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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     showers
    -0.75
    ensitive
    -0.72
     shower
    -0.70
    creen
    -0.66
     retaliate
    -0.64
     outright
    -0.63
    uphem
    -0.63
     retali
    -0.62
     snipp
    -0.62
     IRC
    -0.61
    POSITIVE LOGITS
    ARS
    0.91
    ends
    0.74
    LR
    0.72
    END
    0.70
    EEP
    0.68
     Issues
    0.67
    Foot
    0.66
    RD
    0.66
    cv
    0.65
     Matters
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.