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

    Neuronpedia

    INDEX
    Explanations

    expressions relating to time and duration in years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hir
    -0.16
    uff
    -0.15
    stell
    -0.15
    lotte
    -0.15
    ictions
    -0.15
    stor
    -0.14
    studio
    -0.14
    ullet
    -0.14
    ège
    -0.14
    adium
    -0.14
    POSITIVE LOGITS
    ften
    0.19
    erton
    0.17
    -License
    0.17
     CWE
    0.15
    appen
    0.15
    ContentLoaded
    0.15
    702
    0.15
    dale
    0.14
    chin
    0.14
     BaÄŁ
    0.14
    Act Density 0.005%

    No Known Activations