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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making processes and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bu
    -0.15
     gross
    -0.15
    /features
    -0.14
    geben
    -0.14
    onga
    -0.14
     Pend
    -0.14
    üstü
    -0.13
    gross
    -0.13
    ZY
    -0.13
     Gross
    -0.13
    POSITIVE LOGITS
    oload
    0.18
    à¥Ĥद
    0.15
    conde
    0.15
    OMP
    0.15
    xAE
    0.14
    اÙĬÙĨ
    0.14
    ezier
    0.14
    à¤Ĥश
    0.14
    DEST
    0.13
     DalÅ¡ÃŃ
    0.13
    Act Density 0.438%

    No Known Activations