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

    Neuronpedia

    INDEX
    Explanations

    references to tasks and their various attributes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '}>
    -0.95
     GenerationType
    -0.89
     CNA
    -0.84
    ']}
    -0.83
    ")));
    -0.81
    ;'>
    -0.81
     \\
    -0.81
    ︎
    -0.81
    vea
    -0.80
     Marac
    -0.80
    POSITIVE LOGITS
     tasks
    1.89
     task
    1.69
     Tasks
    1.66
     Task
    1.64
     TASK
    1.64
    tasks
    1.62
    Tasks
    1.60
    Task
    1.57
    TASK
    1.55
    getTask
    1.44
    Act Density 0.030%

    No Known Activations