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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nut
    -0.17
     p
    -0.16
    -0.16
     amb
    -0.16
     T
    -0.16
    Âł
    -0.16
     mid
    -0.16
    án
    -0.16
    amente
    -0.15
     half
    -0.15
    POSITIVE LOGITS
    .EventQueue
    0.17
    buie
    0.17
    adow
    0.16
    ارج
    0.16
    egative
    0.16
    radu
    0.16
    agedList
    0.16
    pus
    0.16
     пÑĥ
    0.15
    isclosed
    0.15
    Act Density 0.001%

    No Known Activations