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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sequential processes and conditional outcomes

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

    preceding verbs of completion or ending

    np_acts-logits-general · gemini-2.0-flash

    completion and end states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.55
     kasarigan
    -0.53
     immédi
    -0.48
     Immediate
    -0.48
    then
    -0.47
    kept
    -0.46
     immédiatement
    -0.46
     Quick
    -0.45
    打了
    -0.45
     Immediately
    -0.43
    POSITIVE LOGITS
     complete
    0.83
     fully
    0.81
     completely
    0.77
     reach
    0.69
     Completely
    0.68
     Complete
    0.68
     COMPLETE
    0.68
    Completely
    0.67
    ]='\
    0.67
     Fully
    0.67
    Act Density 0.281%

    No Known Activations