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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic or scientific investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to research activities or the concept of research itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.80
    lehem
    -0.73
    footed
    -0.71
    rollers
    -0.71
    faced
    -0.67
    vez
    -0.66
    enance
    -0.66
    sama
    -0.65
    lime
    -0.65
    olded
    -0.62
    POSITIVE LOGITS
     research
    3.46
    research
    2.88
    Research
    2.55
     Research
    2.50
     researcher
    2.15
     resear
    2.14
     researching
    2.03
     researchers
    2.03
     study
    1.85
     studies
    1.82
    Act Density 0.021%

    No Known Activations