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

    Neuronpedia

    INDEX
    Explanations

    references to sponsorship in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arr
    -0.17
    antry
    -0.15
     knife
    -0.15
    flip
    -0.15
     flip
    -0.14
    gear
    -0.14
    heimer
    -0.14
    anim
    -0.14
     Flip
    -0.14
    olar
    -0.14
    POSITIVE LOGITS
    HWND
    0.14
    atto
    0.14
    оÑĢон
    0.14
    ãĥ³ãĥģ
    0.14
    jem
    0.14
     Reb
    0.13
     पà¤ķ
    0.13
     Geld
    0.13
    AKE
    0.13
    ë´ī
    0.13
    Act Density 0.031%

    No Known Activations