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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    חי
    0.46
    if
    0.46
    #!/
    0.45
    おそらく
    0.45
    Profiles
    0.43
    *
    0.42
    ל
    0.42
    decl
    0.41
    guns
    0.41
    Potential
    0.41
    POSITIVE LOGITS
     neben
    0.53
     Cork
    0.52
     Countess
    0.51
    ение
    0.51
     聞い
    0.51
     Umbrella
    0.50
     추
    0.50
     Duchess
    0.49
     Mace
    0.49
    illées
    0.49
    Act Density 0.000%

    No Known Activations