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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    т
    1.82
    boosting
    1.68
     explosives
    1.60
     dating
    1.54
    ٤
    1.47
    rhe
    1.45
    ../
    1.41
    ка
    1.41
    absence
    1.36
    بھ
    1.35
    POSITIVE LOGITS
    Probably
    1.76
     própria
    1.66
     supone
    1.66
     figlio
    1.64
    اا
    1.61
    ков
    1.60
     subito
    1.59
     병
    1.56
    ové
    1.54
     größ
    1.54
    Act Density 0.000%

    No Known Activations