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

    Neuronpedia

    INDEX
    Explanations

    the term "out," indicating outputs or results in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.05
     referenties
    -1.02
    GEBURTSDATUM
    -0.92
     Roskov
    -0.89
     виправивши
    -0.86
    principalTable
    -0.81
    studium
    -0.81
     الرخصة
    -0.81
    migrationBuilder
    -0.81
    ₂)
    -0.80
    POSITIVE LOGITS
    y
    0.82
    an
    0.67
    Output
    0.65
    z
    0.61
    w
    0.60
     output
    0.58
    output
    0.56
     Goss
    0.56
    ou
    0.56
     Output
    0.56
    Act Density 0.006%

    No Known Activations