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

    Neuronpedia

    INDEX
    Explanations

    numerical values with surrounding punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and references to statistics or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agra
    -0.66
    gone
    -0.64
    NetMessage
    -0.62
    cius
    -0.61
     hog
    -0.60
     este
    -0.59
    yre
    -0.58
     pressures
    -0.58
    pass
    -0.58
    morrow
    -0.57
    POSITIVE LOGITS
    ]
    1.10
    ],[
    1.03
    ]).
    0.99
    ]),
    0.97
    ][
    0.96
    ])
    0.96
    ].
    0.92
    ]"
    0.89
    ]);
    0.84
    ]'
    0.82
    Act Density 0.035%

    No Known Activations