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

    Neuronpedia

    INDEX
    Explanations

    key phrases that denote conditions or qualifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istar
    -0.16
     Vest
    -0.15
    alus
    -0.14
    redentials
    -0.14
    bury
    -0.14
    ayar
    -0.14
     Lange
    -0.14
    å¼ĺ
    -0.14
    erce
    -0.13
    oner
    -0.13
    POSITIVE LOGITS
    /Dk
    0.16
    .generated
    0.16
    DMIN
    0.14
    lue
    0.14
    okia
    0.14
    urga
    0.14
    pon
    0.14
    elper
    0.13
    iosa
    0.13
    inning
    0.13
    Act Density 0.015%

    No Known Activations