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

    Neuronpedia

    INDEX
    Explanations

    references to laws and regulations related to safety and policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acula
    -0.16
    mani
    -0.15
     اÙĦØŃÙĬ
    -0.15
    954
    -0.14
    MarshalAs
    -0.14
     Seamless
    -0.14
    _Cmd
    -0.14
    GLOBAL
    -0.13
    EdgeInsets
    -0.13
    ader
    -0.13
    POSITIVE LOGITS
    hower
    0.16
    ystems
    0.15
     themselves
    0.15
     Boards
    0.15
    crets
    0.15
     their
    0.15
    avo
    0.14
     passed
    0.14
     systems
    0.14
     residents
    0.14
    Act Density 0.177%

    No Known Activations