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

    Neuronpedia

    INDEX
    Explanations

    strings of text related to physical objects or structures

    oai_token-act-pair · gpt-3.5-turbo

    physical objects and materials described in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reservations
    -0.77
     prospects
    -0.68
     demographics
    -0.67
     finances
    -0.66
     Taxes
    -0.64
     resurg
    -0.63
     talents
    -0.62
     lifestyles
    -0.62
     priorities
    -0.61
     angst
    -0.61
    POSITIVE LOGITS
     shaped
    1.07
    shaped
    0.98
    worm
    0.91
     protr
    0.82
     consisting
    0.82
     resembling
    0.81
    hole
    0.80
    like
    0.79
     surrounded
    0.79
     containing
    0.79
    Act Density 0.339%

    No Known Activations