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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gaining knowledge or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate gaining knowledge or discovering information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vision
    -0.72
    vantage
    -0.69
    ģĸ
    -0.69
    ayan
    -0.69
    aukee
    -0.68
    apters
    -0.67
    itect
    -0.67
    ulp
    -0.66
    alus
    -0.66
    enes
    -0.65
    POSITIVE LOGITS
     news
    0.59
     announces
    0.58
     announcing
    0.58
    imaru
    0.56
    RECT
    0.56
    Chel
    0.55
     vacancies
    0.55
     thou
    0.54
    YY
    0.54
     nothing
    0.54
    Act Density 0.143%

    No Known Activations