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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ────
    -0.08
     ----
    -0.07
     airstrikes
    -0.07
     Expect
    -0.07
    やはり
    -0.07
    _-_
    -0.07
    $list
    -0.07
    面子
    -0.07
     السابع
    -0.07
     vegan
    -0.07
    POSITIVE LOGITS
    waż
    0.07
     orn
    0.07
    mpz
    0.07
     gymn
    0.07
    ܩ
    0.07
    钋
    0.07
    ala
    0.07
     tłumacz
    0.06
    né
    0.06
    Ar
    0.06
    Act Density 0.005%

    No Known Activations