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

    Neuronpedia

    INDEX
    Explanations

    numeric values in a specific format - "25 X" where X is a non-zero value

    oai_token-act-pair · gpt-3.5-turbo

    the number '25' and its variations in the context provided

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ophon
    -0.79
    sein
    -0.70
    ĸļ
    -0.69
    paio
    -0.69
    yle
    -0.68
    rium
    -0.66
    chio
    -0.65
    phis
    -0.64
    plin
    -0.63
    atis
    -0.63
    POSITIVE LOGITS
    th
    0.99
    00
    0.98
    60
    0.94
    isher
    0.93
    50
    0.92
    %-
    0.91
    %
    0.91
    ishers
    0.90
    %:
    0.88
    ishing
    0.88
    Act Density 0.064%

    No Known Activations