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

    Neuronpedia

    INDEX
    Explanations

    specific numbers related to dates or quantities

    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
    -0.80
    paio
    -0.76
    yle
    -0.73
    sein
    -0.73
    phis
    -0.70
    chio
    -0.69
    icago
    -0.69
    chwitz
    -0.66
    atis
    -0.65
    ĸļ
    -0.64
    POSITIVE LOGITS
    ishing
    0.93
    isher
    0.92
    ishers
    0.89
    th
    0.84
    00
    0.84
    ISH
    0.82
    60
    0.80
    50
    0.79
    %-
    0.78
    %:
    0.77
    Act Density 0.039%

    No Known Activations