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

    Neuronpedia

    INDEX
    Explanations

    Latin characters Ċ followed by numerical values 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    sentences indicating conflict or violence, particularly in a geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commissions
    -0.67
    enary
    -0.65
     Minion
    -0.65
    eca
    -0.65
     Vaughn
    -0.64
     purs
    -0.64
     honors
    -0.63
    boro
    -0.63
    endas
    -0.62
    utical
    -0.62
    POSITIVE LOGITS
    Meanwhile
    1.16
    ccording
    0.98
    SPONSORED
    0.98
    However
    0.98
    Such
    0.97
    Asked
    0.95
    AFP
    0.94
    Reuters
    0.92
    Scroll
    0.90
    Foreign
    0.90
    Act Density 0.519%

    No Known Activations