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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     or
    1.68
     to
    1.54
     and
    1.48
     all
    1.34
     certain
    1.27
     impressively
    1.25
     Hoos
    1.23
     if
    1.20
     in
    1.17
     almighty
    1.16
    POSITIVE LOGITS
    ли
    1.55
    ج
    1.52
    an
    1.47
    ان
    1.46
    áme
    1.45
    ल
    1.45
    риев
    1.41
    anlagen
    1.41
    ap
    1.40
     católica
    1.39
    Act Density 0.114%

    No Known Activations