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

    Neuronpedia

    INDEX
    Explanations

    technical computer-related terms and descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     NCT
    -0.56
     Colomb
    -0.56
    Footnote
    -0.52
    Nut
    -0.51
     Canaver
    -0.51
     .)
    -0.50
     Dane
    -0.50
    .")
    -0.49
     Continent
    -0.49
    qqa
    -0.48
    POSITIVE LOGITS
     Allows
    0.66
    ';
    0.65
     optionally
    0.58
     varies
    0.58
    isable
    0.56
     TBA
    0.56
    optional
    0.56
     etc
    0.55
     preferably
    0.54
     (+
    0.54
    Act Density 0.855%

    No Known Activations