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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to decision-making and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulla
    -0.16
    AF
    -0.15
    ML
    -0.15
    976
    -0.14
    ilha
    -0.14
     Du
    -0.14
    exit
    -0.14
     Tor
    -0.14
    InSection
    -0.13
     tor
    -0.13
    POSITIVE LOGITS
    kara
    0.14
     hết
    0.14
     Mitar
    0.14
    ستر
    0.14
    oler
    0.14
     ontvangst
    0.13
    _sparse
    0.13
    cel
    0.13
    hift
    0.13
    utz
    0.13
    Act Density 0.002%

    No Known Activations