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

    Neuronpedia

    INDEX
    Explanations

    explicit mentions and discussions of opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gutenberg
    -0.78
     Danger
    -0.73
     Roose
    -0.70
    mers
    -0.68
    mable
    -0.68
    enegger
    -0.66
     Roses
    -0.65
    tons
    -0.65
    bang
    -0.65
     Intermediate
    -0.64
    POSITIVE LOGITS
     opinion
    0.87
     opinions
    0.85
    atorial
    0.83
    ated
    0.78
     polls
    0.77
    Ĵ
    0.77
    obook
    0.77
    atively
    0.77
    odox
    0.76
     largeDownload
    0.76
    Act Density 0.042%

    No Known Activations