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

    Neuronpedia

    INDEX
    Explanations

    quotes or dialogue in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.73
    thâu
    -0.59
    IsContent
    -0.56
    WithIOException
    -0.54
     chiave
    -0.53
     MDF
    -0.52
    かわらず
    -0.52
    oa̍t
    -0.51
     disambiguazione
    -0.51
     réjou
    -0.51
    POSITIVE LOGITS
    (!__
    0.71
     pinulongan
    0.57
    UNLOCK
    0.56
    <tfoot>
    0.54
    initely
    0.54
    /******/
    0.54
    tionally
    0.52
    ditions
    0.52
    enumii
    0.51
     darker
    0.50
    Act Density 0.009%

    No Known Activations