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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ports
    -0.70
    ourning
    -0.70
    hill
    -0.70
    acl
    -0.68
    uterte
    -0.67
    ortunate
    -0.67
    ict
    -0.66
    afa
    -0.66
    gans
    -0.66
    abal
    -0.65
    POSITIVE LOGITS
    #$
    0.73
    ï¸ı
    0.68
     Mori
    0.65
    below
    0.64
    ).[
    0.63
    minist
    0.63
     backstage
    0.62
     Wit
    0.62
     ballpark
    0.62
     Bulg
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.