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

    Neuronpedia

    INDEX
    Explanations

    negative expressions or mentions of absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behulp
    -0.58
    什么呢
    -0.55
    istoitu
    -0.55
    ,
    -0.54
    われました
    -0.54
     verschil
    -0.53
    创建时间
    -0.52
    PerformLayout
    -0.52
    圖片來源
    -0.52
     inol
    -0.51
    POSITIVE LOGITS
    MENAFN
    0.68
     
    0.65
    welli
    0.65
    \{\\
    0.65
    Rohy
    0.64
    < 
    0.64
    Identyfik
    0.63
    ########.
    0.62
     isNameExpr
    0.62
    /#{
    0.61
    Act Density 0.152%

    No Known Activations