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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.81
     Diversity
    -0.76
     ********************************
    -0.71
     Donation
    -0.69
     Equality
    -0.68
     TI
    -0.67
     Equal
    -0.67
     Discrimination
    -0.66
     Mehran
    -0.66
    SourceFile
    -0.66
    POSITIVE LOGITS
    Jer
    0.74
    ön
    0.74
    acher
    0.65
    uania
    0.65
     drilled
    0.64
    Blocks
    0.63
     glued
    0.63
     ballistic
    0.62
    jer
    0.61
    cius
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.