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

    Neuronpedia

    INDEX
    Explanations

    references to financial savings

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

    cost savings, energy savings, time savings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fø
    -0.46
     Fø
    -0.44
    <
    -0.44
    Wait
    -0.42
    Fuck
    -0.40
    [
    -0.40
    Write
    -0.40
    Pre
    -0.40
     Hase
    -0.40
    “
    -0.40
    POSITIVE LOGITS
    NINGS
    0.72
    aderie
    0.68
    vings
    0.68
    Personendaten
    0.67
    -------------</
    0.66
    Savings
    0.66
     savings
    0.63
     Savings
    0.63
     kasarigan
    0.63
    rungs
    0.62
    Act Density 0.005%

    No Known Activations