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

    Neuronpedia

    INDEX
    Explanations

    references to prominent publications and their articles or authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lingen
    -0.15
     Candle
    -0.15
    onda
    -0.15
    unning
    -0.14
    ienne
    -0.14
    ál
    -0.14
    lint
    -0.14
    inas
    -0.14
    edo
    -0.14
     sor
    -0.13
    POSITIVE LOGITS
     Guardian
    0.33
     Telegraph
    0.32
     Mail
    0.31
    Guard
    0.30
     guardian
    0.28
    Tele
    0.28
    Mail
    0.27
    guard
    0.27
     MAIL
    0.26
     Financial
    0.26
    Act Density 0.196%

    No Known Activations