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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to dates or statistics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number 25

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ophon
    -0.84
    paio
    -0.82
    phis
    -0.78
    ei
    -0.77
    rium
    -0.76
    sein
    -0.76
    yle
    -0.73
    ramid
    -0.71
    chwitz
    -0.71
    atis
    -0.71
    POSITIVE LOGITS
     ILCS
    0.89
    00
    0.85
    ISH
    0.84
    th
    0.82
    isher
    0.82
    %:
    0.82
    50
    0.80
    60
    0.79
    ishers
    0.78
    %-
    0.78
    Act Density 0.025%

    No Known Activations