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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uphem
    -0.77
    emort
    -0.77
    estic
    -0.76
    verett
    -0.69
    inational
    -0.69
    oppable
    -0.66
    aughs
    -0.65
    ocry
    -0.64
    braska
    -0.64
    London
    -0.64
    POSITIVE LOGITS
    isations
    0.74
    ctrl
    0.71
    must
    0.69
     Scrib
    0.65
    flies
    0.62
    thro
    0.62
     Inspection
    0.61
    washer
    0.61
     steering
    0.60
     throats
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.