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

    Neuronpedia

    INDEX
    Explanations

    the symbol "<end>" that signifies the end of a text segment

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive matchups or contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phia
    -0.66
     NETWORK
    -0.63
     Byzantine
    -0.61
    uct
    -0.61
    åº
    -0.61
    AAF
    -0.61
    Ö¼
    -0.61
     Ort
    -0.59
    oÄŁ
    -0.59
    é¾
    -0.59
    POSITIVE LOGITS
    ratulations
    0.66
    ache
    0.61
     Winston
    0.61
    quartered
    0.61
     shoulders
    0.60
    quarters
    0.60
    forth
    0.60
    ikuman
    0.58
    gow
    0.58
    ourage
    0.57
    Act Density 0.101%

    No Known Activations