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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.85
     GD
    -0.73
    uberty
    -0.69
     digit
    -0.69
    udic
    -0.68
    rounder
    -0.66
     PowerPoint
    -0.65
    ]}
    -0.65
     corpus
    -0.64
     spoiler
    -0.64
    POSITIVE LOGITS
    é¾įåĸļ士
    0.75
     Apprentice
    0.73
    éļ
    0.71
    Heart
    0.70
    birth
    0.69
    ships
    0.68
    ¯¯
    0.68
    ãĥ
    0.67
    çİĭ
    0.67
    maid
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.