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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĪ
    -0.82
     Genocide
    -0.73
     filib
    -0.70
    icas
    -0.68
     Rape
    -0.67
     Cong
    -0.66
    ilib
    -0.66
    âķ
    -0.65
    éĥ
    -0.65
     rapists
    -0.65
    POSITIVE LOGITS
     tremend
    0.74
     consolidation
    0.68
    focus
    0.67
    advertisement
    0.66
    picture
    0.64
    forth
    0.62
    ilion
    0.61
    complex
    0.61
    grain
    0.60
    warts
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.