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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     LS
    -0.72
     reservation
    -0.70
     Mechdragon
    -0.69
     Hilton
    -0.69
    STD
    -0.68
     borrowed
    -0.68
    Sensor
    -0.67
     convertible
    -0.66
     accent
    -0.63
     Jaguar
    -0.62
    POSITIVE LOGITS
    oly
    0.86
    ynes
    0.78
    acteria
    0.70
    ospels
    0.70
    itability
    0.70
    oves
    0.69
    untary
    0.68
    maxwell
    0.67
    lyak
    0.66
    augh
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.