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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific decades in the 20th century

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades, particularly the 1950s, 1980s, and 1990s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.83
    acts
    -0.71
    uala
    -0.71
    ournals
    -0.69
    iam
    -0.66
    Maker
    -0.65
    bind
    -0.64
    emy
    -0.61
    azor
    -0.61
    Unity
    -0.61
    POSITIVE LOGITS
     onwards
    1.13
     onward
    1.05
     era
    0.98
     Era
    0.88
    ixties
    0.87
     nostalg
    0.86
    -'
    0.85
     BCE
    0.75
     hey
    0.75
     sitcom
    0.73
    Act Density 0.060%

    No Known Activations