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

    Neuronpedia

    INDEX
    Explanations

    keywords related to different nationalities, religions, and ethnicities

    oai_token-act-pair · gpt-3.5-turbo

    references to various ethnicities, religions, and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    initions
    -0.81
    Sym
    -0.63
    gency
    -0.63
    tions
    -0.62
    prise
    -0.62
    lag
    -0.62
    LEASE
    -0.61
    plementation
    -0.61
     Wast
    -0.60
    teness
    -0.60
    POSITIVE LOGITS
    ophobic
    0.83
     anyway
    0.74
    wired
    0.73
     enough
    0.73
    hovah
    0.73
     anymore
    0.71
    listed
    0.70
    aware
    0.68
    isexual
    0.68
     Enough
    0.67
    Act Density 0.211%

    No Known Activations