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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "is" and its variations, indicating a focus on existential or definitional statements

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

    contractions with "it's" and the letter "s" that follows.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     surla
    -0.79
     дописавши
    -0.71
    ChildScrollView
    -0.69
    Personendaten
    -0.59
    parsedMessage
    -0.59
    rungsseite
    -0.57
    PhysRevD
    -0.57
    adaptiveStyles
    -0.57
     pinulongan
    -0.55
    delwed
    -0.54
    POSITIVE LOGITS
     always
    0.59
     not
    0.59
     probably
    0.55
     certainly
    0.53
     hard
    0.50
     important
    0.49
     true
    0.48
     also
    0.48
     unfortunate
    0.47
     just
    0.47
    Act Density 0.185%

    No Known Activations