INDEX
    Explanations

    tattoos and piercings

    The neuron is chiefly detecting mentions of body jewelry and piercings.

    New Auto-Interp
    Negative Logits
    uzzy
    -0.07
    -0.06
    .ticket
    -0.06
     setStatus
    -0.06
    сию
    -0.06
    urf
    -0.06
     jurisdictions
    -0.06
    ayload
    -0.06
    Monday
    -0.06
    ieme
    -0.06
    POSITIVE LOGITS
    .Security
    0.07
     sweets
    0.07
    ↵↵↵↵↵↵
    0.07
    ।↵↵
    0.07
    —or
    0.06
    ーパ
    0.06
     harmon
    0.06
    )↵↵↵↵↵↵
    0.06
    VisualStyle
    0.06
    .linkedin
    0.06
    Act Density 0.004%

    No Known Activations