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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Liberal
    -0.30
    .lot
    -0.25
    arer
    -0.25
    luet
    -0.25
     ttl
    -0.25
     @[
    -0.25
    ARED
    -0.24
    äºı
    -0.24
    Īëĭ¤
    -0.24
    -lib
    -0.24
    POSITIVE LOGITS
     conviction
    0.28
    ino
    0.28
    æ°´åĩĨ
    0.26
    -exc
    0.26
    greso
    0.25
    pan
    0.25
     наÑģ
    0.25
    jian
    0.25
    edb
    0.24
    ’ex
    0.24
    Act Density 0.002%

    No Known Activations

    This feature has no known activations.