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

    Neuronpedia

    INDEX
    Explanations

    personal and location names, potentially from a transcription or dialogue

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly people's names and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     polluted
    -0.71
     agric
    -0.71
    historic
    -0.70
     centrally
    -0.68
     institutional
    -0.66
     polar
    -0.65
     respectively
    -0.65
    BuyableInstoreAndOnline
    -0.64
     centralized
    -0.64
     consolidation
    -0.64
    POSITIVE LOGITS
    laughter
    1.04
    laughs
    1.01
    aughed
    0.86
    ause
    0.86
     laughs
    0.85
    Narr
    0.85
     laughed
    0.85
    laugh
    0.84
    Pause
    0.83
    ridor
    0.82
    Act Density 0.137%

    No Known Activations