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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values preceded by a space and followed by a digit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 25

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phis
    -0.80
    paio
    -0.79
    ophon
    -0.76
    yle
    -0.74
    sein
    -0.74
    orsi
    -0.74
    rium
    -0.73
    avascript
    -0.73
    atis
    -0.73
    chio
    -0.71
    POSITIVE LOGITS
    ishers
    0.86
    isher
    0.86
    ISH
    0.85
    ishing
    0.85
    th
    0.83
    %:
    0.79
    00
    0.79
    50
    0.77
    60
    0.76
    ishable
    0.75
    Act Density 0.026%

    No Known Activations