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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Palestinians
    -0.69
     deaf
    -0.68
    Palestinian
    -0.65
     Jude
    -0.64
     observable
    -0.63
     envelope
    -0.62
    Either
    -0.62
    warts
    -0.61
     proto
    -0.59
    xious
    -0.59
    POSITIVE LOGITS
    andise
    0.80
    eor
    0.77
    opsis
    0.77
    ruby
    0.74
    ornia
    0.74
    \/\/
    0.72
    pour
    0.70
    pection
    0.70
    abase
    0.70
    ortium
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.