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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "com" appearing with varying levels of significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    p
    -0.25
    pic
    -0.24
    pics
    -0.21
    ped
    -0.21
    pressions
    -0.20
    pie
    -0.20
    pression
    -0.20
    py
    -0.20
    pas
    -0.20
    pet
    -0.19
    POSITIVE LOGITS
    ún
    0.19
    PAD
    0.18
    ings
    0.18
     com
    0.17
    rade
    0.17
    posites
    0.17
    pton
    0.16
    etary
    0.16
     ass
    0.15
    fty
    0.15
    Act Density 0.011%

    No Known Activations