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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Me" as a standalone word or part of a longer word

    oai_token-act-pair · gpt-3.5-turbo

    the name "Me" or its variations, indicating a focus on a specific individual or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pole
    -0.72
    paralle
    -0.70
    DragonMagazine
    -0.68
     corners
    -0.68
     legality
    -0.68
     totality
    -0.67
    */(
    -0.65
    çĶŁ
    -0.64
    ordinate
    -0.64
    edged
    -0.62
    POSITIVE LOGITS
    zzo
    1.20
    asuring
    1.15
    cca
    1.11
    asured
    1.10
    asure
    1.09
    asures
    1.06
    adow
    1.02
    adows
    0.98
    aning
    0.97
    gan
    0.94
    Act Density 0.021%

    No Known Activations