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

    Neuronpedia

    INDEX
    Explanations

    email addresses and related metadata

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of email headers and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.72
    åĤ
    -0.71
     tremend
    -0.70
    inventoryQuantity
    -0.69
    aband
    -0.66
     veter
    -0.65
    acity
    -0.65
    ior
    -0.65
    ¿½
    -0.64
    Ļ½
    -0.63
    POSITIVE LOGITS
     CTR
    1.01
     Franç
    0.79
     Editorial
    0.76
     john
    0.66
     SPACE
    0.65
     PubMed
    0.65
     Random
    0.65
     Mens
    0.64
     BOOK
    0.64
     NEWS
    0.64
    Act Density 0.073%

    No Known Activations