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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lions
    1.01
    நில
    0.98
     чет
    0.93
     Artillery
    0.89
     monasteries
    0.88
     Lenin
    0.88
     tỷ
    0.87
     Donetsk
    0.87
     Lakes
    0.87
    lights
    0.87
    POSITIVE LOGITS
    “
    1.45
    "
    1.39
    ”
    1.39
    )"
    1.17
    }"
    1.15
    -"
    1.13
    )”
    1.10
    ",
    1.09
    ]"
    1.09
    ")
    1.08
    Act Density 0.000%

    No Known Activations