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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditional or sequential actions

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

    "Once you" followed by an action

    np_acts-logits-general · gemini-2.0-flash

    once you have completed something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    至今
    -0.68
     CreateTagHelper
    -0.65
     never
    -0.60
     कभी
    -0.60
    今も
    -0.59
    never
    -0.59
     malah
    -0.58
     никогда
    -0.57
     nigdy
    -0.54
     Never
    -0.54
    POSITIVE LOGITS
     sufficiently
    1.00
     satisfactorily
    0.86
     enough
    0.82
     sufficient
    0.80
     settled
    0.80
     adequately
    0.80
     finished
    0.80
     Completed
    0.77
     completed
    0.77
     satisfactory
    0.75
    Act Density 0.464%

    No Known Activations