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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numerical data within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     totiž
    -0.18
    amos
    -0.15
    amo
    -0.15
    vik
    -0.14
    raphics
    -0.13
     therefore
    -0.13
     ÙĩÙħÛĮÙĨ
    -0.13
    ').'
    -0.13
    ajo
    -0.13
    elden
    -0.12
    POSITIVE LOGITS
     besides
    0.19
    Regarding
    0.18
     Additionally
    0.17
     among
    0.17
     Regarding
    0.17
    DITION
    0.17
     regarding
    0.16
     other
    0.16
     additionally
    0.16
    ãģĿãģ®ä»ĸ
    0.16
    Act Density 0.274%

    No Known Activations