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

    Neuronpedia

    INDEX
    Explanations

    words related to folding or models that are foldable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asive
    -0.17
    ÐĬ
    -0.16
    erap
    -0.16
    eled
    -0.15
    ÄĽt
    -0.14
    eland
    -0.14
    andler
    -0.14
    assen
    -0.14
    éĿ©
    -0.14
    ples
    -0.14
    POSITIVE LOGITS
    able
    0.20
     Fold
    0.20
    backs
    0.19
     folding
    0.18
    -fold
    0.18
     fold
    0.17
     defaultstate
    0.17
    æĬĺ
    0.17
    fold
    0.16
    ery
    0.15
    Act Density 0.019%

    No Known Activations