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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    На
    1.36
     Со
    1.26
    Д
    1.25
    Verdict
    1.18
    Я
    1.17
    Neither
    1.17
    ymmetrical
    1.13
    Со
    1.13
    Ба
    1.12
     sentencing
    1.12
    POSITIVE LOGITS
     Replies
    1.00
    εται
    0.98
     sombras
    0.98
    suited
    0.96
    lg
    0.95
     Hitch
    0.95
    sk
    0.94
    𝘀
    0.94
     circunstancias
    0.94
     peanut
    0.94
    Act Density 0.000%

    No Known Activations