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

    Neuronpedia

    INDEX
    Explanations

    references to numbered references within text

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hog
    -0.84
    cies
    -0.75
    cius
    -0.73
     pen
    -0.72
    */(
    -0.69
    NetMessage
    -0.69
    lane
    -0.67
    aturday
    -0.64
     cul
    -0.63
     este
    -0.63
    POSITIVE LOGITS
    ]
    1.07
    ].
    0.94
    ]).
    0.91
    ]"
    0.89
    ][
    0.87
     ]
    0.87
    ]:
    0.82
     ].
    0.82
    ])
    0.82
    ]'
    0.81
    Act Density 0.042%

    No Known Activations