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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the severity or impact of a situation or event

    oai_token-act-pair · gpt-3.5-turbo

    themes related to serious societal issues or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jasper
    -0.65
    Natural
    -0.65
     Innocent
    -0.60
     Juven
    -0.58
     Athletic
    -0.58
     Background
    -0.56
     Weston
    -0.56
     Adren
    -0.54
     Photographer
    -0.54
     Tunnel
    -0.54
    POSITIVE LOGITS
    [/
    1.56
    %"
    1.47
    ]"
    1.45
    "—
    1.43
    "?
    1.35
    »
    1.35
    ''
    1.29
    ãĢı
    1.29
    "
    1.27
    \"
    1.25
    Act Density 0.947%

    No Known Activations