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

    Neuronpedia

    INDEX
    Explanations

    words related to research institutes

    oai_token-act-pair · gpt-3.5-turbo

    references to various research institutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.92
    gets
    -0.74
    taboola
    -0.73
    catentry
    -0.70
    mere
    -0.70
     ages
    -0.67
    outer
    -0.67
    halla
    -0.65
     tame
    -0.64
    stories
    -0.62
    POSITIVE LOGITS
    itute
    0.85
     Institution
    0.83
     Institute
    0.83
     Research
    0.74
     Transparency
    0.74
    Research
    0.72
    una
    0.72
    inery
    0.71
     Square
    0.69
     Levy
    0.69
    Act Density 0.019%

    No Known Activations