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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Stamp
    -0.77
     monop
    -0.68
    tails
    -0.66
     Rib
    -0.65
    hest
    -0.64
     recorder
    -0.63
     Bomber
    -0.61
    hair
    -0.61
     Elephant
    -0.60
     mand
    -0.59
    POSITIVE LOGITS
    ======
    0.77
    isconsin
    0.74
    IFA
    0.67
    ioch
    0.67
    bur
    0.66
     hepat
    0.63
    rawdownloadcloneembedreportprint
    0.62
    Jer
    0.62
    Compan
    0.62
    Jake
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.