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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "Who" or "Who's" that are asking for information about people or actions

    oai_token-act-pair · gpt-3.5-turbo

    questions starting with "who" or statements posing inquiries about identity or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vity
    -0.83
    aneous
    -0.81
    ooters
    -0.80
    naissance
    -0.72
     moot
    -0.71
    poons
    -0.70
    umsy
    -0.69
    utterstock
    -0.68
    lance
    -0.66
    arity
    -0.66
    POSITIVE LOGITS
     Pearce
    0.72
    ?),
    0.71
     Cameroon
    0.67
     hect
    0.65
    ç¥ŀ
    0.62
     anat
    0.61
     hapl
    0.61
    ?)
    0.60
     Boko
    0.60
    doms
    0.59
    Act Density 0.165%

    No Known Activations