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

    Neuronpedia

    INDEX
    Explanations

    phrases related to requests and conditions in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Exiting
    -0.15
    adi
    -0.14
    Ưá»
    -0.14
    beer
    -0.14
    éīĦéģĵ
    -0.14
    bench
    -0.14
    ToJson
    -0.14
    attice
    -0.13
     Esk
    -0.13
     Desk
    -0.13
    POSITIVE LOGITS
    ãĥ¬ãĥ¼
    0.15
     ìĶ¨
    0.15
    reek
    0.14
    ipse
    0.14
     zoekt
    0.14
     Ph
    0.14
    isure
    0.14
     bets
    0.14
    hf
    0.14
    undi
    0.14
    Act Density 0.432%

    No Known Activations