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

    Neuronpedia

    INDEX
    Explanations

    the frequent repetition of the word "just" and variations that imply simplicity or emphasis in reasoning

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

    "Just" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    just followed by reason or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ųjų
    -0.61
     purpoſe
    -0.59
     ſeveral
    -0.54
    parseFloat
    -0.53
     ſou
    -0.51
     ſame
    -0.51
     ſch
    -0.51
     Fø
    -0.50
     Kiedy
    -0.50
    μαστε
    -0.50
    POSITIVE LOGITS
     nahilalakip
    0.91
    GEBURTSDATUM
    0.77
    0.70
     cherchés
    0.66
     nakalista
    0.65
    RegressionTest
    0.64
     متعلقه
    0.64
     发表于
    0.63
     мәкал
    0.62
     Meksiku
    0.62
    Act Density 0.370%

    No Known Activations