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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    on
    1.25
    uit
    1.21
    it
    1.14
    rows
    1.14
    at
    1.12
    į
    1.07
    il
    1.05
    he
    1.04
    ene
    1.02
    ো
    1.00
    POSITIVE LOGITS
     ਜੋ
    1.34
     worse
    1.32
     insurrection
    1.25
     romp
    1.25
     warn
    1.24
     worsen
    1.21
    葶
    1.21
     confuse
    1.18
     funcionar
    1.17
     antigua
    1.16
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.