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

    Neuronpedia

    INDEX
    Explanations

    text related to volumes or levels of something

    oai_token-act-pair · gpt-3.5-turbo

    references to quantitative amounts or counts, particularly relating to "volumes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nordic
    -0.74
    yg
    -0.73
     Elys
    -0.69
     Nether
    -0.69
     Hol
    -0.63
    eworld
    -0.63
    nell
    -0.62
     Nir
    -0.62
     Hex
    -0.62
     Kaufman
    -0.61
    POSITIVE LOGITS
     volumes
    1.65
    umes
    1.13
    Volume
    0.95
     volume
    0.94
    volume
    0.93
     tremend
    0.92
     exha
    0.88
     challeng
    0.86
     discounts
    0.83
     proport
    0.82
    Act Density 0.007%

    No Known Activations