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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dependency or lack, particularly the word "without"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ware
    -0.14
    yst
    -0.14
    egan
    -0.13
    æľ¬
    -0.13
     Kraj
    -0.13
     broken
    -0.13
    WARE
    -0.13
    leine
    -0.13
     Emer
    -0.13
     Hed
    -0.13
    POSITIVE LOGITS
    afa
    0.18
    olls
    0.16
    myp
    0.15
    ozilla
    0.14
    croll
    0.14
    ollah
    0.14
    mando
    0.14
    ync
    0.14
    oug
    0.14
    ijd
    0.14
    Act Density 0.020%

    No Known Activations