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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     साथियों
    1.66
     размера
    1.56
    서
    1.56
    લ
    1.56
     connues
    1.55
     inférieurs
    1.52
    ра
    1.49
    ג
    1.47
    ها
    1.46
     ennemis
    1.45
    POSITIVE LOGITS
     idiot
    1.77
     Extremely
    1.75
     Tourists
    1.73
     Beware
    1.68
     Apo
    1.67
    park
    1.66
     Aan
    1.63
    sync
    1.62
    ompact
    1.62
     Do
    1.60
    Act Density 0.018%

    No Known Activations