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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    A
    0.33
    In
    0.30
     In
    0.29
     included
    0.28
     A
    0.28
    4
    0.28
     includes
    0.27
     utilize
    0.27
    ↵
    0.27
     include
    0.27
    POSITIVE LOGITS
     pensamento
    0.31
     یا
    0.30
     wład
    0.29
    ังสือ
    0.29
     başka
    0.28
     columnName
    0.28
     booze
    0.28
    NewUrl
    0.28
     idées
    0.28
     menulis
    0.28
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.