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

    Neuronpedia

    INDEX
    Explanations

    specific years or decades

    oai_token-act-pair · gpt-3.5-turbo

    mentions of decades, particularly the 1950s, 1960s, 1970s, and 1980s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spons
    -0.71
    plan
    -0.66
     continu
    -0.62
    FIN
    -0.61
    venge
    -0.60
     voic
    -0.58
    ngth
    -0.58
    Else
    -0.58
    Tickets
    -0.58
    terday
    -0.57
    POSITIVE LOGITS
    -'
    0.91
    eenth
    0.90
    s
    0.89
    ieth
    0.81
    sie
    0.80
    sburg
    0.78
    ixties
    0.76
    ties
    0.75
    enthal
    0.75
    ies
    0.74
    Act Density 0.031%

    No Known Activations