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

    Neuronpedia

    INDEX
    Explanations

    references to real-life situations

    oai_token-act-pair · gpt-3.5-turbo

    references to reality or real-life situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.94
    ebook
    -0.75
    berries
    -0.70
     Presbyter
    -0.65
    indal
    -0.65
    ACK
    -0.65
    utions
    -0.65
    bard
    -0.64
     Pavilion
    -0.64
     Include
    -0.62
    POSITIVE LOGITS
    ignment
    1.36
     estate
    1.20
    isation
    1.20
    polit
    1.14
    isable
    1.10
    igning
    1.08
    izations
    1.07
    estate
    1.07
    izable
    1.04
    igned
    1.04
    Act Density 0.032%

    No Known Activations