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

    Neuronpedia

    INDEX
    Explanations

    references to positions of authority or organizational roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eskort
    -0.15
    INCLUDED
    -0.14
    ë¦
    -0.14
    å¹³æĪIJ
    -0.14
    andum
    -0.14
    erb
    -0.14
    ikler
    -0.14
    æ¦ľ
    -0.14
    ätz
    -0.14
    rowsable
    -0.14
    POSITIVE LOGITS
     at
    0.19
     chez
    0.18
     for
    0.18
     of
    0.17
     Parcel
    0.16
    aw
    0.16
     unto
    0.15
     carte
    0.15
    sko
    0.14
     and
    0.14
    Act Density 0.071%

    No Known Activations