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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    leases
    -0.78
     Advocate
    -0.66
    aires
    -0.65
     Rus
    -0.63
    lishes
    -0.62
     Venezuel
    -0.62
     Aram
    -0.61
     elig
    -0.61
     Jehovah
    -0.61
     Ares
    -0.60
    POSITIVE LOGITS
    ĸļ
    1.06
    «ĺ
    0.91
    Ŀ
    0.88
     Lumpur
    0.80
    ¶ħ
    0.78
    §
    0.78
    µ
    0.78
    Ĥ
    0.78
    bably
    0.74
    ĭ
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.