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

    Neuronpedia

    INDEX
    Explanations

    elements related to social behavior and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udi
    -0.15
    emplate
    -0.14
    аков
    -0.14
    shal
    -0.14
    avit
    -0.13
    istrovstvÃŃ
    -0.13
    lay
    -0.13
    ocht
    -0.13
    oren
    -0.13
     YES
    -0.13
    POSITIVE LOGITS
    eyen
    0.15
    DITION
    0.15
    udur
    0.15
    iyon
    0.14
    abouts
    0.14
    rál
    0.13
    sdale
    0.13
    оби
    0.13
    iny
    0.13
    DonaldTrump
    0.13
    Act Density 0.360%

    No Known Activations