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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0
    1.70
     in
    1.45
    ０
    1.15
     an
    1.13
     In
    1.07
     Into
    1.07
    ],
    1.05
    เป็น
    1.04
     inflaton
    1.03
     increases
    1.02
    POSITIVE LOGITS
    ів
    1.11
    ac
    1.05
    ስቃ
    1.04
    .
    1.01
     constitu
    1.00
    ﻊ
    1.00
    ٣
    0.98
     comprim
    0.96
     coexist
    0.93
     negoci
    0.91
    Act Density 0.000%

    No Known Activations