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

    Neuronpedia

    INDEX
    Explanations

    references to specific intervals or periods of time

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

    interval measurement duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    black
    -0.47
    make
    -0.47
    Black
    -0.46
    BLACK
    -0.45
    Psycho
    -0.43
     Públicas
    -0.42
    doctor
    -0.42
     BLACK
    -0.42
    george
    -0.41
    fuck
    -0.41
    POSITIVE LOGITS
     Interval
    1.27
     interval
    1.20
     Intervals
    1.12
     intervals
    1.11
     INTERVAL
    1.02
    interval
    1.00
    Interval
    1.00
    intervals
    0.94
    INTERVAL
    0.88
    Intervals
    0.88
    Act Density 0.007%

    No Known Activations