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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     even
    1.35
     and
    1.35
     六
    1.34
     (
    1.33
     和
    1.31
     at
    1.26
     political
    1.25
     AND
    1.24
     a
    1.24
     suffer
    1.24
    POSITIVE LOGITS
    aktu
    1.67
    essere
    1.65
    acas
    1.55
     ছিলোনা
    1.54
    varchar
    1.54
    dimensioni
    1.53
    ukuran
    1.53
    Ens
    1.52
    Chaos
    1.52
    motion
    1.52
    Act Density 0.017%

    No Known Activations