INDEX
Explanations
pronouns
The neuron responds to personal pronouns (e.g. you, she, her) and other small subject-referencing words.
New Auto-Interp
Negative Logits
mái
-0.07
警
-0.07
Shot
-0.06
협
-0.06
ifiant
-0.06
modele
-0.06
způsob
-0.06
_UL
-0.06
coupon
-0.06
hooks
-0.06
POSITIVE LOGITS
persists
0.07
}));↵
0.07
Angie
0.07
perseverance
0.06
?',↵
0.06
asmine
0.06
vX
0.06
�
0.06
/team
0.06
/org
0.06
Activations Density 0.011%