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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    contractions and the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cum
    -0.79
    ]+
    -0.71
    soever
    -0.69
    ranged
    -0.67
    âĵĺ
    -0.66
    >]
    -0.64
    -"
    -0.63
     biod
    -0.62
     agitation
    -0.62
    rone
    -0.62
    POSITIVE LOGITS
    estern
    0.69
    resa
    0.67
     Tycoon
    0.66
     Ful
    0.65
     Official
    0.64
    bris
    0.64
    advertisement
    0.63
    nik
    0.61
     ironic
    0.61
    gae
    0.60
    Act Density 0.400%

    No Known Activations