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

    Neuronpedia

    INDEX
    Explanations

    verbs related to causing harm or damage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative impacts or detrimental effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.75
    mad
    -0.66
    avior
    -0.66
    sa
    -0.61
    puted
    -0.60
    lich
    -0.59
    ann
    -0.58
    overed
    -0.58
     Edited
    -0.57
    zero
    -0.57
    POSITIVE LOGITS
     havoc
    1.14
     undermin
    1.01
     endanger
    0.76
     livelihood
    0.76
     morale
    0.76
     carbohyd
    0.76
     misunder
    0.75
     credibility
    0.75
     jeopard
    0.73
     detriment
    0.72
    Act Density 0.204%

    No Known Activations