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

    Neuronpedia

    INDEX
    Explanations

    dates, months, and years referenced in texts

    oai_token-act-pair · gpt-3.5-turbo

    dates and time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agy
    -0.70
    Administ
    -0.63
    ++;
    -0.61
    =""
    -0.58
    ä½ľ
    -0.57
    fram
    -0.56
    ardless
    -0.56
    udging
    -0.56
    DN
    -0.56
    natureconservancy
    -0.56
    POSITIVE LOGITS
    roth
    0.77
     2019
    0.72
    Ĥİ
    0.70
     2018
    0.69
     Maiden
    0.68
    ember
    0.68
     2014
    0.68
     Lights
    0.67
     2017
    0.65
     2015
    0.64
    Act Density 0.217%

    No Known Activations