INDEX
Explanations
mentions of a specific name "Ike."
the repeated use of the word "like" in various contexts
New Auto-Interp
Negative Logits
ILCS
-0.89
istics
-0.77
istry
-0.73
porary
-0.66
rooms
-0.66
amental
-0.66
stru
-0.65
istically
-0.64
ples
-0.63
ogyn
-0.63
POSITIVE LOGITS
lihood
0.93
mens
0.91
bike
0.86
aukee
0.76
li
0.73
jriwal
0.71
wik
0.71
manship
0.70
IGH
0.69
anu
0.67
Activations Density 0.042%