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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific objects or actions, such as customer, municipal airport, Facebook, dream, high denomination Euros, recipe, medical MRI, pink ribbons, Kurdish militant, fallen ceiling, bakery, power investments, human hair, electric charge, left signals, pedestrian conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to customer-related concepts and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    partisan
    -0.68
    arcity
    -0.60
     Adin
    -0.57
    govtrack
    -0.56
    intend
    -0.56
     Founders
    -0.56
    isode
    -0.54
    ĺħ
    -0.53
    encers
    -0.53
     Fiscal
    -0.53
    POSITIVE LOGITS
    natureconservancy
    0.60
     guiActiveUn
    0.55
    VERTISEMENT
    0.54
     symbol
    0.54
     prey
    0.53
    Joined
    0.52
     crou
    0.52
     dye
    0.51
     bubbles
    0.51
     pee
    0.51
    Act Density 1.744%

    No Known Activations