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

    Neuronpedia

    INDEX
    Explanations

    mentions of different human populations or communities in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to communities and their social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasis
    -0.68
    --+
    -0.66
    Attempts
    -0.65
    ty
    -0.60
    Delivery
    -0.60
    thumbnails
    -0.60
    ties
    -0.60
    Accessory
    -0.59
    neau
    -0.58
    nit
    -0.58
    POSITIVE LOGITS
    chool
    1.28
    hare
    1.17
    pace
    1.13
    mith
    1.11
    poons
    1.09
    ystem
    1.05
    wana
    1.03
    cale
    1.03
    ourcing
    1.00
    hips
    0.99
    Act Density 0.215%

    No Known Activations