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

    Neuronpedia

    INDEX
    Explanations

    references to actions or processes related to influence and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.16
    anova
    -0.16
    alytics
    -0.16
     Lump
    -0.15
    infeld
    -0.15
    vek
    -0.14
    wins
    -0.14
    agate
    -0.14
    grams
    -0.14
    ãĥĥãĤ·ãĥ¥
    -0.14
    POSITIVE LOGITS
    /from
    0.17
    unes
    0.15
    orsk
    0.15
     Orc
    0.15
    sert
    0.15
     diret
    0.14
    /on
    0.14
    á»ı
    0.14
    orang
    0.14
    orer
    0.13
    Act Density 0.097%

    No Known Activations