INDEX
    Explanations

    visual effects/rendering

    The neuron fires on mentions of visual “effects” (e.g. tokens like “effect” and names of specific effects such as “blood,” “neon,” “film,” “scan lines,” etc.).

    New Auto-Interp
    Negative Logits
    :last
    -0.07
    バイ
    -0.07
    Tooltip
    -0.06
    	cc
    -0.06
    _MY
    -0.06
    ینه
    -0.06
     TODAY
    -0.06
    Milliseconds
    -0.06
     wastes
    -0.06
    MBED
    -0.06
    POSITIVE LOGITS
     humble
    0.06
    schema
    0.06
    deaux
    0.06
     veil
    0.06
     Clemson
    0.06
     decorate
    0.06
    _KeyPress
    0.06
     Responsible
    0.06
     پر
    0.06
     cục
    0.06
    Act Density 0.040%

    No Known Activations