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

    Neuronpedia

    INDEX
    Explanations

    terms associated with decay processes in scientific contexts

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

    decay and its products/rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Str
    -0.45
    Nin
    -0.45
     indis
    -0.45
    Ben
    -0.44
    Bob
    -0.44
     Whitley
    -0.43
     Whitman
    -0.43
    ├
    -0.43
    Thomas
    -0.43
    Fran
    -0.43
    POSITIVE LOGITS
     decay
    2.25
     Decay
    2.08
    decay
    2.03
    Decay
    1.95
     decays
    1.75
     decayed
    1.62
     decaying
    1.59
    deca
    0.99
    衰
    0.98
     decline
    0.91
    Act Density 0.005%

    No Known Activations