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

    Neuronpedia

    INDEX
    Explanations

    URLs and website addresses

    oai_token-act-pair · gpt-3.5-turbo

    web domain names and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snowball
    -0.62
     filibuster
    -0.59
     recess
    -0.59
    ĪĴ
    -0.58
     succeeding
    -0.56
     streng
    -0.56
     positively
    -0.55
     doubling
    -0.54
    laus
    -0.54
     transform
    -0.54
    POSITIVE LOGITS
    /?
    1.94
    /,
    1.68
    /#
    1.68
    /_
    1.60
    /)
    1.56
    /
    1.52
    /.
    1.48
    /-
    1.44
    /+
    1.31
     âĢº
    1.31
    Act Density 0.030%

    No Known Activations