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

    Neuronpedia

    INDEX
    Explanations

    negative contractions and their usage in informal contexts

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

    don't/doesn't/wouldn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olerance
    -0.39
    ScopeManager
    -0.34
    意义
    -0.33
    VALIDATE
    -0.32
     respecto
    -0.32
     sentimentos
    -0.32
     adecu
    -0.31
     ministres
    -0.31
     sentimientos
    -0.31
     especific
    -0.31
    POSITIVE LOGITS
     humorous
    0.84
     quirky
    0.82
     humor
    0.79
     playful
    0.74
     comedic
    0.74
     humour
    0.73
     witty
    0.73
     whimsical
    0.73
     satirical
    0.72
    humor
    0.71
    Act Density 0.024%

    No Known Activations