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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    y
    1.10
    yb
    1.09
    یات
    1.05
     risking
    1.02
     deck
    0.99
    ele
    0.96
    zzle
    0.94
    ksam
    0.93
     carefully
    0.93
     risk
    0.92
    POSITIVE LOGITS
    Ő
    1.32
     extrême
    1.29
     Każ
    1.26
    quinazoline
    1.26
    azoline
    1.26
    മായ
    1.24
     énon
    1.24
    छे
    1.22
     pás
    1.20
     वाले
    1.19
    Act Density 0.000%

    No Known Activations