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

    Neuronpedia

    INDEX
    Explanations

    phrases related to visual elements and descriptions in texts

    oai_token-act-pair · gpt-3.5-turbo

    elements related to narrative themes and storytelling techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carney
    -0.69
     Canaver
    -0.62
     )]
    -0.60
    */(
    -0.57
     reins
    -0.56
    bnb
    -0.54
    cipled
    -0.53
     Sloan
    -0.53
     lawy
    -0.53
     interviewed
    -0.52
    POSITIVE LOGITS
    odiac
    0.63
     deities
    0.61
     landmarks
    0.60
     ..."
    0.58
     UFOs
    0.58
     deity
    0.58
    ".[
    0.57
     lifestyles
    0.56
    inals
    0.56
    ,...
    0.56
    Act Density 1.154%

    No Known Activations