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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     transports
    -0.68
    icion
    -0.68
    aily
    -0.67
    iston
    -0.66
     Dayton
    -0.65
     landfill
    -0.63
    ibrary
    -0.62
    ipedia
    -0.61
     cloning
    -0.61
     privatization
    -0.60
    POSITIVE LOGITS
    'm
    0.95
     suppose
    0.90
    displayText
    0.88
    UD
    0.86
    JB
    0.84
    zzo
    0.84
    've
    0.83
    KE
    0.80
    'll
    0.79
     rejoice
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.