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

    Neuronpedia

    INDEX
    Explanations

    phrases related to general statements about people

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express general agreement or disagreement among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NEXT
    -0.67
     Advertisement
    -0.66
     largeDownload
    -0.66
     ................
    -0.65
     Void
    -0.65
    )].
    -0.63
    cule
    -0.63
     =================================================================
    -0.62
     TAMADRA
    -0.61
     ACTIONS
    -0.61
    POSITIVE LOGITS
     anymore
    0.76
     appe
    0.72
    asio
    0.72
    acea
    0.70
    ones
    0.67
     fortun
    0.66
     necessarily
    0.63
    ASON
    0.63
    ernel
    0.62
    ardy
    0.62
    Act Density 0.033%

    No Known Activations