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

    Neuronpedia

    INDEX
    Explanations

    technical terms and mathematical formulas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    awaru
    -1.23
    ivated
    -1.20
    ODUCT
    -1.18
    dyl
    -1.17
    abies
    -1.15
    rieved
    -1.13
    oulos
    -1.10
    rican
    -1.09
    ģĸ
    -1.07
    olkien
    -1.06
    POSITIVE LOGITS
    phrine
    2.38
    lla
    1.70
    jad
    1.69
    lihood
    1.46
    llo
    1.43
    hart
    1.39
    backer
    1.35
    lli
    1.28
    clude
    1.26
    Motion
    1.15
    Act Density 1.770%

    No Known Activations