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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     diseng
    -0.73
     Twe
    -0.67
     commons
    -0.65
     Administration
    -0.65
     enthus
    -0.64
     cool
    -0.64
     Associ
    -0.63
    vironment
    -0.61
     wills
    -0.60
     balances
    -0.60
    POSITIVE LOGITS
    ata
    1.01
    ©¶æ¥µ
    0.88
    once
    0.84
    rites
    0.84
    ascal
    0.79
    ĸļ
    0.79
    eon
    0.78
    roma
    0.75
    cod
    0.75
    ranked
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.