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

    Neuronpedia

    INDEX
    Explanations

    mentions of commentators in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to commentators and their commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riages
    -0.67
    agna
    -0.61
    artifacts
    -0.60
     mountainous
    -0.60
     Pradesh
    -0.60
    urat
    -0.59
     suitcase
    -0.59
     levers
    -0.58
     Pie
    -0.58
    oku
    -0.58
    POSITIVE LOGITS
     commentator
    0.94
     commentators
    0.91
     laureate
    0.78
    acers
    0.76
    ervative
    0.74
    alyst
    0.74
    jad
    0.73
    oad
    0.72
    trop
    0.70
    odox
    0.69
    Act Density 0.014%

    No Known Activations