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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Freedom
    -0.07
    Submission
    -0.07
     Ernst
    -0.07
     Vlad
    -0.07
    ifferent
    -0.07
     voll
    -0.07
    Gay
    -0.07
    Portal
    -0.07
    (hit
    -0.07
    .seek
    -0.07
    POSITIVE LOGITS
    ᾽
    0.06
    ♱
    0.06
    🟡
    0.06
     =>
↵
    0.06
    헵
    0.06
     brib
    0.06
    traî
    0.06
    -auth
    0.06
    磜
    0.06
    <hr
    0.06
    Act Density 0.010%

    No Known Activations