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

    Neuronpedia

    INDEX
    Explanations

    structural elements or sections within written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifax
    -0.16
    uling
    -0.15
    reen
    -0.14
     underside
    -0.14
    ãĥ³ãĥIJ
    -0.14
    illi
    -0.13
     reversal
    -0.13
    otos
    -0.13
    941
    -0.13
    isia
    -0.13
    POSITIVE LOGITS
     introduction
    0.86
     introdu
    0.77
     Introduction
    0.75
     intro
    0.75
    Introduction
    0.70
     introduce
    0.67
     introduced
    0.67
     Intro
    0.66
     introducing
    0.61
    intro
    0.60
    Act Density 0.078%

    No Known Activations