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

    Neuronpedia

    INDEX
    Explanations

    time-related terms like days, weeks, months, and years

    oai_token-act-pair · gpt-3.5-turbo

    references to recent events or time-specific occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ////////////////////////////////
    -0.68
    arta
    -0.64
    SPA
    -0.60
    itute
    -0.59
    ãĥĺ
    -0.58
    eers
    -0.57
    itutes
    -0.57
    heid
    -0.56
    maximum
    -0.55
    please
    -0.54
    POSITIVE LOGITS
     when
    1.20
    when
    1.11
     unveiling
    0.83
     announcing
    0.76
     WHEN
    0.75
     regarding
    0.74
     after
    0.70
     morning
    0.68
     alleging
    0.67
     unveil
    0.67
    Act Density 0.247%

    No Known Activations