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

    Neuronpedia

    INDEX
    Explanations

    the word "which" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pageContext
    -0.54
     Aman
    -0.53
    ällor
    -0.53
     нет
    -0.52
     EnglishChoose
    -0.51
    ografija
    -0.50
    taient
    -0.50
     goûts
    -0.49
     Careful
    -0.49
     хвати
    -0.48
    POSITIVE LOGITS
     GenerationType
    0.86
    ynchronously
    0.70
    phrag
    0.66
     CanadaChoose
    0.66
     تضيفلها
    0.65
    withIdentifier
    0.65
     cref
    0.64
    getDoctrine
    0.63
    VersionUID
    0.62
    ]**
    0.61
    Act Density 0.019%

    No Known Activations