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

    Neuronpedia

    INDEX
    Explanations

    dates in a month-year format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics presented in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enzie
    -0.84
     Beir
    -0.82
    ropolis
    -0.79
    yle
    -0.78
    orney
    -0.77
    aleb
    -0.76
    alist
    -0.74
    illation
    -0.74
    ype
    -0.74
    ellation
    -0.73
    POSITIVE LOGITS
    th
    0.97
    00
    0.92
    650
    0.82
    士
    0.74
    teen
    0.72
    nd
    0.72
     livest
    0.71
    50
    0.71
    017
    0.71
    66
    0.71
    Act Density 0.037%

    No Known Activations