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

    Neuronpedia

    INDEX
    Explanations

    titles or headings related to topics or sections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratom
    -0.71
    gm
    -0.69
     Kahn
    -0.63
     Spicer
    -0.62
     Spice
    -0.61
    eln
    -0.60
     Rhino
    -0.60
    eu
    -0.60
    lynn
    -0.59
     Stef
    -0.59
    POSITIVE LOGITS
    marks
    0.88
    pins
    0.83
    manship
    0.81
    title
    0.77
    mast
    0.75
    eous
    0.75
    marked
    0.73
    plates
    0.73
    knife
    0.72
    ¥µ
    0.72
    Act Density 0.699%

    No Known Activations