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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or references related to structure or functionality in contexts like entertainment or history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     displacement
    -0.17
     Morrison
    -0.15
    gewater
    -0.15
    /fixtures
    -0.14
     hell
    -0.14
    KHR
    -0.14
    elsius
    -0.14
     pant
    -0.13
    हर
    -0.13
    ircuit
    -0.13
    POSITIVE LOGITS
    yz
    0.16
    êm
    0.15
    enia
    0.15
    eba
    0.15
    enz
    0.14
     McMahon
    0.14
    itre
    0.14
     tro
    0.14
    tro
    0.14
     Idea
    0.14
    Act Density 0.026%

    No Known Activations