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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.79
    ixt
    -0.78
    beit
    -0.75
    toe
    -0.75
    uku
    -0.74
    riott
    -0.74
    ido
    -0.74
    pez
    -0.71
    rera
    -0.71
    white
    -0.69
    POSITIVE LOGITS
     Scientific
    0.66
     @@
    0.65
     BAS
    0.63
     Awareness
    0.62
    Values
    0.62
    CHA
    0.62
     Computing
    0.61
     Krug
    0.61
     BS
    0.61
     Science
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.