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

    Neuronpedia

    INDEX
    Explanations

    words related to opposition or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to opposition or resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.75
    reau
    -0.75
    nces
    -0.75
    horn
    -0.75
    negie
    -0.72
    utical
    -0.70
    ndra
    -0.70
    tesy
    -0.70
     largeDownload
    -0.68
    itz
    -0.67
    POSITIVE LOGITS
     anything
    0.80
     overturn
    0.75
     convict
    0.75
     vehemently
    0.74
     vigorously
    0.72
     defend
    0.72
     oppose
    0.71
     stray
    0.70
     dissent
    0.68
     communism
    0.68
    Act Density 0.090%

    No Known Activations