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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĪ
    -0.79
    ĺħ
    -0.77
     congr
    -0.75
    GBT
    -0.72
    æ©
    -0.72
    oola
    -0.71
    âķIJâķIJ
    -0.71
    âĸ¬
    -0.70
     nurs
    -0.70
     Oro
    -0.70
    POSITIVE LOGITS
    hers
    0.66
    orney
    0.65
     Clancy
    0.63
    hor
    0.63
    sth
    0.62
    immer
    0.61
    ior
    0.61
    sect
    0.61
    oths
    0.59
    iors
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.