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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to pride and self-identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UMMY
    -0.18
    abis
    -0.17
    etik
    -0.17
    RIA
    -0.16
    abcdef
    -0.16
    μβ
    -0.16
     ÑħÑĥд
    -0.15
    assi
    -0.15
    /tos
    -0.15
    anggan
    -0.15
    POSITIVE LOGITS
     tro
    0.15
     mish
    0.14
     Tro
    0.14
    atin
    0.14
     Lau
    0.14
    ãĥĥãĥĦ
    0.14
    pha
    0.14
    èĮĤ
    0.14
    aney
    0.14
     Stocks
    0.14
    Act Density 0.003%

    No Known Activations