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

    Neuronpedia

    INDEX
    Explanations

    events or actions that indicate a timeline or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    time-related words and temporal references (years, days, dates).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    dates and references to specific times or events.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi
    New Auto-Interp
    Negative Logits
    ſehen
    -0.57
    hoeddwyd
    -0.56
     AttributeSet
    -0.55
    basicConfig
    -0.54
     Geſch
    -0.54
     queſta
    -0.54
     infatti
    -0.53
    Disclosures
    -0.53
    ésultats
    -0.52
     isNameExpr
    -0.52
    POSITIVE LOGITS
     again
    0.54
     للاسماء
    0.52
    enterOuterAlt
    0.47
    今度は
    0.46
    AutoScale
    0.44
     Again
    0.40
    Again
    0.40
    again
    0.37
    再來
    0.36
     AGAIN
    0.36
    Act Density 0.322%

    No Known Activations