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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uci
    -0.15
    vos
    -0.14
    istrovstvÃŃ
    -0.14
    ̣
    -0.14
    agara
    -0.14
    anzi
    -0.14
     detriment
    -0.14
     Socorro
    -0.14
     liver
    -0.14
    ï
    -0.13
    POSITIVE LOGITS
    shan
    0.17
    æķ£
    0.15
    nge
    0.15
    lopedia
    0.15
    cej
    0.15
    inta
    0.14
    /gallery
    0.14
    emento
    0.14
    .tie
    0.14
    lys
    0.14
    Act Density 0.104%

    No Known Activations