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

    Neuronpedia

    INDEX
    Explanations

    mentions of introductory topics, courses, or tutorials

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Introduction" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.85
    rage
    -0.79
     opio
    -0.76
    rie
    -0.70
    rio
    -0.69
     saline
    -0.67
     sclerosis
    -0.67
    rice
    -0.62
    lean
    -0.62
    ief
    -0.61
    POSITIVE LOGITS
     thereto
    1.04
    matter
    0.95
    spection
    0.86
     Introduction
    0.74
    ptions
    0.73
    plates
    0.72
    plate
    0.69
     Jav
    0.69
     Forth
    0.68
     Principles
    0.68
    Act Density 0.043%

    No Known Activations