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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and emphasizes their frequency in connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gl
    -0.16
    im
    -0.15
    -0.15
    ac
    -0.15
    cape
    -0.15
    lie
    -0.15
     je
    -0.14
    idon
    -0.14
    mer
    -0.14
    ahr
    -0.14
    POSITIVE LOGITS
    оÑĢод
    0.17
    edList
    0.16
     Armour
    0.16
    centage
    0.16
    èªĮ
    0.15
    odelist
    0.15
    AccessType
    0.15
     Paging
    0.15
    мÑı
    0.15
    eut
    0.14
    Act Density 0.154%

    No Known Activations