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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Obrázky
    -0.65
    awtextra
    -0.56
    curité
    -0.56
    rceil
    -0.55
    büro
    -0.54
    Incl
    -0.54
     slå
    -0.52
    ziplin
    -0.51
    morphic
    -0.51
     pab
    -0.51
    POSITIVE LOGITS
     TextEditing
    0.72
    躇
    0.66
    itness
    0.60
    Cordialement
    0.57
     فريبيس
    0.55
     deepcopy
    0.55
    helves
    0.54
     deſt
    0.53
    LookAnd
    0.53
    ريكية
    0.53
    Act Density 0.537%

    No Known Activations