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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     traitors
    -0.79
     perverted
    -0.78
     despotism
    -0.75
     venge
    -0.74
     scound
    -0.73
     tyrannical
    -0.73
     barbaric
    -0.72
     ruinous
    -0.72
     despicable
    -0.72
     pervert
    -0.71
    POSITIVE LOGITS
    <bos>
    7.66
    LookAnd
    1.36
     dispen
    1.30
     fign
    1.27
     effe
    1.26
     ftu
    1.26
    GEBURTSDATUM
    1.26
    expandindo
    1.25
     fta
    1.22
     fup
    1.22
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.