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

    Neuronpedia

    INDEX
    Explanations

    dates or specific numbers mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific suffixes or word endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    footed
    -0.78
    ierrez
    -0.69
     CPR
    -0.65
    minecraft
    -0.64
    repre
    -0.62
     DOI
    -0.62
    avorite
    -0.61
     Folder
    -0.59
    udeb
    -0.59
     lawy
    -0.59
    POSITIVE LOGITS
    roth
    0.99
    RAL
    0.79
    ral
    0.78
    士
    0.69
    opol
    0.67
    enne
    0.67
    »Ĵ
    0.66
    Ĥİ
    0.64
    bor
    0.63
    DragonMagazine
    0.63
    Act Density 0.114%

    No Known Activations