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

    Neuronpedia

    INDEX
    Explanations

    references to technical and statistical concepts related to causation and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.54
     sch
    -0.50
    erei
    -0.45
     Schre
    -0.45
    camp
    -0.45
    ագր
    -0.41
    met
    -0.40
     forder
    -0.40
    sqrt
    -0.40
     T
    -0.39
    POSITIVE LOGITS
    Personendaten
    1.05
    RenderAtEndOf
    0.95
     auroit
    0.87
     חיצוניים
    0.83
     avoient
    0.82
     HasFactory
    0.80
     autorytatywna
    0.80
     feroit
    0.79
    UnusedPrivate
    0.78
     pouvoit
    0.78
    Act Density 1.200%

    No Known Activations