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

    Neuronpedia

    INDEX
    Explanations

    programming-related commands and statuses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Jost
    -0.50
     Huxley
    -0.43
    جان
    -0.42
    usda
    -0.42
     exclu
    -0.42
     Monticello
    -0.40
    onerror
    -0.40
    du
    -0.39
     Serra
    -0.38
    ญ
    -0.37
    POSITIVE LOGITS
    ]")]
    0.93
    ValueGeneration
    0.92
    IsContent
    0.82
    AxisAlignment
    0.82
     незавершена
    0.81
     kasarigan
    0.79
    __*/
    0.78
     дописавши
    0.78
    abetes
    0.77
     Chwiliwch
    0.74
    Act Density 0.017%

    No Known Activations