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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dumps
    -0.66
    NG
    -0.64
    misc
    -0.63
    saf
    -0.62
    erest
    -0.62
     Vent
    -0.60
    ugh
    -0.60
    nown
    -0.60
    ventions
    -0.59
     preparations
    -0.58
    POSITIVE LOGITS
    olkien
    0.78
    isphere
    0.73
     Ribbon
    0.66
     Canaver
    0.65
     occas
    0.64
    oleon
    0.64
    atis
    0.64
     fragmentation
    0.63
     Fenrir
    0.63
     Confederation
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.