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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user instructions and capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дем
    -0.16
    imens
    -0.15
    ê±´
    -0.15
    ocrates
    -0.14
    apon
    -0.14
    ä¹ĥ
    -0.14
    оÑĢов
    -0.14
    kJ
    -0.14
    ÏĦÎŃ
    -0.14
    ιÏĥÏĦο
    -0.14
    POSITIVE LOGITS
     can
    0.21
    can
    0.16
    oyer
    0.16
    'll
    0.14
    LOY
    0.14
     might
    0.14
    909
    0.14
    enton
    0.14
     get
    0.14
     PAY
    0.14
    Act Density 0.114%

    No Known Activations