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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    avorite
    -0.96
    metadata
    -0.78
    eatures
    -0.77
    ategories
    -0.75
     depths
    -0.75
    ciating
    -0.72
    illation
    -0.68
    pleting
    -0.67
    anwhile
    -0.67
    pite
    -0.67
    POSITIVE LOGITS
    enhagen
    0.68
    ¦
    0.66
    fecture
    0.65
     Bender
    0.64
     Sphere
    0.64
     Op
    0.64
    parents
    0.64
     Canaan
    0.62
    ¯
    0.62
     ----------------------------------------------------------------
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.