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

    Neuronpedia

    INDEX
    Explanations

    years from the 80s and 90s

    oai_token-act-pair · gpt-3.5-turbo

    references to decades, particularly the 1980s and 1990s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affirmation
    -0.70
     vain
    -0.68
     fronts
    -0.64
     pse
    -0.63
     justification
    -0.61
     exha
    -0.61
     foundations
    -0.60
     plateau
    -0.60
     aim
    -0.60
     sympathetic
    -0.60
    POSITIVE LOGITS
    20439
    1.27
    70
    1.01
    40
    0.98
    00
    0.96
    71
    0.94
    ï¸ı
    0.93
    76
    0.93
    66
    0.92
    39
    0.92
    69
    0.92
    Act Density 0.101%

    No Known Activations