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

    Neuronpedia

    INDEX
    Explanations

    time-related information such as cooking times or total time in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time measurements and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pher
    -0.77
    hare
    -0.76
    lyn
    -0.76
    lash
    -0.75
    hov
    -0.75
    lain
    -0.74
    etsy
    -0.72
     Lazarus
    -0.71
    erald
    -0.71
    ker
    -0.66
    POSITIVE LOGITS
    itarian
    0.86
     Eclipse
    0.86
     Thoughts
    0.73
     Lifetime
    0.72
     Conversion
    0.71
     Difference
    0.69
    itar
    0.67
     Âł Âł Âł Âł Âł Âł Âł Âł
    0.66
    idad
    0.66
     Percent
    0.66
    Act Density 0.023%

    No Known Activations