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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arde
    -0.75
    conom
    -0.69
    ahu
    -0.68
    ¬¼
    -0.66
    assed
    -0.66
    uay
    -0.65
    eni
    -0.65
    uy
    -0.64
    atre
    -0.64
    iller
    -0.64
    POSITIVE LOGITS
     etc
    1.17
     preferably
    1.03
     regardless
    0.98
     including
    0.97
     please
    0.96
     however
    0.92
     INCLUD
    0.90
     irrespective
    0.88
     except
    0.86
     respectively
    0.86
    Act Density 0.762%

    No Known Activations