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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence-ending marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enville
    -0.15
    ofs
    -0.14
    ikel
    -0.14
    p
    -0.14
    uma
    -0.14
    missible
    -0.14
    rlen
    -0.13
    nik
    -0.13
    ap
    -0.13
    ÙĪÛĮÙĦ
    -0.13
    POSITIVE LOGITS
    ionale
    0.14
    asher
    0.14
     unanimously
    0.13
    specialchars
    0.13
    orr
    0.13
     tack
    0.13
    istrat
    0.13
    efe
    0.13
    алом
    0.13
    lint
    0.13
    Act Density 0.018%

    No Known Activations