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

    Neuronpedia

    INDEX
    Explanations

    instances of articles indicating new or significant developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    567
    -0.16
    -widgets
    -0.15
    uden
    -0.15
    303
    -0.14
    446
    -0.14
     Favorite
    -0.14
    ooter
    -0.13
    à¸ļà¸Ĺ
    -0.13
    наÑĤ
    -0.13
    ENUM
    -0.13
    POSITIVE LOGITS
     alike
    0.20
     slightest
    0.17
     stuff
    0.15
    like
    0.15
     certain
    0.15
    çĬ¶
    0.15
     scenery
    0.15
    asma
    0.14
    yan
    0.14
     biggest
    0.14
    Act Density 0.465%

    No Known Activations