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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atre
    -0.80
    izen
    -0.74
    alde
    -0.73
    hani
    -0.67
    jri
    -0.66
    reon
    -0.66
    artifacts
    -0.66
    jab
    -0.66
    armac
    -0.66
    isitions
    -0.65
    POSITIVE LOGITS
     Thick
    0.68
     Borders
    0.66
     The
    0.63
     Fet
    0.63
     Cull
    0.61
     Corpus
    0.60
     Fey
    0.60
     Pipeline
    0.60
     Yellowstone
    0.59
     Contin
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.