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

    Neuronpedia

    INDEX
    Explanations

    historical dates

    oai_token-act-pair · gpt-3.5-turbo

    specific years related to significant historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hed
    -0.91
    tro
    -0.77
    resso
    -0.75
    hes
    -0.74
    ithe
    -0.72
    onet
    -0.70
    Nation
    -0.69
    econom
    -0.68
    andering
    -0.66
    act
    -0.65
    POSITIVE LOGITS
    å¹
    0.89
     1946
    0.77
     1953
    0.76
     1949
    0.76
     1958
    0.75
     1954
    0.73
     1952
    0.72
     1957
    0.72
     1962
    0.72
     1956
    0.71
    Act Density 0.021%

    No Known Activations