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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols, potentially indicating encoding issues or unusual text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acters
    -0.86
    chn
    -0.84
    isher
    -0.81
    cker
    -0.79
    essing
    -0.77
    ker
    -0.76
    istically
    -0.76
    istics
    -0.75
    ket
    -0.74
    ister
    -0.74
    POSITIVE LOGITS
    è¦
    0.79
    sburg
    0.73
    使
    0.65
     Polo
    0.65
    MJ
    0.63
    estic
    0.63
    ãĤ§
    0.62
    rising
    0.62
    fal
    0.61
    Truth
    0.61
    Act Density 0.062%

    No Known Activations