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

    Neuronpedia

    INDEX
    Explanations

    information related to conducting research and gathering data

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "research" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cakes
    -0.70
     Leilan
    -0.67
    zzi
    -0.66
     Nept
    -0.66
     rapp
    -0.64
    twitch
    -0.61
     dism
    -0.60
     Alive
    -0.59
     mortals
    -0.58
     Lann
    -0.57
    POSITIVE LOGITS
    sonian
    0.84
    Ô
    0.81
    çīĪ
    0.78
     researching
    0.75
    ively
    0.75
     psychology
    0.74
    research
    0.72
     psychologist
    0.71
     resear
    0.70
    iably
    0.69
    Act Density 0.034%

    No Known Activations