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

    Neuronpedia

    INDEX
    Explanations

    sources of information or external data

    oai_token-act-pair · gpt-3.5-turbo

    references to governance, social issues, and community-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Natural
    -0.73
    ciplinary
    -0.70
    EVA
    -0.65
    SHIP
    -0.61
    uitive
    -0.60
    uilt
    -0.60
    ustomed
    -0.58
    dinand
    -0.57
    ertility
    -0.57
     Weston
    -0.57
    POSITIVE LOGITS
    »
    1.20
    ãĢı
    1.17
    [/
    1.09
    ãĢį
    1.08
    ''
    1.05
    ãĢij
    1.04
    ,''
    1.03
    "—
    0.98
    ]"
    0.97
    \)
    0.96
    Act Density 0.911%

    No Known Activations