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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrasts or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    combinations of conjunctions and expressions indicating inclusivity or emphasis in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ery
    -0.70
    erick
    -0.67
    icky
    -0.65
    edia
    -0.65
    ETHOD
    -0.65
    etting
    -0.63
    wyn
    -0.62
    ickers
    -0.61
    ICK
    -0.61
    eny
    -0.61
    POSITIVE LOGITS
    except
    1.58
     except
    1.55
     Including
    1.47
     including
    1.37
     regardless
    1.37
    including
    1.34
     irrespective
    1.34
     INCLUD
    1.21
     imaginable
    1.13
    excluding
    1.11
    Act Density 0.562%

    No Known Activations