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

    Neuronpedia

    INDEX
    Explanations

    formatting or punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    references to numbered items or sequences in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     )))
    -0.63
     ."
    -0.61
     cooperative
    -0.60
     traject
    -0.59
     dispers
    -0.59
    milo
    -0.59
    Shell
    -0.57
     pressures
    -0.56
     positively
    -0.56
     Ware
    -0.56
    POSITIVE LOGITS
    ],
    1.77
    ]=
    1.77
    ]:
    1.75
    ][
    1.75
    ]-
    1.72
    ].
    1.69
    ]
    1.67
    ]'
    1.64
    ]+
    1.54
    ],"
    1.54
    Act Density 0.072%

    No Known Activations