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

    Neuronpedia

    INDEX
    Explanations

    structured data and programming-related elements in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypsum
    -0.15
    dent
    -0.15
    olet
    -0.15
    _FAR
    -0.14
    uning
    -0.14
    errick
    -0.14
    edii
    -0.14
     tém
    -0.14
     å¯
    -0.14
    ä¿
    -0.14
    POSITIVE LOGITS
     appropriate
    0.26
    ichever
    0.25
     whichever
    0.24
     chosen
    0.23
     selected
    0.23
     corresponding
    0.22
    appropriate
    0.20
     depending
    0.20
     particular
    0.20
     according
    0.20
    Act Density 0.227%

    No Known Activations