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

    Neuronpedia

    INDEX
    Explanations

    updates and changes in software or systems

    oai_token-act-pair · gpt-3.5-turbo

    elements related to software updates and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.80
     stereotyp
    -0.76
     pictured
    -0.74
     photographed
    -0.72
    orkshire
    -0.72
    llah
    -0.71
     hors
    -0.70
     imperson
    -0.69
     Beir
    -0.69
     dressed
    -0.69
    POSITIVE LOGITS
    Version
    1.04
    Patch
    0.95
     Fixes
    0.94
    Developer
    0.92
    Changes
    0.91
    Added
    0.87
     Revised
    0.87
    FIX
    0.87
    iOS
    0.87
    Updated
    0.85
    Act Density 0.408%

    No Known Activations