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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or concepts of importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social responsibility and collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovember
    -0.54
    gew
    -0.50
    weed
    -0.50
     Belg
    -0.47
    Engineers
    -0.47
     Zac
    -0.46
    ————————
    -0.46
    itz
    -0.46
     Collabor
    -0.45
    azz
    -0.44
    POSITIVE LOGITS
    )=(
    0.57
    yang
    0.55
    strous
    0.53
    livious
    0.53
    noxious
    0.53
    ODY
    0.52
     hers
    0.52
    inces
    0.51
    zon
    0.51
    ilogy
    0.50
    Act Density 1.808%

    No Known Activations