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

    Neuronpedia

    INDEX
    Explanations

    references to editing or editing-related activities

    oai_token-act-pair · gpt-3.5-turbo

    sections that denote edits or modifications in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    userc
    -0.79
    gren
    -0.75
    etsy
    -0.73
    milo
    -0.71
    hene
    -0.71
    mable
    -0.67
    imens
    -0.67
    iru
    -0.67
    ocket
    -0.66
    ongyang
    -0.64
    POSITIVE LOGITS
     edit
    0.86
     Blizzard
    0.73
     Wikipedia
    0.70
    ...]
    0.69
    ][
    0.69
    ].
    0.68
    âĶĢâĶĢ
    0.68
    ]).
    0.66
     ]
    0.64
    ËĪ
    0.64
    Act Density 0.019%

    No Known Activations