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

    Neuronpedia

    INDEX
    Explanations

    captions related to news articles or photographs

    oai_token-act-pair · gpt-3.5-turbo

    instances of captions associated with images or photos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.87
    axis
    -0.69
    abol
    -0.68
     endeavour
    -0.68
     conversion
    -0.67
    gger
    -0.66
    bye
    -0.66
    cule
    -0.64
    road
    -0.63
     debate
    -0.63
    POSITIVE LOGITS
    uments
    0.88
     Thumbnails
    0.88
     Caption
    0.85
     ï
    0.80
     Close
    0.79
     Execution
    0.79
    actionDate
    0.78
     Photographer
    0.74
     Loading
    0.72
    ainers
    0.71
    Act Density 0.007%

    No Known Activations