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

    Neuronpedia

    INDEX
    Explanations

    legal and terms of service-related language

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal agreements and conditions of service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exper
    -0.74
    avid
    -0.72
    Around
    -0.72
    ï¸ı
    -0.72
    thought
    -0.70
    ffee
    -0.70
     gigs
    -0.70
    beat
    -0.70
    Avg
    -0.70
    byn
    -0.69
    POSITIVE LOGITS
     applicable
    1.29
     pursuant
    1.15
     lawfully
    1.14
     specified
    1.10
     herein
    1.06
     authorized
    1.03
     lawful
    1.03
     hereby
    1.02
     prescribed
    1.02
     shall
    1.00
    Act Density 1.289%

    No Known Activations