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

    Neuronpedia

    INDEX
    Explanations

    news agencies or sources

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Reuters news agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sed
    -0.70
    izers
    -0.61
     Britann
    -0.61
    ount
    -0.58
    uster
    -0.58
    dies
    -0.56
     perm
    -0.56
     prem
    -0.56
     weights
    -0.56
     intellig
    -0.55
    POSITIVE LOGITS
    UTERS
    0.91
    FORE
    0.90
    CLASSIFIED
    0.85
    Film
    0.79
    photo
    0.78
    HAEL
    0.77
    PLE
    0.76
    externalActionCode
    0.76
    WAR
    0.75
    allery
    0.74
    Act Density 0.017%

    No Known Activations