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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or event happening at a specific time in the past

    oai_token-act-pair · gpt-3.5-turbo

    phrases starting with the word "Until."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Es
    -0.66
    hazard
    -0.61
    eny
    -0.60
    )].
    -0.60
    AE
    -0.60
    Adds
    -0.58
    76561
    -0.58
    âĵĺ
    -0.58
    que
    -0.58
    rolling
    -0.57
    POSITIVE LOGITS
    unda
    0.80
    soever
    0.78
    ndra
    0.74
     Ago
    0.70
    rely
    0.66
     proven
    0.66
    ilage
    0.65
    entimes
    0.64
     Stats
    0.61
    redo
    0.61
    Act Density 0.023%

    No Known Activations