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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and entities related to data formats or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appa
    -0.17
     underst
    -0.15
    ifact
    -0.14
     شع
    -0.14
    ķĮ
    -0.14
    usra
    -0.14
    /fl
    -0.14
    arden
    -0.14
    ãĤ¡
    -0.14
    æľį
    -0.14
    POSITIVE LOGITS
     Wax
    0.17
    shift
    0.17
    illon
    0.15
    :disable
    0.14
    ayıp
    0.14
     Injection
    0.14
    Ñģии
    0.14
    dot
    0.14
    anj
    0.13
    ùi
    0.13
    Act Density 0.086%

    No Known Activations