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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Kaplan
    -0.29
    åįł
    -0.28
    azzi
    -0.28
    lectic
    -0.27
     Reading
    -0.26
    iner
    -0.26
    .textContent
    -0.26
    loser
    -0.26
    asket
    -0.25
    lis
    -0.25
    POSITIVE LOGITS
    æıĨ
    0.27
     bom
    0.26
    пÑĥÑģÑĤ
    0.26
    é³ħ
    0.26
     prm
    0.26
    angelog
    0.25
    NCY
    0.25
     synthetic
    0.24
    äºĨä¸Ģåľº
    0.24
    å°±æĺ¯åľ¨
    0.24
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.