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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dengan
    1.40
    With
    1.38
    It
    1.36
    The
    1.31
    That
    1.31
     With
    1.31
    To
    1.26
     That
    1.25
     To
    1.23
     It
    1.22
    POSITIVE LOGITS
    ᅯ
    1.47
    ᅭ
    1.46
     snd
    1.29
    simmons
    1.27
    computation
    1.27
    lesssim
    1.27
    sy
    1.26
    coating
    1.25
    ursal
    1.25
    atthakath
    1.24
    Act Density 0.044%

    No Known Activations