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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ô
    -0.85
     Gleaming
    -0.78
    ]=
    -0.70
    ¯¯¯¯
    -0.66
     dime
    -0.63
     sand
    -0.63
    ][/
    -0.62
    ¥µ
    -0.62
     rainy
    -0.61
     neutral
    -0.61
    POSITIVE LOGITS
    frey
    0.75
    ulia
    0.73
     Granger
    0.72
    pring
    0.70
    mble
    0.68
    nyder
    0.68
    itability
    0.66
    dad
    0.66
    erity
    0.63
    blance
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.