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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time or sequences of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hec
    -0.16
    rait
    -0.15
    STRUCTOR
    -0.15
    ìĦĿ
    -0.15
    #w
    -0.14
    erken
    -0.14
    à¹ģà¸Ĺà¸Ļ
    -0.14
    Ø´ÙĬ
    -0.14
    .jp
    -0.14
    ãĥ©ãĥ¼
    -0.14
    POSITIVE LOGITS
     being
    0.33
    wards
    0.26
    ward
    0.26
    thought
    0.25
    no
    0.24
    words
    0.24
     Being
    0.23
     having
    0.22
    noon
    0.21
    Being
    0.21
    Act Density 0.090%

    No Known Activations