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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers mentioned as part of a statement or argument

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and their variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighb
    -0.72
     describ
    -0.70
     Mub
    -0.69
     territ
    -0.68
     petrol
    -0.67
     flex
    -0.67
     sculpt
    -0.67
     Ont
    -0.67
     dismant
    -0.67
     crunch
    -0.66
    POSITIVE LOGITS
    Offline
    1.31
    Joined
    1.30
    Reviewer
    1.26
    Topic
    1.23
    Overview
    1.21
    Description
    1.20
    Introduction
    1.19
    ////////////////////////////////
    1.17
    Enlarge
    1.16
    Status
    1.16
    Act Density 0.290%

    No Known Activations