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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    n
    1.24
    iteit
    1.16
    l
    1.07
    empi
    1.04
    שה
    1.02
    igraf
    1.00
    τητα
    1.00
    éria
    0.98
    ranno
    0.97
    անդ
    0.97
    POSITIVE LOGITS
     purified
    1.45
     purify
    1.40
    主任
    1.35
     exhaust
    1.34
    Minimal
    1.32
     gulf
    1.30
    鲽
    1.29
    氳
    1.29
     vicious
    1.29
    ZIP
    1.27
    Act Density 0.000%

    No Known Activations