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

    Neuronpedia

    INDEX
    Explanations

    phrases related to assignments and grading expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     training
    -0.17
     Training
    -0.17
     Grades
    -0.16
     schooling
    -0.16
    æĽ
    -0.15
     shin
    -0.15
    Training
    -0.15
     Shin
    -0.15
    ikipedia
    -0.14
     ages
    -0.14
    POSITIVE LOGITS
    cke
    0.17
    osit
    0.16
    à¹ģà¸ģ
    0.15
    Commerce
    0.15
     Commerce
    0.15
     CreateMap
    0.15
    -lfs
    0.14
    uccess
    0.14
     ObjectType
    0.14
    sy
    0.14
    Act Density 0.307%

    No Known Activations