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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    selves
    1.25
    henburg
    1.21
    ুনিক
    1.12
    words
    1.10
    sentences
    1.10
    decks
    1.08
    speakers
    1.07
    iterranean
    1.07
     paragraphs
    1.06
    suffixes
    1.06
    POSITIVE LOGITS
    ر
    1.07
    AddNew
    0.89
    Freight
    0.87
    Accessibility
    0.85
    Empty
    0.85
    Accessible
    0.84
     rzecz
    0.83
    Access
    0.83
    Lett
    0.83
    Cheat
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.