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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ’:
    -0.08
    scenario
    -0.07
    /proto
    -0.07
    /utility
    -0.07
    modele
    -0.07
    _Selection
    -0.07
     trx
    -0.07
     Cheryl
    -0.07
    㴔
    -0.07
     vuel
    -0.07
    POSITIVE LOGITS
    封闭
    0.07
    _major
    0.07
    POS
    0.07
    Length
    0.07
    BD
    0.07
     FORWARD
    0.07
    Kar
    0.07
    _emails
    0.07
    0.06
    tested
    0.06
    Act Density 0.006%

    No Known Activations