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

    Neuronpedia

    INDEX
    Explanations

    words related to news articles or journalistic content

    oai_token-act-pair · gpt-3.5-turbo

    references to articles or segments within articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asters
    -0.74
    alth
    -0.73
    kson
    -0.72
    cffffcc
    -0.71
    enthal
    -0.68
    aterasu
    -0.66
    uits
    -0.65
    merce
    -0.64
    bledon
    -0.64
    aukee
    -0.64
    POSITIVE LOGITS
     Continued
    1.20
     CONTIN
    0.91
     continues
    0.89
     Contin
    0.86
    ICLE
    0.77
     excerpt
    0.70
     omitted
    0.70
     VIII
    0.68
     VII
    0.67
     contents
    0.67
    Act Density 0.014%

    No Known Activations