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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anamo
    -0.87
    ammy
    -0.85
     peril
    -0.68
    pport
    -0.67
    gey
    -0.65
    plin
    -0.64
     age
    -0.63
    elia
    -0.63
    onga
    -0.62
    owler
    -0.61
    POSITIVE LOGITS
    "}],"
    0.90
    advertisement
    0.86
    VERTISEMENT
    0.77
     WATCHED
    0.75
    backer
    0.75
    ADVERTISEMENT
    0.74
     Provided
    0.74
     behav
    0.73
     ãĤµ
    0.73
    taboola
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.