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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    perse
    -0.87
    rika
    -0.76
    rition
    -0.75
    otle
    -0.74
    Constructed
    -0.71
    chell
    -0.70
     Paste
    -0.69
    iaries
    -0.69
    atus
    -0.69
    acity
    -0.69
    POSITIVE LOGITS
     embargo
    0.79
     dominated
    0.78
     starved
    0.76
     deceived
    0.76
     deprived
    0.76
    ļéĨĴ
    0.74
     desp
    0.74
     subord
    0.72
     perce
    0.71
     offended
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.