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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ascript
    -0.88
    upt
    -0.80
     pledges
    -0.68
    itaire
    -0.68
    atana
    -0.66
    phrine
    -0.66
     reorgan
    -0.66
     withdrawing
    -0.65
     confisc
    -0.64
     manifesto
    -0.63
    POSITIVE LOGITS
     Gow
    0.76
     Corpus
    0.76
     SPORTS
    0.75
     Crow
    0.75
     Soccer
    0.74
     Astros
    0.71
     Tur
    0.71
     Runs
    0.71
     Annotations
    0.70
    ENCY
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.