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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the letter "M"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the letter "M" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evid
    -0.65
     Mith
    -0.62
     Samar
    -0.62
     Hath
    -0.61
     Jama
    -0.61
     christ
    -0.60
     Subtle
    -0.60
     Dispatch
    -0.59
     tallest
    -0.59
     derivative
    -0.59
    POSITIVE LOGITS
    ornings
    1.26
    ISSION
    1.23
    igrant
    1.23
    ention
    1.21
    ovember
    1.21
    antle
    1.18
    insk
    1.17
    aternal
    1.15
    ONEY
    1.14
    aintain
    1.14
    Act Density 0.034%

    No Known Activations