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

    Neuronpedia

    INDEX
    Explanations

    references to specific points in time in Earth's history

    oai_token-act-pair · gpt-3.5-turbo

    references to large numbers of years, particularly in the context of age and historical timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.71
    Quality
    -0.66
     Rez
    -0.66
    tek
    -0.64
    Johnny
    -0.63
    Priv
    -0.63
     glim
    -0.63
    Sov
    -0.63
    Guest
    -0.62
    anooga
    -0.62
    POSITIVE LOGITS
     ago
    1.44
     Ago
    1.07
     BCE
    0.91
     old
    0.83
     olds
    0.82
     elapsed
    0.81
     extinct
    0.81
    osaurs
    0.79
     Ceres
    0.78
    history
    0.74
    Act Density 0.064%

    No Known Activations