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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express uncertainty or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     misd
    -0.17
    ¼
    -0.15
    .ma
    -0.15
    canf
    -0.15
    ês
    -0.14
    á»ĵi
    -0.14
    交
    -0.14
    ãģ©ãģĨ
    -0.14
    alo
    -0.14
    pert
    -0.14
    POSITIVE LOGITS
    æ¯Ķ
    0.15
     flashed
    0.15
     Hast
    0.14
     Seb
    0.14
     Honest
    0.14
     flash
    0.14
    неÑĤ
    0.14
    -flash
    0.13
    ABEL
    0.13
    çŃĸ
    0.13
    Act Density 0.271%

    No Known Activations