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

    Neuronpedia

    INDEX
    Explanations

    references to figures and tables in academic documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     NSM
    -0.79
     artesanales
    -0.66
     Kader
    -0.64
     vulcan
    -0.59
     itſelf
    -0.58
    ywna
    -0.56
     Ketten
    -0.56
     Préférences
    -0.56
     længere
    -0.56
     Huns
    -0.55
    POSITIVE LOGITS
     fig
    1.30
    fig
    1.26
     Fig
    1.17
     figs
    1.16
    Fig
    1.11
     Figue
    1.10
     FIGURES
    1.09
     FIG
    1.05
     Figs
    1.05
    figs
    1.04
    Act Density 0.563%

    No Known Activations