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

    Neuronpedia

    INDEX
    Explanations

    dates or days of the week

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.74
    framework
    -0.73
    onne
    -0.69
    ogly
    -0.67
    ById
    -0.65
    leeve
    -0.65
    arah
    -0.63
    Condition
    -0.62
    acci
    -0.61
    ggle
    -0.61
    POSITIVE LOGITS
     marks
    1.14
    's
    1.09
     marked
    0.92
     we
    0.91
     brings
    0.89
     was
    0.86
     corresponds
    0.79
     saw
    0.79
     is
    0.78
     sees
    0.78
    Act Density 0.126%

    No Known Activations