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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    matter
    -0.73
    coal
    -0.65
    Sad
    -0.63
    Fail
    -0.62
    erno
    -0.62
    rite
    -0.61
    Cause
    -0.61
    tsy
    -0.61
     opium
    -0.60
     explan
    -0.60
    POSITIVE LOGITS
     Indiana
    0.60
     Premium
    0.59
    visors
    0.58
    IELD
    0.57
     ×
    0.56
     maxim
    0.56
     tread
    0.55
    rection
    0.55
    ards
    0.55
     Queens
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.