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

    Neuronpedia

    INDEX
    Explanations

    common words used in technical instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlEnum
    -0.78
     Kategor
    -0.69
     FBref
    -0.67
     exé
    -0.66
     komik
    -0.65
    ihnachten
    -0.64
     BIBSYS
    -0.64
     kaos
    -0.63
     kategor
    -0.63
     soutient
    -0.63
    POSITIVE LOGITS
     intersper
    0.91
     encomp
    0.85
     whatnot
    0.77
     shenan
    0.77
     unspeak
    0.75
     disagre
    0.75
     vainly
    0.72
     indescri
    0.71
     increa
    0.71
     reccom
    0.70
    Act Density 0.389%

    No Known Activations