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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Celt
    -0.79
    Discuss
    -0.67
     demonstr
    -0.67
     overt
    -0.64
     unab
    -0.64
     Ruff
    -0.61
     unve
    -0.60
    isy
    -0.60
     authenticated
    -0.59
     subordinate
    -0.59
    POSITIVE LOGITS
    erity
    0.84
    aund
    0.82
    iod
    0.76
    amination
    0.73
    ulation
    0.70
    ohyd
    0.70
    rats
    0.70
    rification
    0.69
     Helpful
    0.69
    oult
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.