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

    Neuronpedia

    INDEX
    Explanations

    proper nouns appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific name or title that begins with "Der."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hetti
    -0.83
    INTER
    -0.71
     Dragonbound
    -0.70
     [|
    -0.67
    sburgh
    -0.67
     Samoa
    -0.66
    odcast
    -0.65
    ships
    -0.64
    margin
    -0.63
    hews
    -0.63
    POSITIVE LOGITS
    bys
    0.98
    ricks
    0.93
    bil
    0.90
     Spiegel
    0.88
    iving
    0.88
    mal
    0.88
    rek
    0.87
    isively
    0.86
    ived
    0.84
    ivation
    0.84
    Act Density 0.009%

    No Known Activations