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

    Neuronpedia

    INDEX
    Explanations

    specific mention of research study participants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of participants in studies or experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vengeance
    -0.66
     Nept
    -0.64
    FU
    -0.63
    separ
    -0.62
     reforming
    -0.62
    MENT
    -0.60
    flu
    -0.60
    RAY
    -0.60
     pastoral
    -0.59
     thicker
    -0.58
    POSITIVE LOGITS
     Participants
    1.16
     participants
    1.07
     participant
    1.05
     Participant
    0.97
    arnaev
    0.96
     guiActiveUn
    0.95
     attendees
    0.88
    cript
    0.88
     contestants
    0.87
    particip
    0.87
    Act Density 0.010%

    No Known Activations