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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "looked."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rn
    -0.16
     Po
    -0.15
    utto
    -0.14
    atti
    -0.14
     Mund
    -0.14
    ibo
    -0.14
    ibox
    -0.14
    .ham
    -0.14
     late
    -0.14
    ereum
    -0.14
    POSITIVE LOGITS
     è»
    0.17
    ovable
    0.15
    olph
    0.14
    iazza
    0.14
    çķ
    0.14
    ÑĩаÑģ
    0.14
    INARY
    0.13
     пÑĢоÑģ
    0.13
    scenario
    0.13
    ackson
    0.13
    Act Density 0.015%

    No Known Activations