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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥij
    -0.83
     beaut
    -0.67
     Blessing
    -0.67
    Friend
    -0.64
    Duration
    -0.61
     Perse
    -0.61
     Lite
    -0.61
     angels
    -0.60
     Basil
    -0.59
     Weasley
    -0.59
    POSITIVE LOGITS
    culosis
    0.84
    irrel
    0.73
     Investigative
    0.72
    seys
    0.72
    iven
    0.71
    ipel
    0.70
    psc
    0.69
    vy
    0.68
    anwhile
    0.67
    jury
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.