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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or lack of confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ua
    -0.22
    oud
    -0.17
    ascar
    -0.17
    allon
    -0.16
    RAY
    -0.16
    udas
    -0.16
    /Dk
    -0.15
    راÙĨ
    -0.15
    enco
    -0.15
    hazi
    -0.15
    POSITIVE LOGITS
     Hut
    0.17
     proven
    0.15
    iselect
    0.15
    pedia
    0.15
    663
    0.14
    HCI
    0.14
    lÃŃ
    0.14
    ÄŁit
    0.14
    InstanceOf
    0.14
     Humb
    0.13
    Act Density 0.009%

    No Known Activations