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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    vae
    -0.88
    atche
    -0.77
    isions
    -0.77
    tyard
    -0.75
    ogue
    -0.74
    ursion
    -0.73
    herty
    -0.73
    behind
    -0.72
    hillary
    -0.71
    witz
    -0.71
    POSITIVE LOGITS
    theless
    0.80
     Cancel
    0.76
    Mania
    0.68
     ACTIONS
    0.65
    BUR
    0.63
     hypocrisy
    0.62
     usual
    0.61
    CU
    0.60
     Theft
    0.59
    \\\\\\\\\\\\\\\\
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.