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

    Neuronpedia

    INDEX
    Explanations

    phrases related to completing tasks or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Completions or finishing actions

    np_acts-logits-general · gemini-2.0-flash

    once action completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.70
    kept
    -0.66
     instantly
    -0.66
    immediately
    -0.65
     never
    -0.64
     immediately
    -0.63
     malah
    -0.61
     justru
    -0.60
     kept
    -0.60
    never
    -0.59
    POSITIVE LOGITS
     finished
    1.13
     completes
    1.07
     finishes
    1.06
     completed
    1.00
     finish
    0.99
     sufficiently
    0.94
     Finished
    0.91
     Completed
    0.91
     completion
    0.88
     xong
    0.88
    Act Density 0.429%

    No Known Activations