INDEX
Explanations
references to peppers and spicy ingredients in food contexts
New Auto-Interp
Negative Logits
للاسماء
-0.50
AsUp
-0.46
awtextra
-0.46
kasarigan
-0.45
cruz
-0.44
Bioaccumulative
-0.43
solas
-0.43
Crea
-0.42
sue
-0.41
Monto
-0.41
POSITIVE LOGITS
peppers
1.80
Peppers
1.50
pepper
1.19
poiv
0.85
Pepper
0.81
перец
0.76
pepper
0.72
🫑
0.71
Pepper
0.71
simmon
0.61
Activations Density 0.003%