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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods, particularly decades

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades, particularly the terms "decade" combined with numerical indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquid
    -0.75
    iqu
    -0.72
    amina
    -0.70
    anamo
    -0.68
    ournals
    -0.66
     ingred
    -0.66
     procedural
    -0.65
    govtrack
    -0.64
    ffic
    -0.64
    perse
    -0.62
    POSITIVE LOGITS
     ILCS
    0.98
     ago
    0.87
    ĸļ
    0.77
    uously
    0.74
     onward
    0.72
    -'
    0.70
    alist
    0.70
    icity
    0.69
    ary
    0.69
    hetti
    0.69
    Act Density 0.027%

    No Known Activations