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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĪÑĮ
    -0.15
    951
    -0.14
     Sure
    -0.14
    ero
    -0.14
    vil
    -0.14
    of
    -0.14
    units
    -0.13
    ogenic
    -0.13
    окон
    -0.13
    ools
    -0.13
    POSITIVE LOGITS
    Ñħо
    0.17
    /Gate
    0.16
    enant
    0.15
    моÑĢ
    0.14
    ENCED
    0.14
    hangi
    0.14
    ़र
    0.14
    é¢ij次
    0.14
    âĢŀV
    0.14
    habit
    0.14
    Act Density 0.072%

    No Known Activations