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

    Neuronpedia

    INDEX
    Explanations

    important statements and summaries about the narrative or argument presented

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -cur
    -0.16
    andom
    -0.15
    bane
    -0.15
     Wein
    -0.15
    mrt
    -0.15
    isters
    -0.14
    warts
    -0.14
    oux
    -0.14
     Pell
    -0.14
    unei
    -0.14
    POSITIVE LOGITS
    hest
    0.16
    vertiser
    0.15
    .mozilla
    0.15
    ulta
    0.15
    å°Ĭ
    0.14
    andi
    0.14
    ê·Ģ
    0.14
    verter
    0.14
    å¿
    0.13
    hsi
    0.13
    Act Density 0.530%

    No Known Activations