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

    Neuronpedia

    INDEX
    Explanations

    concepts related to belief and questioning established norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.40
     circulaire
    -0.40
     ujednoznacz
    -0.40
    GeneratedCode
    -0.40
    estacks
    -0.40
    SpringRunner
    -0.38
    setUserId
    -0.38
    dom
    -0.38
    cipar
    -0.38
    stylers
    -0.37
    POSITIVE LOGITS
     незавершена
    0.50
    CppMethod
    0.48
     dismissed
    0.47
     dimentic
    0.45
    ACHUSET
    0.42
     dismissing
    0.42
    Jîn
    0.40
     moletom
    0.39
     DataLoader
    0.39
    andosi
    0.39
    Act Density 0.371%

    No Known Activations