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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "com" in various contexts, likely related to communication or community themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    p
    -0.26
    pus
    -0.26
    pic
    -0.24
    pie
    -0.23
    pit
    -0.23
    pch
    -0.22
    pics
    -0.21
    ped
    -0.21
    ply
    -0.20
    pd
    -0.20
    POSITIVE LOGITS
    posites
    0.23
    posit
    0.22
    rade
    0.22
    pon
    0.20
    templ
    0.18
    posure
    0.18
    ical
    0.18
    templates
    0.17
    iser
    0.17
    plit
    0.17
    Act Density 0.011%

    No Known Activations