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

    Neuronpedia

    INDEX
    Explanations

    references to names and naming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istes
    -0.17
    ters
    -0.17
    tes
    -0.15
    ting
    -0.15
    inae
    -0.15
    ors
    -0.14
    tings
    -0.14
    itz
    -0.14
    arily
    -0.14
    nds
    -0.14
    POSITIVE LOGITS
    ake
    0.24
    plate
    0.23
    plates
    0.20
    åı¤å±ĭ
    0.19
    less
    0.18
    AKE
    0.18
    ValueCollection
    0.17
    perature
    0.16
    -brand
    0.16
    adesh
    0.16
    Act Density 0.068%

    No Known Activations