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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    specific years and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.75
    izoph
    -0.74
    phia
    -0.74
     predec
    -0.72
    matically
    -0.70
     ingred
    -0.66
    overs
    -0.64
    acebook
    -0.64
     undermin
    -0.64
    unn
    -0.63
    POSITIVE LOGITS
     partName
    1.05
     GMT
    0.95
     07
    0.86
     02
    0.86
     08
    0.85
     UTC
    0.84
     PST
    0.78
     04
    0.77
     09
    0.77
     03
    0.76
    Act Density 0.056%

    No Known Activations