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

    Neuronpedia

    INDEX
    Explanations

    imperative statements urging action or change

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or agitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iday
    -0.70
    aneously
    -0.68
     culminating
    -0.65
     synonymous
    -0.64
    cember
    -0.64
     concluding
    -0.62
    Posted
    -0.61
    similar
    -0.61
    changed
    -0.60
     unmatched
    -0.60
    POSITIVE LOGITS
     yourselves
    1.24
    !:
    1.09
     Yourself
    1.04
     yourself
    1.03
    !
    1.02
    !'
    1.00
    !".
    0.92
    !"
    0.92
    !",
    0.91
     NOW
    0.90
    Act Density 0.291%

    No Known Activations