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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate dismissive attitudes or arguments about serious issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    found that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.73
    ंदीखरीदारी
    -0.60
     tartalomajánló
    -0.54
     esternos
    -0.53
     يتيمه
    -0.52
     chi̍t
    -0.52
    routeProvider
    -0.52
    rrggbb
    -0.50
     CreateTagHelper
    -0.50
     noDo
    -0.50
    POSITIVE LOGITS
    انيف
    0.35
     flats
    0.34
     сталь
    0.33
    scaron
    0.33
    動画
    0.33
    nalpot
    0.32
    bcc
    0.32
     tecnici
    0.32
     kons
    0.31
    化
    0.31
    Act Density 0.103%

    No Known Activations