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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or decorative symbols used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rompt
    -0.17
    Æ°á»Ľng
    -0.15
    wart
    -0.15
    åıĤ
    -0.15
    cken
    -0.15
     Shame
    -0.14
    coder
    -0.14
    ittings
    -0.14
    .mousePosition
    -0.14
    icorn
    -0.14
    POSITIVE LOGITS
    ires
    0.16
     Trailer
    0.15
     rug
    0.15
     enough
    0.15
     Hor
    0.15
    399
    0.14
     Working
    0.14
    inar
    0.14
     nar
    0.14
     trailer
    0.14
    Act Density 0.006%

    No Known Activations