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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     their
    -2.02
    Their
    -1.80
     themselves
    -1.78
    their
    -1.77
     Their
    -1.77
     THEIR
    -1.55
    themselves
    -1.48
    他们的
    -1.41
     theirs
    -1.38
    彼らの
    -1.35
    POSITIVE LOGITS
    تقاوى
    0.59
    FFIX
    0.58
    Démographie
    0.58
    Datuak
    0.57
    Pautan
    0.54
    Tracce
    0.54
    0.52
    ◄
    0.51
    ]),
    0.51
    SBATCH
    0.50
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.