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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their associated forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !")
    -0.74
     ſte
    -0.67
     raiſ
    -0.64
     leaſt
    -0.63
    '])
    -0.61
     ſtill
    -0.60
     Jefus
    -0.60
     diſt
    -0.59
     houſe
    -0.59
     themſelves
    -0.59
    POSITIVE LOGITS
     Bourgoin
    0.74
    cheidet
    0.64
     désolés
    0.59
    RTLD
    0.57
    EndProject
    0.57
    SqlClient
    0.57
    criminate
    0.57
     CreateTagHelper
    0.56
    NameInMap
    0.56
    THISDAY
    0.54
    Act Density 0.133%

    No Known Activations