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

    Neuronpedia

    INDEX
    Explanations

    elements related to scoring and game outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acier
    -0.16
    luet
    -0.16
    uguay
    -0.15
    DataTask
    -0.15
    idor
    -0.15
    892
    -0.15
    unu
    -0.15
    дел
    -0.15
    olini
    -0.14
    ermen
    -0.14
    POSITIVE LOGITS
    ennes
    0.15
    豪
    0.14
    ÙĨاÙĨ
    0.14
     Nap
    0.14
     Creature
    0.14
    NaN
    0.14
     settle
    0.14
    gii
    0.13
     TED
    0.13
     Fork
    0.13
    Act Density 0.460%

    No Known Activations