INDEX
Explanations
references to the name "Carl"
the mention of the name "Carl."
New Auto-Interp
Negative Logits
HER
-0.70
BLE
-0.69
vetting
-0.63
nomine
-0.63
jihad
-0.62
termination
-0.61
scant
-0.61
lled
-0.60
ELL
-0.60
gearing
-0.60
POSITIVE LOGITS
isle
1.61
otta
1.04
obal
1.02
Sagan
0.98
stadt
0.96
ota
0.92
sson
0.92
osaurus
0.91
izabeth
0.91
sen
0.90
Activations Density 0.017%