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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     toes
    -0.65
     gasoline
    -0.64
     dormant
    -0.63
     panties
    -0.63
    kus
    -0.63
    idia
    -0.62
    cule
    -0.60
     bells
    -0.59
    omore
    -0.59
     residents
    -0.59
    POSITIVE LOGITS
    eeks
    0.78
    ury
    0.75
    Nap
    0.73
    athi
    0.71
    apter
    0.70
    arist
    0.70
    Que
    0.69
    rib
    0.65
    achine
    0.65
    arily
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.