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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe various types of forms and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fung
    -0.16
    δά
    -0.14
    unger
    -0.14
     пла
    -0.14
     Higgins
    -0.14
    nish
    -0.14
    ertia
    -0.14
    atur
    -0.14
    erties
    -0.13
    amel
    -0.13
    POSITIVE LOGITS
     Rena
    0.14
    êu
    0.14
     Garn
    0.14
    çesi
    0.14
    ocre
    0.13
    YNC
    0.13
    igo
    0.13
    ijken
    0.13
    imar
    0.13
    utherford
    0.13
    Act Density 0.021%

    No Known Activations