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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Although
    0.46
     Yet
    0.46
    룩
    0.42
    Yet
    0.42
     অথচ
    0.41
     虽然
    0.41
    يرة
    0.41
     Doch
    0.40
     Jeśli
    0.39
    একটা
    0.39
    POSITIVE LOGITS
     also
    0.41
    也
    0.40
    上也
    0.39
     også
    0.38
     myös
    0.38
     anche
    0.37
     também
    0.36
    also
    0.36
     också
    0.36
     επίσης
    0.35
    Act Density 0.000%

    No Known Activations