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

    Neuronpedia

    INDEX
    Explanations

    the phrase "half a" followed by various measurements or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "half."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Marginal
    -0.76
    ãĤ¡
    -0.72
     intrins
    -0.67
    PLA
    -0.66
    rha
    -0.62
    values
    -0.60
    IRC
    -0.60
     [*
    -0.57
     services
    -0.57
     behaviours
    -0.55
    POSITIVE LOGITS
    dozen
    1.12
     dozen
    1.09
    century
    0.86
    ousand
    0.84
    ths
    0.81
     century
    0.80
    agos
    0.74
    hour
    0.74
    hops
    0.70
    hyde
    0.70
    Act Density 0.083%

    No Known Activations