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

    Neuronpedia

    INDEX
    Explanations

    action verbs in past tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence or actions of individuals, particularly in contexts of capability or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itton
    -0.68
    ahime
    -0.68
     Introdu
    -0.65
    wig
    -0.65
    pez
    -0.64
     Locations
    -0.59
    soDeliveryDate
    -0.59
    udeau
    -0.59
    igs
    -0.58
     Attribution
    -0.58
    POSITIVE LOGITS
     whatsoever
    1.26
     nor
    1.09
     ever
    1.04
     anymore
    0.96
     EVER
    0.92
     necessarily
    0.91
     anywhere
    0.91
     bothered
    0.88
     remotely
    0.85
     slightest
    0.83
    Act Density 0.201%

    No Known Activations