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

    Neuronpedia

    INDEX
    Explanations

    references to media and entertainment like movies, books, video games, and music

    oai_token-act-pair · gpt-3.5-turbo

    references to rankings and popularity of video games, films, and music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.69
    ruciating
    -0.65
    igham
    -0.63
    llah
    -0.62
    MODE
    -0.62
    FLAG
    -0.62
    IER
    -0.60
    irrel
    -0.59
    urat
    -0.58
    rir
    -0.57
    POSITIVE LOGITS
     EVER
    1.44
     ever
    1.29
     Ever
    1.08
    ever
    0.85
    Ever
    0.84
     of
    0.84
     since
    0.80
     yet
    0.79
     imaginable
    0.77
     anywhere
    0.75
    Act Density 0.181%

    No Known Activations