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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     games
    0.57
     prison
    0.54
     Bark
    0.53
    prison
    0.51
     cricket
    0.50
     I
    0.49
     acting
    0.48
     אם
    0.47
     तो
    0.46
     extradition
    0.46
    POSITIVE LOGITS
    н
    0.51
    eti
    0.48
     sacc
    0.45
    opf
    0.44
     нео
    0.43
    0.43
    шек
    0.42
    зо
    0.41
    uais
    0.41
     долго
    0.40
    Act Density 0.000%

    No Known Activations