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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a need for citation or verification of information

    oai_token-act-pair · gpt-3.5-turbo

    references or citations indicating a need for further information or validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    profits
    -0.68
     runaway
    -0.66
     cabinets
    -0.63
     condos
    -0.62
     thrott
    -0.61
     racks
    -0.61
     scrim
    -0.60
     scenery
    -0.59
     carts
    -0.58
     presided
    -0.58
    POSITIVE LOGITS
    ]
    1.03
    ])
    0.98
    ]).
    0.98
    ]:
    0.96
     ]
    0.94
    ]),
    0.93
    ]"
    0.92
    ].
    0.89
    }.
    0.89
    çīĪ
    0.88
    Act Density 0.017%

    No Known Activations