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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "lasting" effects or experiences

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

    lasting effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.54
     springfox
    -0.53
    InjectMocks
    -0.53
    rungsseite
    -0.53
     naughty
    -0.52
     idiots
    -0.52
     devil
    -0.52
    ambién
    -0.51
     Broccoli
    -0.50
     Sandwiches
    -0.50
    POSITIVE LOGITS
     lasting
    1.77
     Lasting
    1.71
    lasting
    1.48
     enduring
    1.13
     everlasting
    0.91
     duradero
    0.85
     permanent
    0.85
    permanent
    0.82
     durable
    0.77
    Permanent
    0.77
    Act Density 0.004%

    No Known Activations