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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ijn
    -0.72
    fine
    -0.72
    clair
    -0.71
    sterdam
    -0.71
    ventory
    -0.70
    luence
    -0.70
    cius
    -0.70
    lic
    -0.68
    license
    -0.68
    lication
    -0.68
    POSITIVE LOGITS
     Technician
    0.74
     technicians
    0.69
     grandparents
    0.60
     Corinth
    0.60
     nevertheless
    0.60
     Nurs
    0.59
     Patriarch
    0.59
     horm
    0.59
    ij士
    0.58
     holiest
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.