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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases suggesting influence, impact, or assessment towards the subject matter

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and auxiliary verbs indicating possibilities or abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooters
    -0.71
    ques
    -0.64
    anwhile
    -0.63
     remarks
    -0.62
    allas
    -0.62
     Sources
    -0.61
     Reports
    -0.58
    rams
    -0.56
    Che
    -0.56
     Cond
    -0.56
    POSITIVE LOGITS
    natureconservancy
    0.79
     antit
    0.72
     bothered
    0.69
     bitten
    0.68
    :(
    0.68
     fasc
    0.65
     bothering
    0.65
     genuinely
    0.64
    )].
    0.63
    STD
    0.62
    Act Density 0.286%

    No Known Activations