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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rift
    -0.84
    maid
    -0.83
    weeney
    -0.73
    doctor
    -0.72
    Doctor
    -0.71
    rus
    -0.71
     TBA
    -0.71
    ragon
    -0.67
    ertodd
    -0.66
     Logged
    -0.65
    POSITIVE LOGITS
    ALLY
    0.76
    ²¾
    0.74
     millenn
    0.73
    FTWARE
    0.73
     apparatus
    0.72
    uchi
    0.72
     tremend
    0.72
    itzer
    0.71
     proport
    0.71
     obser
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.