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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes in a structured format

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    esides
    -0.73
    anwhile
    -0.66
     crossings
    -0.64
    erella
    -0.61
    entials
    -0.60
    hement
    -0.59
    luster
    -0.59
    autical
    -0.59
    enegger
    -0.58
     intersections
    -0.58
    POSITIVE LOGITS
     alias
    0.71
    ©¶æ
    0.67
    ãĤ¦ãĤ¹
    0.67
     Member
    0.64
    Script
    0.64
    ð
    0.63
     {"
    0.63
    bos
    0.63
    false
    0.63
     è£ıç
    0.62
    Act Density 0.261%

    No Known Activations