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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     counters
    -0.69
     rapists
    -0.66
     lesbians
    -0.64
     ought
    -0.63
     incarcer
    -0.61
    Sexual
    -0.60
     sixty
    -0.59
    asketball
    -0.58
    icts
    -0.58
    accompanied
    -0.58
    POSITIVE LOGITS
    oglu
    0.94
    ariat
    0.78
    uve
    0.77
    pora
    0.73
    outube
    0.72
    aer
    0.71
    oros
    0.69
    oire
    0.68
    ĵĺ
    0.67
     Verge
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.