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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ITIES
    -0.69
     Cummings
    -0.67
    eries
    -0.67
    irds
    -0.65
    ibles
    -0.65
    atl
    -0.63
    andise
    -0.63
    apons
    -0.63
     Lamar
    -0.63
     Ital
    -0.63
    POSITIVE LOGITS
     environmentally
    0.71
     degrading
    0.71
     superpower
    0.70
     insecure
    0.69
     electron
    0.67
     nanop
    0.66
     ideologically
    0.66
     dismant
    0.66
     dystopian
    0.64
     deter
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.