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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĶĭ
    -0.18
    fty
    -0.16
    eba
    -0.16
    favor
    -0.15
    ç«ľ
    -0.14
    fffffff
    -0.14
    emy
    -0.14
    atak
    -0.14
    _nested
    -0.14
    Å¡ku
    -0.14
    POSITIVE LOGITS
     like
    0.15
    èī
    0.15
    akis
    0.14
    ë°°
    0.14
    urette
    0.14
    á»ĵn
    0.14
    ,:
    0.13
    không
    0.13
    icons
    0.13
    ÏīÏĤ
    0.13
    Act Density 0.199%

    No Known Activations