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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -Javadoc
    -0.07
    #######↵
    -0.07
     hope
    -0.07
    \P
    -0.07
    /testing
    -0.07
     dec
    -0.07
    ’ex
    -0.06
    .save
    -0.06
    section
    -0.06
     testified
    -0.06
    POSITIVE LOGITS
     Zahl
    0.07
     Ceramic
    0.07
     rift
    0.07
    BITS
    0.07
    Ultra
    0.07
    _LIMIT
    0.07
     splendid
    0.06
     LW
    0.06
     astonishing
    0.06
    Bron
    0.06
    Act Density 0.018%

    No Known Activations