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

    Neuronpedia

    INDEX
    Explanations

    dates in the format month day, year

    oai_token-act-pair · gpt-3.5-turbo

    dates and specific time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igans
    -0.76
    ukes
    -0.68
     Genie
    -0.68
    ufact
    -0.64
    akespe
    -0.63
    aghetti
    -0.61
    igham
    -0.61
    bage
    -0.59
    GGGGGGGG
    -0.59
    ioch
    -0.58
    POSITIVE LOGITS
    th
    1.15
    rd
    0.88
    TH
    0.81
     2018
    0.79
     2017
    0.77
    2200
    0.76
     2015
    0.74
     2014
    0.72
     2016
    0.70
    2016
    0.70
    Act Density 0.085%

    No Known Activations