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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     disappointed
    0.45
    3
    0.41
    仏
    0.41
    後半
    0.40
     indignant
    0.39
    供
    0.39
     ':
    0.38
    سین
    0.38
    4
    0.38
     `<
    0.37
    POSITIVE LOGITS
     свое
    0.42
    oraj
    0.41
     ServiceNow
    0.41
    ណ
    0.40
     اول
    0.40
     GAAP
    0.40
     Primeiro
    0.39
    ној
    0.39
    acion
    0.38
    ન્
    0.38
    Act Density 0.000%

    No Known Activations