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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Prov
    -0.88
    =~
    -0.80
     Mechdragon
    -0.76
     Strikes
    -0.75
    enegger
    -0.65
    IELD
    -0.65
     Kinder
    -0.65
     Doctrine
    -0.63
     Elections
    -0.63
     Lauder
    -0.63
    POSITIVE LOGITS
    tub
    0.85
     guys
    0.82
    kai
    0.81
    're
    0.78
     yourself
    0.73
    quartered
    0.69
    lex
    0.68
    brance
    0.67
    erker
    0.67
     yourselves
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.