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

    Neuronpedia

    INDEX
    Explanations

    Reuters news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to the news agency Reuters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     haun
    -0.78
     adm
    -0.69
     mosqu
    -0.69
     comprom
    -0.66
     oun
    -0.64
    sed
    -0.64
     satell
    -0.63
     amaz
    -0.62
     distingu
    -0.62
     baff
    -0.61
    POSITIVE LOGITS
    )
    0.89
    )-
    0.89
    )—
    0.82
    +)
    0.76
     Foundation
    0.75
     Health
    0.74
     ATT
    0.72
    )--
    0.72
    %)
    0.71
    )'
    0.69
    Act Density 0.012%

    No Known Activations