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

    Neuronpedia

    INDEX
    Explanations

    time periods expressed in years

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time, particularly in terms of years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stra
    -0.69
    agonist
    -0.66
    iating
    -0.65
    iability
    -0.64
    anooga
    -0.63
     subsc
    -0.62
    esc
    -0.62
    aunch
    -0.62
    own
    -0.61
    geon
    -0.61
    POSITIVE LOGITS
     ago
    1.12
     onward
    0.80
     onwards
    0.80
    osaurs
    0.79
     olds
    0.75
     Ago
    0.71
    idia
    0.69
     old
    0.66
    bp
    0.64
    glass
    0.64
    Act Density 0.051%

    No Known Activations