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

    Neuronpedia

    INDEX
    Explanations

    indicators of potential events or actions related to transitions or changes in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffer
    -0.17
    ules
    -0.16
     oku
    -0.15
    ULE
    -0.15
    ULER
    -0.15
    ulers
    -0.15
    945
    -0.15
     konkrét
    -0.15
    rico
    -0.15
    olini
    -0.15
    POSITIVE LOGITS
     elsewhere
    0.18
    Opaque
    0.16
    uesta
    0.15
    reature
    0.15
    li
    0.14
    bare
    0.14
     Clan
    0.14
     softer
    0.14
    iar
    0.14
    adden
    0.14
    Act Density 0.002%

    No Known Activations