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

    Neuronpedia

    INDEX
    Explanations

    specific references to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to male and female individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.66
     Remastered
    -0.60
    Such
    -0.59
     VIDEOS
    -0.58
    \\\\\\\\
    -0.56
    cross
    -0.55
    elaide
    -0.54
     thickness
    -0.54
    theless
    -0.54
    dress
    -0.54
    POSITIVE LOGITS
     responsible
    1.32
     behind
    1.25
     overseeing
    1.14
     tasked
    1.09
    responsible
    1.07
     who
    1.06
     administering
    1.05
    liest
    1.01
     closest
    1.00
     sponsoring
    1.00
    Act Density 0.262%

    No Known Activations