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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    utterstock
    -0.73
    omon
    -0.67
     disadvantage
    -0.67
     discretion
    -0.66
     pose
    -0.66
     Discipline
    -0.64
     weakness
    -0.63
     Instruct
    -0.63
    obbies
    -0.63
     pastry
    -0.63
    POSITIVE LOGITS
    sonian
    0.69
    batch
    0.69
    nas
    0.69
    hered
    0.67
    scan
    0.66
    $$$$
    0.66
    kept
    0.66
    ulative
    0.64
    issance
    0.63
    interstitial
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.