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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal actions and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyer
    -0.15
    eye
    -0.15
    .Decode
    -0.14
    iani
    -0.14
    è¥
    -0.14
    ayer
    -0.14
    loe
    -0.14
    ount
    -0.14
    cents
    -0.13
    ä¾
    -0.13
    POSITIVE LOGITS
     Kapoor
    0.18
    иÑģлов
    0.17
    iang
    0.16
    artisan
    0.15
    ulary
    0.14
    _deinit
    0.14
     muschi
    0.14
    ä¼
    0.14
    lisi
    0.14
    adan
    0.14
    Act Density 0.183%

    No Known Activations