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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    the start or end of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chaser
    -0.71
     wiser
    -0.61
     assum
    -0.60
     uphill
    -0.58
     destro
    -0.56
     buggy
    -0.55
     Cinderella
    -0.54
    cheat
    -0.54
     cyn
    -0.54
     Gemini
    -0.53
    POSITIVE LOGITS
    erville
    0.66
    heng
    0.65
    ;;;;;;;;;;;;
    0.64
     Refugees
    0.63
    thood
    0.62
    ocaust
    0.62
    iery
    0.61
    ATIONAL
    0.61
     ILCS
    0.60
     Caption
    0.60
    Act Density 0.219%

    No Known Activations