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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Peel
    -0.82
     Pop
    -0.78
    ovie
    -0.72
     Pride
    -0.70
     Virtue
    -0.67
     Menu
    -0.66
     Reign
    -0.64
     VICE
    -0.64
     slack
    -0.64
     Fuji
    -0.64
    POSITIVE LOGITS
    ilion
    0.82
     widow
    0.71
    anos
    0.71
    Rew
    0.68
    amination
    0.67
    ysis
    0.67
    ossier
    0.66
    HCR
    0.66
    Failure
    0.65
    OSS
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.