INDEX
    Explanations

    The neuron detects sentence‐initial temporal or discourse transition words (e.g. “Following,” “After,” “Based on,” etc.).

    New Auto-Interp
    Negative Logits
     flour
    -0.07
     Fur
    -0.07
     Fel
    -0.07
     defends
    -0.06
    borrow
    -0.06
     Müller
    -0.06
    endir
    -0.06
     defended
    -0.06
    chrom
    -0.06
    apur
    -0.06
    POSITIVE LOGITS
    .axis
    0.07
    /console
    0.06
    0.06
    (){
    ↵
    0.06
    _checks
    0.06
     Predator
    0.06
    IEWS
    0.05
     Complete
    0.05
    стров
    0.05
     ราย
    0.05
    Act Density 0.061%

    No Known Activations