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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ist
    1.60
    zhang
    1.39
    fontSize
    1.37
    க
    1.30
    er
    1.25
    ment
    1.25
    squared
    1.25
    зив
    1.25
     excused
    1.22
    aniach
    1.22
    POSITIVE LOGITS
    覦
    1.27
    丆
    1.20
     mila
    1.09
     êtes
    1.07
    ダメ
    1.02
     celebra
    1.01
     delimiters
    0.99
    `),
    0.98
     anharmonic
    0.98
    います
    0.97
    Act Density 0.000%

    No Known Activations