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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning the efficacy or value of actions and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apes
    -0.15
    adr
    -0.15
    à¹ĥà¸Ī
    -0.14
    ALTH
    -0.14
    Ñģол
    -0.14
    ouncer
    -0.14
    incinn
    -0.14
    igure
    -0.14
    outh
    -0.13
    æ£
    -0.13
    POSITIVE LOGITS
    affen
    0.17
    Įĵ
    0.15
     Miche
    0.15
     Benson
    0.15
     Bry
    0.15
     Michaels
    0.14
    ós
    0.14
    olo
    0.14
     Lup
    0.14
     nominated
    0.14
    Act Density 0.129%

    No Known Activations