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

    Neuronpedia

    INDEX
    Explanations

    indications of rules, restrictions, or changes that have been implemented or lifted

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of verbs related to regulatory changes and status updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enaries
    -0.74
     IMAGES
    -0.71
     RTX
    -0.68
     fortunes
    -0.65
     portrays
    -0.64
    course
    -0.64
    âĵĺ
    -0.62
     portray
    -0.62
    lake
    -0.62
     indo
    -0.61
    POSITIVE LOGITS
     revoked
    1.54
     repealed
    1.42
     abolished
    1.33
     rescind
    1.32
     enforced
    1.31
     imposed
    1.31
     waived
    1.21
     instituted
    1.19
     expired
    1.17
     implemented
    1.15
    Act Density 0.314%

    No Known Activations