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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     그는
    0.59
     Additionally
    0.52
     Also
    0.50
     Although
    0.49
    ↵↵
    0.47
     Today
    0.46
     although
    0.46
     ولكن
    0.46
    他也
    0.45
     But
    0.44
    POSITIVE LOGITS
    èses
    0.40
     einigen
    0.38
    某个
    0.38
    <unused48>
    0.38
     McCorm
    0.38
    ěli
    0.38
    تهم
    0.38
    馬
    0.38
    げる
    0.38
    блиоте
    0.37
    Act Density 0.000%

    No Known Activations