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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts and research-related terms

    oai_token-act-pair · gpt-3.5-turbo

    sections or headings in a document, particularly those that indicate structure such as "Abstract" or "Introduction."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    milo
    -0.71
    jer
    -0.69
     streaks
    -0.63
    ardless
    -0.63
    efully
    -0.61
     greens
    -0.61
    soDeliveryDate
    -0.60
    erest
    -0.59
    rett
    -0.58
    aping
    -0.58
    POSITIVE LOGITS
    Abstract
    1.16
    GROUND
    0.96
     Introduction
    0.95
     Abstract
    0.93
    Introduction
    0.91
     References
    0.84
     Purpose
    0.80
    initions
    0.79
    stract
    0.79
    ¶
    0.78
    Act Density 0.030%

    No Known Activations