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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific topics

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific topics and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dere
    -0.80
     innocence
    -0.78
     contro
    -0.75
     cum
    -0.75
     relief
    -0.73
     veh
    -0.70
     slaying
    -0.69
     fault
    -0.69
     pacing
    -0.67
     quir
    -0.67
    POSITIVE LOGITS
     Scientific
    2.57
     Nutrition
    1.92
     Evolution
    1.47
    gold
    1.14
     Ingredients
    1.13
     Laboratories
    1.12
     recommends
    1.10
    maid
    1.10
     Growth
    1.07
    Ingredients
    1.02
    Act Density 0.029%

    No Known Activations