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

    Neuronpedia

    INDEX
    Explanations

    terms related to transactions or financial data

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of empty or placeholder text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pione
    -1.22
    ò
    -1.17
     exting
    -1.16
     eleph
    -1.12
    aditional
    -1.11
    Þ
    -1.07
    ñ
    -1.06
    Ĝ
    -1.04
     practition
    -1.04
    ö
    -1.04
    POSITIVE LOGITS
    .
    1.15
    .,
    0.95
    .?
    0.95
    .-
    0.91
    .—
    0.88
    ./
    0.88
    .:
    0.87
    ._
    0.86
    .–
    0.86
    .(
    0.85
    Act Density 0.165%

    No Known Activations