INDEX
Explanations
references to a specific individual named Perez
occurrences of the name "Perez."
New Auto-Interp
Negative Logits
ories
-0.99
ivities
-0.82
orically
-0.82
ruciating
-0.79
urst
-0.78
RAFT
-0.77
ocaust
-0.76
liest
-0.74
liness
-0.73
orical
-0.73
POSITIVE LOGITS
Hilton
0.79
ocalypse
0.78
Perez
0.78
ilon
0.77
ktop
0.77
anut
0.73
Maker
0.72
icer
0.72
ach
0.70
irez
0.70
Activations Density 0.016%