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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linger
    -0.16
    ÙĪارÙĩ
    -0.15
     Daughter
    -0.14
    ÄIJT
    -0.13
    ÑĢÑĮ
    -0.13
    ault
    -0.13
     oran
    -0.13
     delim
    -0.13
     Welch
    -0.13
    вÑĸлÑĮ
    -0.13
    POSITIVE LOGITS
     was
    0.28
     first
    0.23
    first
    0.20
    was
    0.19
    .first
    0.18
     бÑĭл
    0.18
     byÅĤo
    0.18
     бÑĭло
    0.17
     byÅĤ
    0.17
     était
    0.17
    Act Density 0.045%

    No Known Activations