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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of sentences and delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptr
    -0.18
    rost
    -0.16
    oton
    -0.16
    ussen
    -0.15
    ocker
    -0.15
    uth
    -0.14
    urge
    -0.14
    opak
    -0.14
    ê¸Ī
    -0.14
     Dale
    -0.14
    POSITIVE LOGITS
     Gow
    0.18
     konkrét
    0.16
    Å¡et
    0.15
    ayet
    0.15
    à¸Ńà¸ĩà¸Īาà¸ģ
    0.15
    ɵ
    0.14
    ez
    0.14
    елÑİ
    0.14
    ighton
    0.14
    oui
    0.14
    Act Density 0.012%

    No Known Activations