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

    Neuronpedia

    INDEX
    Explanations

    words related to legislation, government, and regulatory systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     alip
    -0.58
    ==="
    -0.49
    allclose
    -0.49
    !=-
    -0.47
     öf
    -0.46
     logarith
    -0.46
     Erkrank
    -0.46
    şekkür
    -0.46
    :].
    -0.46
    ])*
    -0.45
    POSITIVE LOGITS
     parteci
    0.80
     vuol
    0.78
     dimenti
    0.74
    fordable
    0.74
     dicono
    0.72
     sappi
    0.71
     milano
    0.70
     thermomix
    0.69
     migli
    0.69
     interessa
    0.68
    Act Density 0.842%

    No Known Activations