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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hower
    -0.72
    perial
    -0.72
     Consortium
    -0.70
     gloom
    -0.68
    angelo
    -0.66
    ented
    -0.63
    ÅŁ
    -0.63
     Entered
    -0.63
    ibliography
    -0.63
    itri
    -0.63
    POSITIVE LOGITS
     Generations
    0.77
    riad
    0.73
    ģĸ
    0.72
    Leod
    0.67
    PLA
    0.67
     Maher
    0.64
     Favor
    0.63
     Machines
    0.61
    product
    0.61
     Pip
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.