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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or questioning knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uter
    -0.15
    رÙĪ
    -0.15
    ÑĢик
    -0.14
    asley
    -0.14
    inar
    -0.14
    asad
    -0.13
    borough
    -0.13
    ickets
    -0.13
    orra
    -0.13
    sik
    -0.13
    POSITIVE LOGITS
     whether
    0.17
     anymore
    0.16
    égor
    0.16
    uze
    0.16
     Whether
    0.14
    aise
    0.14
    west
    0.14
    KeyPressed
    0.14
    çľł
    0.14
    whether
    0.14
    Act Density 0.043%

    No Known Activations