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

    Neuronpedia

    INDEX
    Explanations

    mentions of serious matters or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to serious issues or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enaries
    -0.82
    wright
    -0.74
    ride
    -0.73
    sylv
    -0.72
    AW
    -0.70
    ifully
    -0.69
     seamlessly
    -0.69
    weet
    -0.67
    urated
    -0.67
    av
    -0.65
    POSITIVE LOGITS
     consideration
    1.02
    lly
    0.88
     threat
    0.87
     contender
    0.86
     injury
    0.85
     threats
    0.84
     allegation
    0.84
     contenders
    0.83
     trouble
    0.82
     danger
    0.80
    Act Density 0.038%

    No Known Activations