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

    Neuronpedia

    INDEX
    Explanations

    scientific publications or institutions related to science

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific journals and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.79
     withdrawals
    -0.76
    wn
    -0.71
     evict
    -0.71
     len
    -0.71
     occup
    -0.67
     eviction
    -0.66
     eject
    -0.66
     bundles
    -0.65
     dest
    -0.64
    POSITIVE LOGITS
     Science
    3.69
    Science
    3.10
     science
    2.55
    science
    2.39
     Sciences
    2.22
     Scientist
    2.03
     Scientists
    2.03
     sciences
    1.92
     Scientific
    1.91
     Sci
    1.85
    Act Density 0.018%

    No Known Activations