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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and references to equations in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ElementsBy
    -0.15
     Elite
    -0.14
    ErrorCode
    -0.14
    queda
    -0.13
    Elite
    -0.13
    ãĥĥãĤ·ãĥ¥
    -0.13
    _Entity
    -0.13
    EndElement
    -0.13
    .datab
    -0.12
    eval
    -0.12
    POSITIVE LOGITS
     e
    1.41
    *e
    0.89
    =e
    0.89
    	e
    0.87
    )e
    0.85
    .e
    0.84
    (e
    0.84
    >e
    0.82
    -e
    0.81
    :e
    0.79
    Act Density 0.533%

    No Known Activations