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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to social and communal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    organized
    -0.70
    etimes
    -0.67
    folio
    -0.67
    agos
    -0.66
    odiac
    -0.64
    quer
    -0.64
    elta
    -0.64
    endars
    -0.64
     printers
    -0.63
    idis
    -0.63
    POSITIVE LOGITS
     aloud
    1.25
     ABOUT
    1.03
     about
    0.98
     objections
    0.93
     concerning
    0.93
     incred
    0.92
     disbelief
    0.91
     regarding
    0.89
     loudly
    0.89
     uttered
    0.88
    Act Density 0.686%

    No Known Activations