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

    Neuronpedia

    INDEX
    Explanations

    mentions of recent events or developments

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating recency or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gate
    -0.69
     tele
    -0.68
     ends
    -0.68
     hire
    -0.68
     sold
    -0.63
     beast
    -0.63
     stands
    -0.62
     magic
    -0.62
     offense
    -0.61
     cock
    -0.61
    POSITIVE LOGITS
    Recent
    3.91
     Recent
    2.05
    recent
    1.73
    Latest
    1.57
    Current
    1.50
    Recently
    1.39
    Previous
    1.37
    Past
    1.20
    Trend
    1.19
    Evidence
    1.15
    Act Density 0.016%

    No Known Activations