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

    Neuronpedia

    INDEX
    Explanations

    ordinal indicators and directory-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stages
    -1.00
     Phases
    -0.99
     Zones
    -0.92
    Phases
    -0.89
    Stages
    -0.88
     Lines
    -0.87
     Periods
    -0.86
     Sections
    -0.85
     Regions
    -0.85
     Areas
    -0.84
    POSITIVE LOGITS
     section
    0.99
     segment
    0.79
     chapter
    0.66
     sector
    0.63
     lane
    0.62
     Investments
    0.61
     page
    0.61
     zone
    0.60
     channel
    0.59
    \{\\
    0.56
    Act Density 1.105%

    No Known Activations