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

    Neuronpedia

    INDEX
    Explanations

    references to worries or apprehensions about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nore
    -0.17
    alling
    -0.15
    /cop
    -0.14
    ym
    -0.14
    refixer
    -0.14
    Æ°á»Łng
    -0.14
    ÙĨØ´
    -0.14
    ITERAL
    -0.14
    _lastname
    -0.13
    ấp
    -0.13
    POSITIVE LOGITS
    nice
    0.15
    lessly
    0.15
    OrCreate
    0.15
    leich
    0.14
    DIM
    0.14
    ami
    0.14
     ë¨
    0.14
    ãĥĥãĤ·ãĥ¥
    0.14
    atti
    0.14
     scand
    0.13
    Act Density 0.009%

    No Known Activations