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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    displaystyle
    1.30
    ıld
    1.03
    at
    1.00
    ()
    0.99
    MOVE
    0.99
    ($
    0.96
    all
    0.95
    Latin
    0.92
    $\
    0.91
     Rosenthal
    0.90
    POSITIVE LOGITS
    σουν
    1.32
     فس
    1.23
    কি
    1.20
    ಗಳ
    1.18
     σχετικά
    1.16
    cripts
    1.15
    fromParams
    1.12
     образом
    1.12
    ቹ
    1.11
     extremism
    1.11
    Act Density 0.000%

    No Known Activations