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

    Neuronpedia

    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hog
    -0.71
    sels
    -0.67
     seams
    -0.63
     Profession
    -0.62
    userc
    -0.61
     lucrative
    -0.60
     asses
    -0.60
    conservancy
    -0.60
     miraculous
    -0.60
     lobb
    -0.60
    POSITIVE LOGITS
    ]
    1.27
    ]"
    1.21
    ][
    1.12
    ]).
    1.09
    ].
    1.05
    ])
    1.02
    ]:
    1.01
    ?]
    0.99
    ]."
    0.98
    %]
    0.96
    Act Density 0.050%

    No Known Activations