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

    Neuronpedia

    INDEX
    Explanations

    names and titles of individuals in a context of appointments or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dyby
    -0.17
    ниÑĤ
    -0.14
    indre
    -0.14
    stub
    -0.13
    ãĥ³ãĥĦ
    -0.13
     (*.
    -0.12
    inus
    -0.12
    ãĥ©ãĤ¤ãĥĪ
    -0.12
    quis
    -0.12
    lsruhe
    -0.12
    POSITIVE LOGITS
     will
    0.30
     joins
    0.29
     replaces
    0.27
     most
    0.23
     previously
    0.23
     succeeds
    0.23
     returns
    0.23
    will
    0.23
     plans
    0.23
     becomes
    0.21
    Act Density 0.086%

    No Known Activations