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

    Neuronpedia

    INDEX
    Explanations

    reports of legal proceedings and official statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     بيها
    -0.81
    +#+#
    -0.59
     (
    -0.51
    зулта
    -0.48
     to
    -0.46
    ص
    -0.46
     concerning
    -0.45
    :
    -0.45
    ph
    -0.44
     we
    -0.43
    POSITIVE LOGITS
     houſe
    0.88
     ſtre
    0.83
     ſtate
    0.82
     Houſe
    0.82
     ddelweddau
    0.78
     ftate
    0.77
     ſche
    0.75
    ^(@)
    0.75
     deſt
    0.74
     ſeveral
    0.74
    Act Density 0.094%

    No Known Activations