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

    Neuronpedia

    INDEX
    Explanations

    subjects and their actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸Ģæł·
    -0.14
    egt
    -0.14
    /from
    -0.13
    arger
    -0.13
    precated
    -0.13
    (for
    -0.12
     ebenfalls
    -0.12
     unreliable
    -0.12
    inger
    -0.12
    erguson
    -0.12
    POSITIVE LOGITS
     then
    0.40
     also
    0.38
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.36
     therefore
    0.35
    also
    0.34
     ayrıca
    0.32
     thus
    0.31
    then
    0.30
     ÑĤакже
    0.29
    Also
    0.29
    Act Density 0.688%

    No Known Activations