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

    Neuronpedia

    INDEX
    Explanations

    the presence of distinct endings in structured text, such as punctuation marks or specific file extensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ksen
    -0.17
    xeb
    -0.16
    udad
    -0.15
    iset
    -0.15
    ABCDEFGHIJKLMNOP
    -0.15
    ANJI
    -0.15
    iger
    -0.14
    oir
    -0.14
    oca
    -0.14
    gba
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.18
    roupe
    0.15
     æ¹
    0.15
    TouchEvent
    0.15
    éĺª
    0.14
    /Internal
    0.14
    _None
    0.14
    None
    0.13
    gid
    0.13
    _ELEM
    0.13
    Act Density 0.031%

    No Known Activations