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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aldo
    -0.72
    mination
    -0.69
    lua
    -0.69
    erk
    -0.69
    ikan
    -0.67
    gling
    -0.66
    erg
    -0.66
    cd
    -0.65
    orie
    -0.65
    sbm
    -0.65
    POSITIVE LOGITS
    icably
    0.67
     NCT
    0.66
     Slim
    0.63
     succ
    0.60
    phant
    0.60
     transitions
    0.59
    NetMessage
    0.59
    iffe
    0.57
     absent
    0.57
     artisan
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.