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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.67
     ivelany
    -0.63
     '{@
    -0.61
    asgi
    -0.60
     Felic
    -0.58
     AspNetCore
    -0.56
     bower
    -0.55
    StoryboardSegue
    -0.54
    ?):
    -0.54
    !*\
    -0.53
    POSITIVE LOGITS
    Geplaatst
    0.66
    ooga
    0.61
     hard
    0.56
     a
    0.56
    NameInMap
    0.55
    auge
    0.54
     disambiguazione
    0.51
    xmlWriter
    0.50
    ことができました
    0.49
    euw
    0.49
    Act Density 0.093%

    No Known Activations