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

    Neuronpedia

    INDEX
    Explanations

    words related to computer software and applications processes

    oai_token-act-pair · gpt-3.5-turbo

    terminology and concepts related to software development and tools, particularly those related to operating systems and jailbreaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mour
    -0.89
     Urban
    -0.88
     Opportunity
    -0.88
     Exhibition
    -0.88
     Rouge
    -0.84
     Morning
    -0.84
     Oriental
    -0.84
     Spiritual
    -0.83
     Parish
    -0.83
     Evening
    -0.82
    POSITIVE LOGITS
    files
    1.46
    codes
    1.38
    cache
    1.37
    maps
    1.36
    boxes
    1.35
    utils
    1.33
    config
    1.26
     directories
    1.25
    cfg
    1.24
    apps
    1.23
    Act Density 0.335%

    No Known Activations