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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     literature
    -0.69
    éĩ
    -0.69
    phies
    -0.68
    Ü
    -0.68
    iol
    -0.66
     scholarships
    -0.66
    eds
    -0.64
    çļ
    -0.64
     poems
    -0.63
    ãģ®å®
    -0.63
    POSITIVE LOGITS
    hess
    0.83
    hift
    0.71
    iculty
    0.67
     Scouting
    0.63
     Observer
    0.63
    assing
    0.62
    inous
    0.60
     Stain
    0.59
     plotting
    0.59
    atten
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.