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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    an
    1.55
    are
    1.45
    as
    1.33
    in
    1.27
    h
    1.27
    n
    1.23
    ar
    1.21
    ir
    1.21
    et
    1.17
    i
    1.16
    POSITIVE LOGITS
     is
    1.88
     to
    1.55
    ב
    1.41
    ()
    1.27
    ]
    1.16
     has
    1.14
     you
    1.09
     dismay
    1.06
     volition
    1.06
     söyl
    1.05
    Act Density 0.000%

    No Known Activations