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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     repair
    -0.07
     Carn
    -0.07
     nelle
    -0.07
    补
    -0.07
    (rect
    -0.07
     tobacco
    -0.06
     knew
    -0.06
    aux
    -0.06
    侵占
    -0.06
    _join
    -0.06
    POSITIVE LOGITS
    IDA
    0.08
    עמ
    0.08
     Vanguard
    0.07
     ers
    0.07
     часа
    0.07
     oli
    0.07
    نسب
    0.07
     Pradesh
    0.07
     şirket
    0.07
    ΐ
    0.07
    Act Density 0.003%

    No Known Activations