INDEX
    Explanations

    This neuron detects mentions of the "offseason" (including forms like "off-season").

    New Auto-Interp
    Negative Logits
     togg
    -0.06
     encourages
    -0.06
     reliable
    -0.06
    ोच
    -0.06
     Corbyn
    -0.06
     además
    -0.06
     furthermore
    -0.06
    .push
    -0.06
     عاشق
    -0.06
    ("./
    -0.06
    POSITIVE LOGITS
     offseason
    0.11
     postseason
    0.07
     sacked
    0.07
    0.07
     aftermarket
    0.07
    -connect
    0.06
    TypeId
    0.06
    hover
    0.06
    life
    0.06
    months
    0.06
    Act Density 0.006%

    No Known Activations