INDEX
    Explanations

    language bridging connectors

    New Auto-Interp
    Negative Logits
     πως
    1.02
     comfy
    1.01
    ల్ని
    0.91
     crux
    0.91
     জন্যে
    0.88
     inbuilt
    0.87
     वो
    0.86
     чтоб
    0.85
    0.85
     kinda
    0.84
    POSITIVE LOGITS
    <eos>
    1.72
    <start_of_image>
    1.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.42
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.42
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.37
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.36
    ↵↵↵↵↵↵↵↵↵↵
    1.32
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.31
    Act Density 1.443%

    No Known Activations