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

    Neuronpedia

    INDEX
    Explanations

    elements like email addresses or perhaps computer codes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Ferr
    -0.83
    e
    -0.74
    MAS
    -0.67
    rawdownloadcloneembedreportprint
    -0.65
    Austral
    -0.63
    BRE
    -0.63
    cens
    -0.61
     Palest
    -0.61
     Stall
    -0.61
     Leilan
    -0.61
    POSITIVE LOGITS
    zyk
    1.14
    ough
    1.06
    augh
    0.98
    acca
    0.96
    oulos
    0.96
    ahn
    0.95
    obb
    0.95
    anca
    0.93
    razil
    0.93
    ouls
    0.93
    Act Density 0.128%

    No Known Activations