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

    Neuronpedia

    INDEX
    Explanations

    questions and hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    interrogative words and phrases that initiate questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     semin
    -0.61
    yrim
    -0.61
     silenced
    -0.61
     Interior
    -0.61
     Janeiro
    -0.60
     Pione
    -0.60
     Greenwood
    -0.60
    ridges
    -0.59
     foremost
    -0.58
     installations
    -0.57
    POSITIVE LOGITS
    lihood
    0.92
    -
    0.84
    %-
    0.79
    -$
    0.79
    '-
    0.74
    advertising
    0.74
    -'
    0.73
    ciation
    0.72
     clause
    0.70
    "-
    0.69
    Act Density 0.258%

    No Known Activations