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

    Neuronpedia

    INDEX
    Explanations

    proper names (names of people, places) within a large context of text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.79
    ollo
    -0.76
    ħĭ
    -0.72
     Sparrow
    -0.70
    urst
    -0.66
    ĩ
    -0.66
    avorite
    -0.63
    OWER
    -0.61
     Acid
    -0.61
    ij士
    -0.60
    POSITIVE LOGITS
    dict
    1.25
    million
    1.04
    ifying
    1.03
    tex
    1.03
    onica
    1.03
    gence
    1.02
    ifiable
    1.01
    bal
    1.00
    gent
    1.00
    gil
    0.98
    Act Density 0.071%

    No Known Activations