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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    '
    0.55
    Continue
    0.55
    ’
    0.52
     Muslim
    0.50
    -
    0.48
    0.47
    President
    0.46
     government
    0.46
     American
    0.46
     brainchild
    0.46
    POSITIVE LOGITS
    棤
    0.61
    ätzen
    0.54
     Formatting
    0.52
    abilă
    0.51
    ungsseite
    0.51
    qualiter
    0.51
     بالوں
    0.51
    ᐋ
    0.51
    onycha
    0.50
    knię
    0.50
    Act Density 0.000%

    No Known Activations