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

    Neuronpedia

    INDEX
    Explanations

    programming terms and task-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     passagers
    -0.52
     policiers
    -0.52
    BeginContext
    -0.49
     sè
    -0.47
     personalità
    -0.47
     legale
    -0.45
     moza
    -0.44
     smer
    -0.44
    hibernate
    -0.44
     cleanest
    -0.43
    POSITIVE LOGITS
    Tasks
    2.15
     Tasks
    1.56
    tasks
    1.50
     tasks
    1.42
     Task
    1.31
     task
    1.30
    Task
    1.29
    TASKS
    1.22
    task
    1.22
     TASK
    1.06
    Act Density 0.004%

    No Known Activations