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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Accessory
    -0.77
     Guang
    -0.70
    Lex
    -0.70
    framework
    -0.69
     Grac
    -0.68
    Mel
    -0.68
     Kimberly
    -0.67
    Chel
    -0.66
    ucl
    -0.65
     Cheryl
    -0.65
    POSITIVE LOGITS
    assing
    0.78
    ivism
    0.72
    urd
    0.72
    illion
    0.71
     MPG
    0.70
    agnar
    0.69
    ÃįÃį
    0.68
    olf
    0.67
    ival
    0.66
     Obj
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.