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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or entities related to people or places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ative
    -0.72
    ierrez
    -0.71
    ND
    -0.68
    rency
    -0.65
    ourced
    -0.63
     deposition
    -0.63
     aside
    -0.63
    ensical
    -0.62
    OURCE
    -0.61
     congestion
    -0.60
    POSITIVE LOGITS
     Be
    3.22
    Be
    2.14
     BE
    1.75
    Bey
    1.69
    be
    1.52
     Beaver
    1.35
     Beware
    1.23
     Been
    1.22
    Beg
    1.19
     Go
    1.16
    Act Density 0.022%

    No Known Activations