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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    d
    1.51
    at
    1.40
    re
    1.39
    ر
    1.32
    in
    1.27
    ad
    1.24
    aw
    1.23
    ת
    1.20
    don
    1.19
    en
    1.19
    POSITIVE LOGITS
    毅
    1.09
    requestFocus
    1.06
     gezegd
    1.06
     irresist
    1.03
    両
    1.03
     numérica
    1.02
    endosi
    1.02
    ্লীল
    0.99
    ৮
    0.99
     रझा
    0.99
    Act Density 0.000%

    No Known Activations