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

    Neuronpedia

    INDEX
    Explanations

    actions or tasks being performed in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    });
    -0.75
    },
    -0.74
    })
    -0.68
    enei
    -0.65
    >,
    -0.65
     })
    -0.62
    >)
    -0.62
    >[
    -0.61
    ]).
    -0.60
    .?
    -0.60
    POSITIVE LOGITS
     chiefly
    1.01
     mainly
    1.00
     primarily
    1.00
     principally
    0.98
     because
    0.97
     everywhere
    0.95
     whenever
    0.88
     irrespective
    0.85
     intermitt
    0.85
     sparing
    0.84
    Act Density 0.651%

    No Known Activations