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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    idth
    -0.75
    lan
    -0.75
    idi
    -0.74
    itate
    -0.73
    lis
    -0.70
    rosso
    -0.70
     Machina
    -0.69
    enegger
    -0.69
    tti
    -0.68
    opsis
    -0.66
    POSITIVE LOGITS
     disg
    0.80
     senses
    0.73
     racket
    0.71
     jew
    0.67
     account
    0.66
    ommel
    0.66
     Ukrain
    0.63
     htt
    0.61
     transl
    0.61
    deal
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.