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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    es
    1.51
    o
    1.20
    bs
    1.19
    ia
    1.11
    cs
    1.10
    Topic
    1.08
    Factor
    1.07
    ker
    1.04
    ikom
    1.04
    kah
    1.03
    POSITIVE LOGITS
     harassed
    0.96
     DELLA
    0.96
     belongings
    0.95
     lush
    0.91
     assurance
    0.91
     lieutenant
    0.91
     hauling
    0.90
    ajjati
    0.90
     ι
    0.90
     insistence
    0.89
    Act Density 0.000%

    No Known Activations