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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their relationships or references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -1.05
    HasForeignKey
    -0.95
     Paglinawan
    -0.92
    ########.
    -0.91
     disambiguazione
    -0.89
    #+#
    -0.88
     Bullock
    -0.87
     keli
    -0.85
     Sight
    -0.84
     Koval
    -0.83
    POSITIVE LOGITS
    ethene
    0.65
    Viel
    0.64
     xóa
    0.59
     SAGE
    0.59
    Affine
    0.57
     argparse
    0.56
     Luf
    0.56
    lsen
    0.56
     Artem
    0.56
     ActionListener
    0.56
    Act Density 0.657%

    No Known Activations