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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ADS
    -0.08
    竺
    -0.07
    濡
    -0.07
     immediately
    -0.07
     HCI
    -0.07
     indul
    -0.07
    蕙
    -0.07
     Ada
    -0.07
     stup
    -0.07
     acquaint
    -0.07
    POSITIVE LOGITS
    arent
    0.08
    ункци
    0.08
    מניע
    0.07
    -era
    0.07
     şey
    0.07
    求
    0.07
    ʙ
    0.07
    ()),↵
    0.07
    pliers
    0.07
    폄
    0.07
    Act Density 0.021%

    No Known Activations