INDEX
    Explanations

    instances of the word "neither" followed by a contrast or comparison

    instances of the word "neither" in various contexts

    New Auto-Interp
    Negative Logits
    uctions
    -0.75
    ournals
    -0.74
    enges
    -0.70
    roxy
    -0.67
    uers
    -0.66
    enos
    -0.66
    psc
    -0.65
    è¯
    -0.65
    Bang
    -0.64
    ÙĴ
    -0.64
    POSITIVE LOGITS
     sexes
    0.74
    theless
    0.70
     overtly
    0.70
    zee
    0.68
    ndra
    0.66
    llor
    0.64
     side
    0.64
    !--
    0.64
    soever
    0.63
    lect
    0.63
    Act Density 0.012%

    No Known Activations