Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     infatti
    0.45
    ડી
    0.41
     porém
    0.39
     গুলো
    0.38
     więc
    0.38
    ؤں
    0.38
     এইভাবে
    0.37
     pousse
    0.37
     তাই
    0.37
     distillation
    0.36
    POSITIVE LOGITS
    #!
    0.36
     although
    0.35
     precisely
    0.35
    而不是
    0.35
    ?!
    0.34
    destructive
    0.34
    [!
    0.34
    伴
    0.33
    即便
    0.33
    shard
    0.33
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.