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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     expiring
    1.22
     encouraging
    1.20
    ти
    1.14
     exig
    1.13
     jaanu
    1.11
     kanilang
    1.09
    ش
    1.07
    ona
    1.05
    elier
    1.05
     цен
    1.05
    POSITIVE LOGITS
    𝗻
    1.17
    жды
    1.11
    cout
    1.11
    𝗧
    1.11
    can
    1.11
    𝗘
    1.10
    Jeśli
    1.09
    𝗲
    1.06
    𝗴
    1.06
    𝗯
    1.05
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.