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

    Neuronpedia

    INDEX
    Explanations

    years written in the format "19XX" or historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iants
    -0.80
    pora
    -0.76
    iant
    -0.74
    aminer
    -0.73
    arious
    -0.72
    orem
    -0.72
    omorphic
    -0.69
    iance
    -0.67
    senal
    -0.67
    ctica
    -0.67
    POSITIVE LOGITS
    61
    0.97
    âĸĪâĸĪ
    0.92
    62
    0.88
    04
    0.88
    06
    0.87
    05
    0.87
    08
    0.86
    07
    0.84
    49
    0.83
    03
    0.83
    Act Density 0.014%

    No Known Activations