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

    Neuronpedia

    INDEX
    Explanations

    phrases describing relationships or interactions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arch
    -0.64
    OV
    -0.63
    zona
    -0.54
     TBA
    -0.54
    addafi
    -0.54
    antly
    -0.53
    hare
    -0.52
    hoff
    -0.52
    apolis
    -0.52
    bucks
    -0.52
    POSITIVE LOGITS
     which
    2.50
    which
    2.03
     Which
    1.79
     whom
    1.65
    Which
    1.62
     whose
    1.46
     whence
    1.44
     wherein
    1.31
    whose
    1.22
     whereby
    1.12
    Act Density 0.909%

    No Known Activations