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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity and interest in various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing human curiosity and interest in various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    interest and curiosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.56
     raccomand
    -0.53
    EndInit
    -0.52
     recommand
    -0.50
     recommandée
    -0.50
    stdlib
    -0.49
     AssemblyCulture
    -0.49
     сча
    -0.48
    狈
    -0.47
     advice
    -0.47
    POSITIVE LOGITS
     curiosity
    2.60
     interest
    2.26
     curious
    2.07
    curios
    2.05
    interest
    2.02
     Interest
    2.02
    Interest
    2.01
     Curiosity
    2.01
     INTEREST
    1.98
     fascination
    1.92
    Act Density 0.158%

    No Known Activations