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

    Neuronpedia

    INDEX
    Explanations

    references to specific durations of time, particularly focusing on years

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "years" and its variations to emphasize the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.77
    amina
    -0.73
    iqu
    -0.72
     contag
    -0.71
    apa
    -0.67
    iant
    -0.66
    agonist
    -0.63
    agle
    -0.63
    agate
    -0.61
    aminer
    -0.61
    POSITIVE LOGITS
     ago
    1.32
     Ago
    1.15
     olds
    0.86
    mith
    0.74
     anniversary
    0.74
     old
    0.73
    manship
    0.72
    long
    0.71
     wiser
    0.70
    oming
    0.69
    Act Density 0.096%

    No Known Activations