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

    Neuronpedia

    INDEX
    Explanations

    references to skepticism or skepticism-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rontal
    -0.70
     FISA
    -0.70
     firsthand
    -0.64
     1918
    -0.63
    ournal
    -0.61
    女
    -0.61
     circumstance
    -0.60
    ategory
    -0.60
     centuries
    -0.59
     unmarked
    -0.59
    POSITIVE LOGITS
     Ske
    1.21
    cius
    0.92
    leton
    0.88
    letal
    0.87
    leys
    0.84
    bridge
    0.84
    cano
    0.81
    gow
    0.81
    ley
    0.80
    bane
    0.79
    Act Density 0.004%

    No Known Activations