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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    in
    0.54
    i
    0.46
     a
    0.45
    ל
    0.45
     roc
    0.45
    愺
    0.45
    ִי
    0.44
    ادي
    0.43
    l
    0.43
    经历了
    0.42
    POSITIVE LOGITS
     사람들이
    0.49
     ಯಾವ
    0.48
     Gesam
    0.46
     சாலையில்
    0.46
    에서도
    0.45
     невероят
    0.45
    UNCH
    0.44
     kubectl
    0.44
     Verkauf
    0.44
     incógn
    0.44
    Act Density 0.000%

    No Known Activations