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

    Neuronpedia

    INDEX
    Explanations

    terms related to administrative or legal actions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OfWork
    -0.15
    gio
    -0.15
    ·»
    -0.14
    \CMS
    -0.14
    ilibrium
    -0.14
    dit
    -0.14
    igaret
    -0.14
     Apostle
    -0.13
    dera
    -0.13
     cac
    -0.13
    POSITIVE LOGITS
    fur
    0.15
    anka
    0.15
    arity
    0.15
    wap
    0.15
    ubar
    0.14
    /Internal
    0.14
    oupper
    0.14
     WATCH
    0.14
     TOUCH
    0.13
     Nest
    0.13
    Act Density 0.012%

    No Known Activations