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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or concepts, particularly focused on descriptions of entities and their qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gree
    -0.17
    339
    -0.15
     Hin
    -0.14
    ackage
    -0.14
    Visibility
    -0.14
    orman
    -0.14
    idge
    -0.13
    lie
    -0.13
    alis
    -0.13
    μÏĨ
    -0.13
    POSITIVE LOGITS
    nech
    0.18
    acus
    0.15
    /layouts
    0.15
    grav
    0.14
    ä½³
    0.14
     typical
    0.14
    _nullable
    0.14
    pare
    0.14
     Levy
    0.14
    logen
    0.14
    Act Density 0.125%

    No Known Activations