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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating change or transformation

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

    ending in "-ing" describing a process

    np_acts-logits-general · gemini-2.0-flash

    increasingly becoming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olmaz
    -0.48
    aurais
    -0.47
    ずっと
    -0.44
     MonoBehaviour
    -0.41
     незавершена
    -0.41
     HttpNotFound
    -0.41
     pageContext
    -0.41
    1
    -0.41
    dinga
    -0.40
    aurait
    -0.40
    POSITIVE LOGITS
     increasingly
    1.03
    increasing
    0.93
     emerging
    0.90
    slowly
    0.90
     Increasing
    0.86
    Increasing
    0.85
    EndProject
    0.84
     Slowly
    0.83
     slowly
    0.83
     increasing
    0.81
    Act Density 0.243%

    No Known Activations