INDEX
    Explanations

    also, alternatively, additionally

    New Auto-Interp
    Negative Logits
    sciutto
    0.40
    lefthar
    0.38
    adece
    0.36
     same
    0.36
    0.35
    albeit
    0.35
    δου
    0.35
    exactly
    0.35
    "+"|".
    0.34
     viewpoint
    0.34
    POSITIVE LOGITS
    ↵↵↵↵↵↵
    0.54
    ↵↵↵↵↵
    0.52
    ↵↵↵↵↵↵↵
    0.50
     Also
    0.49
     Außerdem
    0.48
    ↵↵↵↵
    0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.47
     außerdem
    0.46
    ↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.45
    Act Density 0.013%

    No Known Activations