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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ang
    0.52
    output
    0.48
    yoga
    0.47
    age
    0.45
    angat
    0.45
    ages
    0.44
    osters
    0.44
    covid
    0.44
    andi
    0.43
     అదే
    0.43
    POSITIVE LOGITS
     killing
    0.46
    ℞
    0.45
    OfDeath
    0.44
    作为一个
    0.43
     ruin
    0.41
     Hond
    0.41
    Buy
    0.40
     Univer
    0.40
    乂
    0.40
    جراء
    0.40
    Act Density 0.009%

    No Known Activations