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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     durata
    0.39
    র্দ
    0.37
    𒂍
    0.36
     splendour
    0.36
    phalt
    0.35
    ضل
    0.35
    frast
    0.35
    ząc
    0.34
    stin
    0.34
     求
    0.34
    POSITIVE LOGITS
     Tailwind
    0.43
     બનાવે
    0.43
     protects
    0.42
     সাধন
    0.40
    नाज
    0.40
     argued
    0.39
    든지
    0.39
     teased
    0.38
     intimidation
    0.38
     cascades
    0.37
    Act Density 0.000%

    No Known Activations