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

    Neuronpedia

    INDEX
    Explanations

    the word "Met" in various contexts, indicating a strong focus on discussions or references to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orz
    -0.18
    ette
    -0.15
    handling
    -0.15
    stoup
    -0.15
    udget
    -0.15
    enco
    -0.15
    иÑĩ
    -0.15
    holders
    -0.14
    anted
    -0.14
    ighter
    -0.14
    POSITIVE LOGITS
    ropolitan
    0.30
    ropolis
    0.29
    tle
    0.28
    abolic
    0.27
    ropol
    0.25
    airie
    0.24
    averse
    0.23
    atars
    0.23
    abol
    0.22
    onym
    0.22
    Act Density 0.014%

    No Known Activations