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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Humor
    0.87
     foliage
    0.86
     Monochrome
    0.86
    avises
    0.86
     Lotion
    0.85
     Uncertainty
    0.85
     Losses
    0.85
     minions
    0.84
     windings
    0.83
    কোষ
    0.83
    POSITIVE LOGITS
    Ş
    0.82
    מה
    0.77
    مع
    0.76
    lle
    0.76
    ORE
    0.75
    IKI
    0.75
    spiritual
    0.75
    पटना
    0.75
    ९
    0.75
    CRIPT
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.