pos logit contributions
gy+0.022
 Pig+0.022
house+0.022
wood+0.021
 darker+0.020
Neg logit contributions
five-0.028
agging-0.026
 cheek-0.025
 mine-0.025
 fourteen-0.025
Token lunch
Token ID9965
Feature activation-2.60e+00

Pos logit contributions
five+0.011
 cheek+0.011
agging+0.011
 mine+0.010
 goodness+0.010
Neg logit contributions
 Pig-0.012
 Beth-0.011
 Ally-0.011
 known-0.011
 Tweet-0.011
Token and
Token ID290
Feature activation+4.18e-01

Pos logit contributions
five+0.120
agging+0.116
 cheek+0.114
 fourteen+0.104
 mine+0.104
Neg logit contributions
 Pig-0.093
 Tweet-0.083
 Beth-0.081
 Ally-0.081
 known-0.080
Token they
Token ID484
Feature activation+4.40e-01

Pos logit contributions
 Pig+0.015
ained+0.015
wood+0.014
 darker+0.014
gy+0.014
Neg logit contributions
five-0.017
 cheek-0.015
 fourteen-0.015
 mine-0.015
 slice-0.014
Token had
Token ID550
Feature activation-4.22e-02

Pos logit contributions
 Pig+0.018
wood+0.016
 Tweet+0.016
 Beth+0.016
 Ally+0.015
Neg logit contributions
five-0.018
agging-0.017
 cheek-0.016
 fourteen-0.016
 mine-0.016
Token a
Token ID257
Feature activation+5.37e-01

Pos logit contributions
five+0.002
agging+0.002
 mine+0.002
 cheek+0.002
 fourteen+0.002
Neg logit contributions
 Pig-0.001
 Beth-0.001
 Ally-0.001
gy-0.001
 Tweet-0.001
Token happy
Token ID3772
Feature activation-7.75e-01

Pos logit contributions
 Pig+0.023
wood+0.021
 Tweet+0.020
 Beth+0.020
gy+0.020
Neg logit contributions
five-0.022
agging-0.020
 cheek-0.020
 mine-0.019
 fourteen-0.018
Token notebook
Token ID20922
Feature activation-1.15e+00

Pos logit contributions
five+0.008
agging+0.008
 cheek+0.008
 mine+0.007
 fourteen+0.007
Neg logit contributions
 Pig-0.008
 Tweet-0.008
 Beth-0.007
 Bunny-0.007
 known-0.007
Token.
Token ID13
Feature activation+8.32e-01

Pos logit contributions
five+0.052
agging+0.050
 cheek+0.050
 mine+0.047
 fourteen+0.046
Neg logit contributions
 Pig-0.042
 Tweet-0.037
 known-0.036
 Bunny-0.036
 Ally-0.036
Token
Token ID198
Feature activation+3.68e-01

Pos logit contributions
 Pig+0.032
 known+0.029
wood+0.028
gy+0.028
 Tweet+0.027
Neg logit contributions
five-0.035
 mine-0.032
 cheek-0.031
agging-0.031
 fourteen-0.031
Token
Token ID198
Feature activation+1.92e-01

Pos logit contributions
 Pig+0.013
 Tweet+0.011
wood+0.011
gy+0.011
 Bunny+0.011
Neg logit contributions
five-0.017
agging-0.016
 cheek-0.016
 fourteen-0.015
arl-0.015
TokenThey
Token ID2990
Feature activation-1.06e-01

Pos logit contributions
 Pig+0.010
 Tweet+0.009
 Beth+0.009
 Ally+0.009
 Bunny+0.009
Neg logit contributions
five-0.005
agging-0.005
 cheek-0.005
 fourteen-0.004
 Deal-0.004
Token both
Token ID1111
Feature activation-2.86e+00

Pos logit contributions
five+0.005
agging+0.004
 mine+0.004
 cheek+0.004
 fourteen+0.004
Neg logit contributions
 Pig-0.004
 Tweet-0.004
wood-0.004
 Bunny-0.003
gy-0.003
Token argued
Token ID7189
Feature activation-1.29e+00

Pos logit contributions
five+0.121
agging+0.112
 cheek+0.109
 fourteen+0.103
 mine+0.103
Neg logit contributions
 Pig-0.118
 Tweet-0.106
 Bunny-0.103
wood-0.103
 Ally-0.101
Token,
Token ID11
Feature activation+4.84e-01

Pos logit contributions
five+0.058
agging+0.056
 cheek+0.054
 fourteen+0.051
 mine+0.050
Neg logit contributions
 Pig-0.049
 Tweet-0.043
 Bunny-0.042
 Beth-0.042
 Ally-0.041
Token but
Token ID475
Feature activation+5.22e-01

Pos logit contributions
 Pig+0.020
 Tweet+0.017
wood+0.017
gy+0.017
 Bunny+0.017
Neg logit contributions
five-0.020
agging-0.019
 cheek-0.019
 fourteen-0.018
 mine-0.018
Token neither
Token ID6159
Feature activation-5.20e-01

Pos logit contributions
 Pig+0.021
wood+0.019
gy+0.018
 Tweet+0.018
 dam+0.018
Neg logit contributions
 mine-0.021
five-0.020
 fourteen-0.019
 cheek-0.019
agging-0.019
Token one
Token ID530
Feature activation+3.79e-01

Pos logit contributions
five+0.022
agging+0.020
 cheek+0.020
 mine+0.019
 fourteen+0.019
Neg logit contributions
 Pig-0.021
 Tweet-0.019
gy-0.019
wood-0.019
 Bunny-0.018