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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions referencing proportions or ratios

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.84
     Assignee
    -0.70
    ernsey
    -0.68
    cektir
    -0.67
    zessin
    -0.62
     CURIAM
    -0.61
     Préférences
    -0.61
    tissement
    -0.60
    ariate
    -0.60
    lismo
    -0.60
    POSITIVE LOGITS
    UnsafeEnabled
    0.61
     skj
    0.60
     doubled
    0.59
    //
    0.59
    WebVitals
    0.57
     PLWABN
    0.56
     doubling
    0.55
    tele
    0.54
     bouteilles
    0.54
    wide
    0.52
    Act Density 0.012%

    No Known Activations