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

    Neuronpedia

    INDEX
    Explanations

    references to hardware components and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ainfi
    -1.23
     myſelf
    -1.17
    AsUp
    -1.16
     propOrder
    -1.15
     feroit
    -1.14
     auroit
    -1.14
     Könige
    -1.13
     leſs
    -1.13
     étoient
    -1.11
     pouvoit
    -1.10
    POSITIVE LOGITS
     hardware
    0.85
     "
    0.79
    ↵
    0.77
    <eos>
    0.75
     $
    0.72
     «
    0.72
     circuit
    0.71
    ↵↵
    0.71
     “
    0.71
     (
    0.70
    Act Density 0.086%

    No Known Activations