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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement or spatial distribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating widespread distribution or presence across various places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliate
    -0.78
    ignt
    -0.72
     Rasmussen
    -0.69
    interstitial
    -0.69
    uca
    -0.68
    TION
    -0.66
    EStream
    -0.66
    ————
    -0.66
    thood
    -0.65
    govtrack
    -0.65
    POSITIVE LOGITS
     room
    1.35
     floor
    1.19
     halls
    1.19
     floors
    1.19
     rooft
    1.19
     globe
    1.17
     shelves
    1.13
     streets
    1.12
     place
    1.11
     entire
    1.08
    Act Density 0.171%

    No Known Activations