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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    re
    1.22
    н
    1.17
    و
    1.14
    р
    1.14
    ו
    1.00
    ter
    0.96
    πό
    0.96
    в
    0.93
    st
    0.92
    inata
    0.88
    POSITIVE LOGITS
     spiced
    1.71
     facts
    1.70
     contradictions
    1.60
     layoffs
    1.59
     confounding
    1.58
     chocolate
    1.55
     verdicts
    1.54
     abnormalities
    1.54
     EFFECTS
    1.53
     precautions
    1.52
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.