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

    Neuronpedia

    INDEX
    Explanations

    references to common expressions or phrases indicating improvement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arty
    -0.18
    urtle
    -0.16
    APT
    -0.15
     Bair
    -0.15
    ovich
    -0.14
    /apt
    -0.14
    URT
    -0.14
    urat
    -0.14
    Âłmiles
    -0.13
    ure
    -0.13
    POSITIVE LOGITS
    endance
    0.15
    eros
    0.15
    uze
    0.15
    HEST
    0.14
     Yön
    0.14
    anship
    0.14
    Ñĸон
    0.13
    pel
    0.13
    eras
    0.13
    otland
    0.13
    Act Density 0.364%

    No Known Activations