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

    Neuronpedia

    INDEX
    Explanations

    initialisms related to organizations or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to social surveys and related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.80
    ning
    -0.72
    ously
    -0.66
    butt
    -0.65
    hood
    -0.63
    ered
    -0.62
    ffen
    -0.61
    ries
    -0.61
    ston
    -0.61
    zzle
    -0.61
    POSITIVE LOGITS
    ullivan
    1.25
    ettings
    1.22
    ocial
    1.19
    erver
    1.12
    ession
    1.10
    ESSION
    1.10
    ometimes
    1.09
    YS
    1.08
    CRIP
    1.07
    nyder
    1.06
    Act Density 0.093%

    No Known Activations