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

    Neuronpedia

    INDEX
    Explanations

    numerical values or codes within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty spaces or lines in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.77
    creen
    -0.74
    oulos
    -0.73
     Mellon
    -0.73
     Asheville
    -0.70
     potatoes
    -0.67
     braces
    -0.66
     Bethlehem
    -0.65
     destro
    -0.64
     Clarkson
    -0.64
    POSITIVE LOGITS
    ________________________________________________________________
    1.03
    urn
    1.01
    Ë
    0.96
    iph
    0.93
    ********
    0.92
    ~~
    0.92
    _____
    0.92
    ~~~~~~~~~~~~~~~~
    0.92
    ---------------
    0.91
    ------------
    0.91
    Act Density 0.011%

    No Known Activations