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

    Neuronpedia

    INDEX
    Explanations

    words related to programming or software development, particularly focusing on terms like "json", "pro", "mod", and "sub"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming or technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vetting
    -0.62
     Democr
    -0.60
    QUI
    -0.58
     democracies
    -0.55
     Advertisement
    -0.52
     definition
    -0.52
     circuits
    -0.51
    Sphere
    -0.51
    Spoiler
    -0.51
     footing
    -0.51
    POSITIVE LOGITS
    sky
    0.90
    sson
    0.90
    å
    0.88
    chev
    0.85
    nir
    0.84
    ukong
    0.84
    zinski
    0.83
    theless
    0.82
    zik
    0.80
    hov
    0.80
    Act Density 0.210%

    No Known Activations