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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.78
    vanje
    -0.56
     gouvernements
    -0.55
    ydı
    -0.53
     chrétiens
    -0.51
     prisonniers
    -0.49
     autorités
    -0.49
     précédentes
    -0.48
     leçon
    -0.47
     chiffres
    -0.47
    POSITIVE LOGITS
    ogh
    0.99
    puts
    0.92
     hindurch
    0.88
     hoops
    0.83
     intermedi
    0.80
     channels
    0.79
    tagHelperRunner
    0.79
     thick
    0.79
    HOUT
    0.78
     motions
    0.78
    Act Density 0.123%

    No Known Activations