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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    bracketed items or lists, likely denoting elements in a series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.85
    oe
    -0.72
    ĪĴ
    -0.71
    İĭ
    -0.64
    userc
    -0.63
    ciating
    -0.61
     cradle
    -0.59
    ±
    -0.59
    ĸļ
    -0.58
     belt
    -0.58
    POSITIVE LOGITS
    âĨij
    0.72
    TPS
    0.71
    ][
    0.70
    *.
    0.68
     Ibid
    0.67
    ].
    0.66
    report
    0.65
    âĨ
    0.63
    >.
    0.63
     Cheong
    0.63
    Act Density 0.048%

    No Known Activations