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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric values and quantifiable changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astify
    -0.83
    tvguidetime
    -0.82
    IUrlHelper
    -0.73
     GenerationType
    -0.70
    (&:
    -0.67
    بوابة
    -0.65
    "];
    -0.65
     المعيارى
    -0.65
    Enllaces
    -0.64
     Audiodateien
    -0.63
    POSITIVE LOGITS
    The
    0.69
    There
    0.67
     The
    0.67
     There
    0.66
    When
    0.64
     If
    0.64
     When
    0.63
    If
    0.61
    In
    0.59
     In
    0.57
    Act Density 0.176%

    No Known Activations