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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     morgen
    0.58
     Nguyen
    0.54
    !”.
    0.53
    azz
    0.51
     hamm
    0.51
    𝗁
    0.50
    ibe
    0.50
    iseren
    0.50
     Tuti
    0.50
     Rahul
    0.49
    POSITIVE LOGITS
    无
    0.52
    颗粒
    0.50
    AS
    0.49
    En
    0.49
    이
    0.48
    ON
    0.47
     can
    0.47
    エン
    0.47
    EN
    0.47
    Elastic
    0.47
    Act Density 0.000%

    No Known Activations