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

    Neuronpedia

    INDEX
    Explanations

    statements that negate or reject ideas or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _WS
    -0.17
     ÑĤÑĢо
    -0.15
    xia
    -0.14
    еÑĢеж
    -0.14
    erox
    -0.14
     Blizzard
    -0.14
    ลล
    -0.14
    csr
    -0.14
     AppleWebKit
    -0.14
    cken
    -0.14
    POSITIVE LOGITS
     usual
    0.17
     merely
    0.15
    ippi
    0.15
     directly
    0.14
    пов
    0.14
     turn
    0.14
    orra
    0.14
     obvious
    0.14
    gan
    0.14
    ollow
    0.14
    Act Density 0.054%

    No Known Activations