INDEX
    Explanations

    This neuron detects mentions of Olympic seasons—especially the word “Summer” (as in “Summer Olympics”).

    New Auto-Interp
    Negative Logits
     Nova
    -0.07
     Cad
    -0.06
     standards
    -0.06
    λος
    -0.06
    (key
    -0.06
    θήκη
    -0.06
     External
    -0.06
     El
    -0.06
    El
    -0.06
    -0.06
    POSITIVE LOGITS
    	session
    0.08
     InputStream
    0.06
     Challenger
    0.06
    PageIndex
    0.06
     Bever
    0.06
     причины
    0.06
     작성
    0.06
    –
    0.06
    ็อต
    0.06
     बन
    0.06
    Act Density 0.001%

    No Known Activations