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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.79
    acter
    -0.72
    >>>>>>>>
    -0.67
    eling
    -0.67
    Ģ
    -0.65
    Gene
    -0.65
     Doodle
    -0.65
     Cruise
    -0.63
    rats
    -0.62
    Doc
    -0.61
    POSITIVE LOGITS
    utterstock
    0.87
    ioned
    0.77
     behold
    0.71
    uate
    0.66
    uates
    0.66
    ocks
    0.65
    erva
    0.65
    uncture
    0.64
    abal
    0.64
    mates
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.