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

    Neuronpedia

    INDEX
    Explanations

    words related to political and social issues

    oai_token-act-pair · gpt-3.5-turbo

    discussions about real issues or problems in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uly
    -0.79
    rily
    -0.79
    uled
    -0.75
     Carbuncle
    -0.73
    region
    -0.70
    ately
    -0.65
    aciously
    -0.65
    ega
    -0.65
    viously
    -0.64
    reau
    -0.60
    POSITIVE LOGITS
    DonaldTrump
    0.72
    UID
    0.68
    ICAN
    0.68
    wives
    0.67
    behind
    0.66
    ãĤ·ãĥ£
    0.64
    ument
    0.63
     reckoning
    0.63
    acea
    0.62
    ãĤ¬
    0.62
    Act Density 0.248%

    No Known Activations