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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases that express inquiry or seek clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anything
    -0.17
    icios
    -0.15
    mente
    -0.15
    ric
    -0.15
    loff
    -0.15
    unate
    -0.14
    oris
    -0.14
    (){}↵↵
    -0.14
    ç±
    -0.13
    educt
    -0.13
    POSITIVE LOGITS
     else
    0.28
    soever
    0.26
     happens
    0.24
     happened
    0.23
    ToDo
    0.22
    æł·çļĦ
    0.20
    /how
    0.19
    abouts
    0.19
     happening
    0.19
    .cd
    0.18
    Act Density 0.153%

    No Known Activations