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

    Neuronpedia

    INDEX
    Explanations

    descriptions of dog behavior and training techniques

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

    dogs and excitement

    np_acts-logits-general · gemini-2.5-flash-lite

    Mentions of dogs, especially descriptions of dog body language, physical parts, and behavior in training or tracking contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Tro
    -0.35
     Bengt
    -0.35
     consent
    -0.34
    قامة
    -0.34
    )‏
    -0.33
    
    -0.33
     consented
    -0.33
     Aufla
    -0.32
     acuer
    -0.32
     Seidel
    -0.31
    POSITIVE LOGITS
    ſelf
    0.83
     ویکی‌پدی
    0.79
     dogs
    0.77
    Dogs
    0.77
     pleaſure
    0.74
     Dogs
    0.73
    parsedMessage
    0.73
     leſs
    0.71
     puppy
    0.70
     purpoſe
    0.69
    Act Density 0.235%

    No Known Activations