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

    Neuronpedia

    INDEX
    Explanations

    medical or technological advancements

    oai_token-act-pair · gpt-3.5-turbo

    words indicating advancements or recommendations in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SIZE
    -0.75
     transporter
    -0.66
    mie
    -0.65
    ··
    -0.64
    WOOD
    -0.63
    master
    -0.62
    cules
    -0.61
     garage
    -0.61
     ownership
    -0.59
    mates
    -0.58
    POSITIVE LOGITS
    anced
    1.27
    ocate
    1.22
    ancing
    1.18
    ices
    1.14
    ances
    1.09
    iced
    1.08
    iral
    1.06
    ocated
    1.04
    ocation
    1.01
    ise
    1.01
    Act Density 0.026%

    No Known Activations