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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Here is a" followed by a description or statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" indicating references or examples in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahu
    -0.87
    alties
    -0.82
    agents
    -0.76
    anism
    -0.75
    agues
    -0.74
    enance
    -0.73
    acid
    -0.70
    errors
    -0.70
    ships
    -0.69
    untu
    -0.68
    POSITIVE LOGITS
     rundown
    1.40
     summary
    1.31
     snippet
    1.24
     breakdown
    1.24
     glimpse
    1.22
     reminder
    1.18
     list
    1.17
     sample
    1.16
     screenshot
    1.15
     sampling
    1.15
    Act Density 0.110%

    No Known Activations