INDEX
Explanations
mentions of the name "McCarthy" in the text
mentions of the name "McCarthy"
New Auto-Interp
Negative Logits
gered
-0.69
orable
-0.68
worthiness
-0.66
orative
-0.65
ifts
-0.64
ultan
-0.63
chest
-0.63
hang
-0.62
PUT
-0.62
LOAD
-0.62
POSITIVE LOGITS
igans
0.94
McCarthy
0.91
ãĥ£
0.87
isms
0.80
ite
0.74
enthal
0.74
igan
0.73
gren
0.71
ites
0.70
arella
0.70
Activations Density 0.023%