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

    Neuronpedia

    INDEX
    Explanations

    specific references to particular items or elements

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific item or concept indicated by the word "particular"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDS
    -0.80
    lyn
    -0.70
    OST
    -0.69
    ÅĤ
    -0.68
    bane
    -0.68
    IR
    -0.66
    glass
    -0.66
    USD
    -0.66
    board
    -0.65
    ORTS
    -0.65
    POSITIVE LOGITS
    ties
    0.99
    ities
    0.93
     embodiments
    0.84
     identifiable
    0.82
    iates
    0.82
     kinds
    0.81
    wcs
    0.78
    gradient
    0.77
    ised
    0.77
    abulary
    0.75
    Act Density 0.016%

    No Known Activations