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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    就像
    0.42
     $_{\
    0.36
     Alain
    0.36
     desal
    0.36
    wege
    0.36
    ორის
    0.36
    рах
    0.34
    찍
    0.34
    接
    0.34
    COCH
    0.34
    POSITIVE LOGITS
     truth
    0.51
     definitive
    0.50
     COMPLETE
    0.50
     Disturb
    0.47
     Average
    0.46
    basics
    0.45
    COMPLETE
    0.45
     disturbing
    0.45
     distinction
    0.45
     conclusive
    0.45
    Act Density 0.002%

    No Known Activations