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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future risks and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olio
    -0.15
    rm
    -0.15
    زÙĩ
    -0.15
    urovision
    -0.14
    каз
    -0.14
    orest
    -0.14
    /Dk
    -0.14
    inspace
    -0.14
    ±
    -0.14
    bai
    -0.14
    POSITIVE LOGITS
    ing
    0.18
    ì²´
    0.15
    heet
    0.15
    amus
    0.14
    yen
    0.14
    ively
    0.13
     Seznam
    0.13
     rost
    0.13
     pás
    0.13
    ItemClick
    0.13
    Act Density 0.006%

    No Known Activations