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

    Neuronpedia

    INDEX
    Explanations

    references to official bodies or committees

    oai_token-act-pair · gpt-3.5-turbo

    references to commissions or investigative bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Klu
    -0.85
    Els
    -0.69
     Dharma
    -0.66
    VK
    -0.66
     Tibetan
    -0.66
     Sina
    -0.65
    nikov
    -0.64
     prest
    -0.63
     Dad
    -0.63
     Aid
    -0.63
    POSITIVE LOGITS
     commissions
    1.11
     commission
    0.99
     commissioners
    0.95
    issions
    0.89
    ing
    0.83
    uting
    0.78
    eers
    0.77
    merce
    0.74
    ittee
    0.71
    eer
    0.69
    Act Density 0.009%

    No Known Activations