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

    Neuronpedia

    INDEX
    Explanations

    text related to written documents, such as papers, reports, and assessments

    oai_token-act-pair · gpt-3.5-turbo

    references to research papers and academic assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meanwhile
    -0.61
     Originally
    -0.57
     brakes
    -0.55
     owes
    -0.55
     veget
    -0.54
     greeted
    -0.53
     reverted
    -0.53
    tan
    -0.53
    oret
    -0.52
     awa
    -0.52
    POSITIVE LOGITS
    .).
    0.91
    )).
    0.86
    ]).
    0.79
    ).
    0.75
    }.
    0.73
    ]."
    0.73
    ].
    0.70
    ãĤ´ãĥ³
    0.66
    >.
    0.64
     ).
    0.64
    Act Density 2.182%

    No Known Activations