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

    Neuronpedia

    INDEX
    Explanations

    terms related to long-term patterns or developments

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic and societal trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gur
    -0.77
    ×Ļ×
    -0.73
    tein
    -0.71
    ricular
    -0.67
    amina
    -0.66
    porting
    -0.65
    ergy
    -0.65
    vette
    -0.65
    unts
    -0.65
    ×Ļ
    -0.64
    POSITIVE LOGITS
     trends
    1.35
     Trends
    1.09
     trend
    1.02
     Trend
    0.95
    Trend
    0.88
     Patterns
    0.85
    ãĤ¼ãĤ¦ãĤ¹
    0.82
    ĸļ
    0.78
     patterns
    0.77
     indicators
    0.75
    Act Density 0.005%

    No Known Activations