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

    Neuronpedia

    INDEX
    Explanations

    important or significant events or entities

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate significance or scale, particularly related to events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bots
    -0.83
     Machines
    -0.77
    abilities
    -0.72
    chairs
    -0.71
    utics
    -0.71
    always
    -0.70
    Gameplay
    -0.69
    alysis
    -0.69
    anners
    -0.69
    clips
    -0.69
    POSITIVE LOGITS
     installment
    1.20
     hurdle
    1.17
     iteration
    1.16
     foray
    1.15
     outing
    1.13
     piece
    1.08
     contender
    1.07
     incarnation
    1.04
     avenue
    1.01
     manifestation
    1.01
    Act Density 0.256%

    No Known Activations