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

    Neuronpedia

    INDEX
    Explanations

    frequent pronouns and punctuation in text

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

    "I" statements indicating actions or personal experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     various
    -0.41
    epsfig
    -0.40
     parallel
    -0.40
     remarkably
    -0.39
     balanced
    -0.38
    .../
    -0.38
     secure
    -0.38
     Various
    -0.37
     paralle
    -0.37
    Various
    -0.37
    POSITIVE LOGITS
    AnchorStyles
    0.74
    :✨
    0.57
    发表于
    0.56
    Viited
    0.53
    parsedMessage
    0.52
    bibfield
    0.51
     CURIAM
    0.50
    MemoryWarning
    0.50
    SpringBootTest
    0.49
    queryInterface
    0.46
    Act Density 0.000%

    No Known Activations