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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is participating in an activity or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of participation or involvement in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gnu
    -0.63
    cyclopedia
    -0.60
     millenn
    -0.58
    onut
    -0.58
     carrots
    -0.57
    bey
    -0.57
    pe
    -0.56
    sav
    -0.56
    ggles
    -0.55
    ilies
    -0.54
    POSITIVE LOGITS
    iers
    0.83
     in
    0.74
     captcha
    0.73
    atta
    0.73
    Admin
    0.65
     therein
    0.63
     onstage
    0.63
    akers
    0.61
    iership
    0.61
     guiActiveUn
    0.60
    Act Density 0.018%

    No Known Activations