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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ernand
    -0.73
     BRA
    -0.71
    maid
    -0.68
    kus
    -0.68
     NAME
    -0.66
     Latin
    -0.66
     Dragonbound
    -0.65
    lance
    -0.63
    ifax
    -0.62
    hov
    -0.61
    POSITIVE LOGITS
    igator
    0.76
    sembly
    0.76
    oys
    0.70
    ADRA
    0.67
    uces
    0.67
    hyde
    0.64
    Constructed
    0.63
    uce
    0.63
    frey
    0.61
    imates
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.