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

    Neuronpedia

    INDEX
    Explanations

    instances of violent actions or physical confrontations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACTIONS
    -0.52
     getParent
    -0.49
    stoppable
    -0.48
    MockBean
    -0.48
     Pender
    -0.47
     altrimenti
    -0.47
     Lid
    -0.46
     act
    -0.45
     fei
    -0.45
    idences
    -0.45
    POSITIVE LOGITS
    发表于
    0.68
    Jeografia
    0.66
     ivelany
    0.66
    出版年
    0.64
    AddTagHelper
    0.60
    دانشنامهٔ
    0.59
    Хьажоргаш
    0.59
    Enllaces
    0.57
    contentLoaded
    0.54
    mergeFrom
    0.54
    Act Density 0.247%

    No Known Activations