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

    Neuronpedia

    INDEX
    Explanations

    words related to suppression of dissent

    oai_token-act-pair · gpt-3.5-turbo

    references to dissent and actions related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onut
    -0.69
     Tycoon
    -0.67
     stakes
    -0.65
    ammy
    -0.65
     GENERAL
    -0.63
    ohyd
    -0.62
    illac
    -0.61
    onz
    -0.60
     Mineral
    -0.59
    ategory
    -0.59
    POSITIVE LOGITS
    ers
    1.01
     dissent
    0.90
    ible
    0.85
    iates
    0.84
     aloud
    0.81
    ership
    0.80
    ously
    0.77
    ively
    0.77
    rained
    0.75
    iating
    0.75
    Act Density 0.019%

    No Known Activations