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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <bos>
    3.00
     the
    2.34
     and
    2.31
     with
    2.12
    the
    2.11
     is
    2.10
     both
    2.08
    '
    2.03
     were
    2.02
     a
    2.02
    POSITIVE LOGITS
     slightest
    1.89
     midst
    1.80
     outermost
    1.77
    Diffuse
    1.72
     outskirts
    1.67
     purest
    1.65
     coldest
    1.65
    Hydrochloride
    1.64
     nascent
    1.63
     lowest
    1.59
    Act Density 0.670%

    No Known Activations