Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -
    0.49
     GPU
    0.48
     stems
    0.47
     ent
    0.46
      
    0.45
    _
    0.44
     applied
    0.43
     vending
    0.43
     ATM
    0.42
     IP
    0.42
    POSITIVE LOGITS
    觥
    0.51
     Сен
    0.51
     ஆனால்
    0.50
     sayılı
    0.49
    倨
    0.47
    保养
    0.47
     ennemis
    0.46
     ریکارڈ
    0.46
     افتتاح
    0.46
     வள
    0.45
    Act Density 0.007%

    No Known Activations