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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝘦
    1.58
    𝘤
    1.48
    𝘶
    1.47
    𝘯
    1.39
    𝘴
    1.31
    𝘻
    1.28
    𝘳
    1.27
    ])){
    1.25
    𝘨
    1.25
    𝘭
    1.24
    POSITIVE LOGITS
     dessen
    1.23
    יים
    1.17
     бес
    1.16
    võ
    1.13
    lari
    1.11
     Kõ
    1.11
    ัต
    1.10
     mää
    1.09
     ujian
    1.08
    inės
    1.07
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.