INDEX
    Explanations

    instances of structured scientific or medical discourse

    New Auto-Interp
    Negative Logits
     становника
    -0.69
    WarningLevel
    -0.68
     onAnimation
    -0.67
    -0.66
    mybatisplus
    -0.65
    inflater
    -0.65
     kasarigan
    -0.64
     propOrder
    -0.64
    DotNetBar
    -0.64
    Amicalement
    -0.61
    POSITIVE LOGITS
    0.78
    ↵↵
    0.78
    ↵↵↵
    0.63
    ↵↵↵↵↵↵
    0.61
    ↵↵↵↵
    0.59
    <eos>
    0.56
    filepath
    0.56
    ↵↵↵↵↵↵↵
    0.54
    ↵↵↵↵↵
    0.53
    	
    0.51
    Act Density 0.061%

    No Known Activations