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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format "February [day]"

    oai_token-act-pair · gpt-3.5-turbo

    dates, particularly in February

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opic
    -0.63
    achu
    -0.61
     cumbers
    -0.60
    kef
    -0.60
     behavi
    -0.59
    ioch
    -0.59
    ographed
    -0.56
     elephant
    -0.55
     delinquent
    -0.55
     parap
    -0.55
    POSITIVE LOGITS
    nd
    1.26
     Madness
    0.93
     2019
    0.92
     2017
    0.85
    ruary
    0.84
     2016
    0.84
     2018
    0.82
     2015
    0.81
    ricks
    0.81
    mber
    0.80
    Act Density 0.022%

    No Known Activations