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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    =>
    -0.80
    lav
    -0.73
    bern
    -0.70
    unity
    -0.66
    ciating
    -0.64
    AAAA
    -0.62
     Citiz
    -0.61
    anting
    -0.61
     clicking
    -0.60
    Reviewer
    -0.59
    POSITIVE LOGITS
     Dunham
    0.77
    aredevil
    0.76
     Reconstruction
    0.72
     arrang
    0.65
    ength
    0.65
    oppy
    0.62
    OAD
    0.61
     iT
    0.61
     Providence
    0.60
     Jinping
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.