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

    Neuronpedia

    INDEX
    Explanations

    the word "which" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     them
    -0.62
    them
    -0.56
     her
    -0.48
    endregion
    -0.46
    gant
    -0.44
    χη
    -0.44
    overe
    -0.43
    includegraphics
    -0.43
     ними
    -0.43
    getRoot
    -0.43
    POSITIVE LOGITS
    ArrowToggle
    0.96
    Демографія
    0.77
    الحياه
    0.75
     calendriers
    0.72
    Which
    0.71
     Which
    0.70
     يتيمه
    0.69
     ويكيپيديا
    0.69
    DockStyle
    0.69
    ✷
    0.68
    Act Density 0.153%

    No Known Activations