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

    Neuronpedia

    INDEX
    Explanations

    words related to negative or controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    words related to negative societal issues and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.76
    cipled
    -0.74
    stood
    -0.70
    TPPStreamerBot
    -0.67
     uphill
    -0.67
     decorated
    -0.66
     readable
    -0.66
    cised
    -0.64
    ĸļ
    -0.63
    FUL
    -0.63
    POSITIVE LOGITS
    ieties
    1.20
    usions
    1.12
    otypes
    1.11
    tones
    1.11
    aunts
    1.11
    acies
    1.11
    acements
    1.11
    isms
    1.10
    ancies
    1.06
    ocations
    1.05
    Act Density 0.495%

    No Known Activations