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

    Neuronpedia

    INDEX
    Explanations

    words related to blogs and bloggers

    oai_token-act-pair · gpt-3.5-turbo

    references to blogs and blogging platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arching
    -0.67
     negotiators
    -0.65
     Lauder
    -0.65
     jeopardy
    -0.61
     rays
    -0.60
     Scotia
    -0.58
    aves
    -0.58
     federally
    -0.57
    ederation
    -0.56
    undai
    -0.56
    POSITIVE LOGITS
    osphere
    1.66
    gers
    1.47
    ger
    1.37
    ging
    1.30
    spot
    1.27
    ged
    1.18
    lov
    1.06
    culosis
    0.95
    posts
    0.92
    bub
    0.92
    Act Density 0.034%

    No Known Activations