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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in a specific crisis or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.79
    nels
    -0.71
    shire
    -0.69
    keyes
    -0.69
    prise
    -0.68
    elaide
    -0.68
    ingly
    -0.65
    ridge
    -0.64
    entity
    -0.63
    trigger
    -0.62
    POSITIVE LOGITS
     Mikhail
    1.33
     Chern
    1.31
     Lavrov
    1.29
     Dmit
    1.26
     Kov
    1.25
     Nikol
    1.24
     Bulgar
    1.21
     Ivan
    1.20
     Vlad
    1.20
     Sergey
    1.19
    Act Density 0.106%

    No Known Activations