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

    Neuronpedia

    INDEX
    Explanations

    image captions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of image captions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolog
    -0.73
    ĪĴ
    -0.72
    Magikarp
    -0.71
    nesia
    -0.70
     soda
    -0.66
    atos
    -0.65
     sed
    -0.63
     dro
    -0.61
     clutch
    -0.59
    jer
    -0.59
    POSITIVE LOGITS
     Scenes
    0.81
     IMAGES
    0.80
    acters
    0.79
     Photograph
    0.72
     Provided
    0.71
     Misty
    0.71
     MARK
    0.70
    aceutical
    0.69
     ï
    0.69
     Fiona
    0.68
    Act Density 0.007%

    No Known Activations