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

    Neuronpedia

    INDEX
    Explanations

    references to individual items or instances presented sequentially

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

    "at a time"

    np_acts-logits-general · gemini-2.0-flash

    at a time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    -0.47
    res
    -0.42
     too
    -0.42
    no
    -0.42
    i
    -0.40
     (
    -0.38
     _
    -0.37
     Sp
    -0.37
    too
    -0.36
     
    -0.36
    POSITIVE LOGITS
     time
    2.48
    time
    1.85
     TIME
    1.68
    Time
    1.60
     Time
    1.49
    TIME
    1.47
     tyme
    1.38
     tijd
    1.37
     времени
    1.34
     vez
    1.28
    Act Density 0.153%

    No Known Activations