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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time or sequences of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umes
    -0.15
    æ¡£
    -0.14
    ÑĢажд
    -0.14
    ål
    -0.14
    ÑĢиÑģ
    -0.14
    appen
    -0.13
    ands
    -0.13
     behalf
    -0.13
    ê¹
    -0.13
    aries
    -0.13
    POSITIVE LOGITS
    noon
    0.23
    ward
    0.19
     initially
    0.15
    alet
    0.15
    agua
    0.14
    WX
    0.14
     GObject
    0.14
    fin
    0.14
    words
    0.14
     arac
    0.14
    Act Density 0.056%

    No Known Activations