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

    Neuronpedia

    INDEX
    Explanations

    inquiries related to curiosity about data manipulation or exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Oster
    -0.78
    Alfredo
    -0.70
    PerformLayout
    -0.68
     Alfredo
    -0.66
    antMatchers
    -0.65
     administracy
    -0.65
    Bhar
    -0.65
    ennheiser
    -0.64
     Bhar
    -0.64
    homonymie
    -0.63
    POSITIVE LOGITS
     curiosity
    1.30
     Curiosity
    1.12
     curious
    1.11
    loc
    1.02
     curio
    1.00
    curious
    0.97
    curios
    0.97
     loc
    0.93
     Curious
    0.93
     curieux
    0.91
    Act Density 0.126%

    No Known Activations