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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rchen
    0.52
    is
    0.48
    kilometer
    0.47
    Weiter
    0.47
    cher
    0.46
    CHER
    0.46
    kyverno
    0.46
    Electricity
    0.45
    ningen
    0.45
     leafy
    0.45
    POSITIVE LOGITS
    ll
    0.43
     duplication
    0.42
    ם
    0.42
     Party
    0.41
    ၌
    0.41
     nerfs
    0.41
     iglesia
    0.40
     duplicating
    0.40
    อส
    0.40
     adultery
    0.40
    Act Density 0.001%

    No Known Activations