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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IContainer
    -0.62
     antaranya
    -0.61
    arithmic
    -0.61
    Obrázky
    -0.60
     ويكيپيديا
    -0.60
    oplasma
    -0.58
    ulkner
    -0.58
     Penh
    -0.58
    уда
    -0.57
     Expédié
    -0.57
    POSITIVE LOGITS
     curious
    4.17
    curious
    3.52
     curiosity
    3.46
     Curious
    3.39
    Curious
    3.30
     curieux
    2.71
    curios
    2.65
     Curiosity
    2.65
     curios
    2.62
     curio
    2.48
    Act Density 0.060%

    No Known Activations