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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    £ı
    -0.82
    Newsletter
    -0.75
    anza
    -0.74
     Ples
    -0.74
    bringer
    -0.74
    vered
    -0.72
    ories
    -0.71
    ItemTracker
    -0.71
    rieg
    -0.67
    é¾
    -0.66
    POSITIVE LOGITS
     surgeons
    0.71
     missionaries
    0.67
     alumni
    0.64
    acements
    0.63
     educators
    0.63
     counselors
    0.63
     runners
    0.63
     graduates
    0.62
     teachers
    0.62
     bankers
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.