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

    Neuronpedia

    INDEX
    Explanations

    the action of initiating or starting something

    oai_token-act-pair · gpt-3.5-turbo

    actions related to the initiation or commencement of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.79
    atu
    -0.71
    olded
    -0.68
    pedia
    -0.68
    pter
    -0.67
    etimes
    -0.66
    CHR
    -0.66
    Appearance
    -0.66
    AIDS
    -0.66
    iste
    -0.66
    POSITIVE LOGITS
     experimenting
    1.31
     researching
    1.14
     accepting
    1.14
     noticing
    1.12
     discussing
    1.12
     distributing
    1.11
     questioning
    1.07
     exploring
    1.06
     assembling
    1.06
     withdrawing
    1.06
    Act Density 0.057%

    No Known Activations