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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     CBI
    -0.80
     sarc
    -0.63
    ---------
    -0.63
     broth
    -0.62
    ridor
    -0.62
    ENDED
    -0.61
     inflamm
    -0.61
     ANN
    -0.60
     TRAN
    -0.60
     Prompt
    -0.59
    POSITIVE LOGITS
    loo
    0.85
    estead
    0.73
    ographers
    0.72
    ouched
    0.72
    adies
    0.71
    perty
    0.71
    iquette
    0.71
    writers
    0.70
    kefeller
    0.70
    ieties
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.