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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Zin
    -0.67
    NPR
    -0.67
     dug
    -0.66
     Omn
    -0.64
     washed
    -0.64
    levision
    -0.63
    alach
    -0.63
    olls
    -0.61
     IPM
    -0.60
    writer
    -0.60
    POSITIVE LOGITS
    ingen
    0.87
    icit
    0.70
    uble
    0.69
    agogue
    0.67
    inge
    0.67
    amphetamine
    0.66
    igure
    0.65
    mberg
    0.63
    uces
    0.63
    ibaba
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.