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

    Neuronpedia

    INDEX
    Explanations

    specific instances of an exact match in text, such as a repeated phrase or concept

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or structures that emphasize consistency or similarity in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.74
    bp
    -0.65
    ways
    -0.64
     respectfully
    -0.63
    meric
    -0.62
    cest
    -0.60
     Louie
    -0.60
    igion
    -0.60
    cellaneous
    -0.59
    Pg
    -0.59
    POSITIVE LOGITS
    è¦
    0.73
    irements
    0.70
    IELD
    0.67
    ettings
    0.66
     guiActiveUn
    0.64
    à¨
    0.64
    ÑĤ
    0.64
     happened
    0.63
    ãĥ¯
    0.61
    isites
    0.60
    Act Density 0.066%

    No Known Activations