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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of people along with their racial or occupational affiliations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the identity or status of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guys
    -0.77
    ivable
    -0.70
    rehensive
    -0.69
    #$#$
    -0.68
    ctive
    -0.67
    snap
    -0.65
    reat
    -0.64
    oire
    -0.64
    ository
    -0.64
     Solution
    -0.63
    POSITIVE LOGITS
     besie
    0.90
     visiting
    0.89
     presiding
    0.89
     awaiting
    0.89
     respectively
    0.88
     stationed
    0.88
     recovering
    0.88
     overseeing
    0.88
     undergoing
    0.86
     battling
    0.85
    Act Density 0.150%

    No Known Activations