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

    Neuronpedia

    INDEX
    Explanations

    references to collective actions or communal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erick
    -0.70
    tz
    -0.66
    wyn
    -0.66
    agram
    -0.65
    ery
    -0.65
    icky
    -0.64
    eln
    -0.64
    edia
    -0.64
    ridge
    -0.64
    eny
    -0.62
    POSITIVE LOGITS
     except
    1.64
    except
    1.63
     regardless
    1.46
     Including
    1.45
     including
    1.43
     irrespective
    1.43
    including
    1.38
     INCLUD
    1.24
     imaginable
    1.15
    excluding
    1.15
    Act Density 0.249%

    No Known Activations