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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Maker
    -0.80
    tl
    -0.77
    aukee
    -0.74
    ciation
    -0.73
     inheritance
    -0.70
    ³³³³³³³³³³³³³³³³
    -0.69
    Twe
    -0.68
    tein
    -0.67
    maker
    -0.66
    achus
    -0.66
    POSITIVE LOGITS
    hid
    0.77
    rity
    0.74
     steroids
    0.70
     Blaz
    0.69
    imb
    0.69
    urger
    0.68
    imar
    0.67
     penet
    0.62
    ©¶æ
    0.61
    amina
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.