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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing a comprehensive or thorough understanding

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to various contexts of "picture" or "depiction" of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -0.81
    iant
    -0.77
    ule
    -0.77
    ajor
    -0.77
    onge
    -0.75
    ugs
    -0.73
    augh
    -0.70
    unts
    -0.70
    iencies
    -0.69
    aughs
    -0.69
    POSITIVE LOGITS
    picture
    1.04
     picture
    0.93
     mosaic
    0.84
     Picture
    0.82
     depicting
    0.80
     mosa
    0.78
     gallery
    0.77
    >>>>>>>>
    0.74
     portrait
    0.74
     painted
    0.72
    Act Density 0.013%

    No Known Activations