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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Beh
    -0.66
     Agric
    -0.64
     metab
    -0.63
     Maced
    -0.62
    Honest
    -0.60
    Enough
    -0.59
     motivational
    -0.59
    elled
    -0.58
    Jews
    -0.58
    Anonymous
    -0.58
    POSITIVE LOGITS
    sonian
    0.70
    oya
    0.69
    uth
    0.68
    llah
    0.66
    awaru
    0.65
    raught
    0.65
    uri
    0.64
    etta
    0.63
    oco
    0.63
    yang
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.