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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kus
    -0.73
     bear
    -0.66
     weigh
    -0.66
     related
    -0.63
     mart
    -0.63
     climb
    -0.61
     Wolf
    -0.59
     rip
    -0.59
     provoking
    -0.58
     crush
    -0.58
    POSITIVE LOGITS
    NetMessage
    0.84
    fman
    0.82
    apolis
    0.77
    pees
    0.77
    notations
    0.76
    Recipe
    0.73
    heast
    0.72
    é¾įå
    0.72
    acons
    0.71
    CONCLUS
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.