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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.90
     Franch
    -0.78
    SOURCE
    -0.77
    YL
    -0.73
    ontent
    -0.70
     Cohn
    -0.69
    VALUE
    -0.69
     Parenthood
    -0.68
    Notes
    -0.68
     RTX
    -0.67
    POSITIVE LOGITS
    eday
    0.87
     groom
    0.74
     spam
    0.71
     logging
    0.66
     beam
    0.64
     impart
    0.63
    hire
    0.63
     assurance
    0.63
     grazing
    0.63
     eaves
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.