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

    Neuronpedia

    INDEX
    Explanations

    the beginning of various paragraphs or sections in the text (denoted by the <bos> token)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.94
    IVEREF
    -0.80
     Monfieur
    -0.77
     Theſe
    -0.74
     myſelf
    -0.73
    GEBURTSDATUM
    -0.72
     springfox
    -0.71
     Efq
    -0.71
    brities
    -0.71
     &___
    -0.70
    POSITIVE LOGITS
    \{\\
    0.57
    translation
    0.56
     also
    0.46
     PhpStorm
    0.46
     séjours
    0.45
     jednocześnie
    0.45
     rest
    0.45
    pañol
    0.44
     पू
    0.43
     involved
    0.43
    Act Density 0.006%

    No Known Activations