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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific time periods, like "recent years."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ""}
    -0.59
     réunions
    -0.57
     ''}
    -0.53
    idać
    -0.52
     urm
    -0.51
     "-";
    -0.50
    spania
    -0.50
     "/";
    -0.49
    essoa
    -0.49
     vœux
    -0.49
    POSITIVE LOGITS
     recent
    0.85
    recent
    0.76
    Recent
    0.74
     Recent
    0.72
     RECENT
    0.70
     recente
    0.69
     minimalis
    0.59
     Lampung
    0.58
     gend
    0.56
    RECENT
    0.55
    Act Density 0.057%

    No Known Activations