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

    Neuronpedia

    INDEX
    Explanations

    references to keys and their related functions in the context of technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dcc
    -0.18
    asar
    -0.15
    amak
    -0.15
     OnTrigger
    -0.15
    ois
    -0.15
    ̧
    -0.15
    oom
    -0.14
    iers
    -0.14
     excess
    -0.14
     Advantage
    -0.13
    POSITIVE LOGITS
    keys
    0.17
    urette
    0.16
     keys
    0.15
    _LA
    0.14
    .logic
    0.14
    /key
    0.14
     Hag
    0.14
    agner
    0.14
    ös
    0.14
     proxy
    0.13
    Act Density 0.019%

    No Known Activations