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

    Neuronpedia

    INDEX
    Explanations

    dates formatted as month/day/year

    oai_token-act-pair · gpt-3.5-turbo

    patterns in numerical date formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     creep
    -0.72
    etheless
    -0.67
     soaring
    -0.66
     crept
    -0.66
     bri
    -0.65
     obsc
    -0.65
    ļéĨĴ
    -0.65
     stalking
    -0.65
     Angelo
    -0.65
     Primordial
    -0.65
    POSITIVE LOGITS
    PUT
    0.99
    etc
    0.99
    2015
    0.91
    RP
    0.89
    2014
    0.85
    2012
    0.85
    1000
    0.84
    2016
    0.84
    present
    0.84
    pmwiki
    0.84
    Act Density 0.045%

    No Known Activations