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

    Neuronpedia

    INDEX
    Explanations

    dates and time indicators

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical references in a timeline or schedule context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dominican
    -0.62
    amus
    -0.62
     Corpus
    -0.60
    omi
    -0.58
    ady
    -0.56
     patches
    -0.56
    ets
    -0.55
    horse
    -0.55
     Dominic
    -0.54
     saint
    -0.54
    POSITIVE LOGITS
     21
    1.24
     22
    1.22
    21
    1.21
    22
    1.17
     2024
    1.14
     23
    1.11
    23
    1.11
     20
    1.03
    24
    1.01
    20
    0.99
    Act Density 0.098%

    No Known Activations