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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     scrut
    -0.67
     Trend
    -0.65
     VICE
    -0.65
     province
    -0.64
     provinces
    -0.63
     YEAR
    -0.63
     ministry
    -0.63
     glim
    -0.62
     inund
    -0.59
     brim
    -0.57
    POSITIVE LOGITS
    rap
    0.74
    onian
    0.73
    ocene
    0.71
    hai
    0.70
    ARS
    0.69
    ¯
    0.69
    stic
    0.69
    papers
    0.68
    hots
    0.68
    kins
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.