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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "close to" is used in a document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ury
    -0.78
     Cosponsors
    -0.72
    Ĥª
    -0.67
    ERG
    -0.65
     Edited
    -0.65
    birds
    -0.64
    Written
    -0.63
    kai
    -0.63
    ©¶æ¥µ
    -0.61
    Reviewer
    -0.61
    POSITIVE LOGITS
     shore
    1.00
    sighted
    0.90
     perfection
    0.88
    shore
    0.75
     midnight
    0.73
     achieving
    0.71
     completion
    0.69
     infancy
    0.69
     home
    0.68
     Confederation
    0.68
    Act Density 0.049%

    No Known Activations