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

    Neuronpedia

    INDEX
    Explanations

    phrases related to long-term factors or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.16
    ìĦľëĬĶ
    -0.16
    /es
    -0.15
     bats
    -0.15
    (es
    -0.15
     createState
    -0.15
    à¥ĭश
    -0.15
    bat
    -0.14
    avin
    -0.14
    ako
    -0.14
    POSITIVE LOGITS
    ainers
    0.16
    ueur
    0.16
    onaut
    0.15
    ARRANT
    0.15
    645
    0.15
     Gund
    0.14
    анов
    0.14
    antro
    0.14
    ginas
    0.14
    çĽijåIJ¬é¡µéĿ¢
    0.14
    Act Density 0.008%

    No Known Activations