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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     artif
    -0.74
    icer
    -0.74
    cham
    -0.73
     concess
    -0.69
     recip
    -0.69
     surpr
    -0.65
     plent
    -0.63
     congratulate
    -0.63
    utral
    -0.62
    icing
    -0.61
    POSITIVE LOGITS
    Malley
    0.84
    rament
    0.74
    eers
    0.71
    alos
    0.71
    ########
    0.70
     Strip
    0.67
    ###
    0.66
     Burg
    0.66
     Alley
    0.65
    itual
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.