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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .asp
    -0.08
     Flutter
    -0.07
     besar
    -0.07
     hollow
    -0.06
     Tok
    -0.06
     Frontier
    -0.06
    最好
    -0.06
    Admin
    -0.06
    .Api
    -0.06
     worksheets
    -0.06
    POSITIVE LOGITS
    ']."</
    0.07
    :"↵
    0.07
    	code
    0.07
     וב
    0.07
    /high
    0.06
    ❞
    0.06
    剟
    0.06
     draws
    0.06
     arbe
    0.06
     çıkma
    0.06
    Act Density 0.145%

    No Known Activations