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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     butcher
    -0.69
    ahime
    -0.68
     tanker
    -0.68
     torch
    -0.65
    rette
    -0.63
     graffiti
    -0.63
     crackdown
    -0.62
     midrange
    -0.62
     destro
    -0.61
     haw
    -0.61
    POSITIVE LOGITS
    omorph
    0.82
     Clim
    0.79
     Blackwell
    0.77
     Fore
    0.73
    opl
    0.71
     Principle
    0.71
     Bound
    0.70
     Born
    0.69
     Ecology
    0.66
     Âł Âł
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.