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

    Neuronpedia

    INDEX
    Explanations

    sentences transitioning to a new topic or section in a text

    oai_token-act-pair · gpt-3.5-turbo

    box office revenue figures of movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.30
    !".
    -0.27
    )."
    -0.26
     ."
    -0.26
     [...]
    -0.25
    ]."
    -0.23
    ".
    -0.23
    ".[
    -0.23
    ?".
    -0.23
    .).
    -0.23
    POSITIVE LOGITS
    esides
    0.21
    atform
    0.21
    ivot
    0.20
    roups
    0.19
    olit
    0.18
    raltar
    0.17
    onents
    0.17
    ouple
    0.17
    rina
    0.17
    argo
    0.16
    Act Density 6.435%

    No Known Activations