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

    Neuronpedia

    INDEX
    Explanations

    expressions of criticism and negative evaluations regarding various arguments and statements

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

    falsity/absurdity

    np_acts-logits-general · gemini-2.0-flash

    is absurd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.76
     EconPapers
    -0.69
    GraphicsUnit
    -0.64
     puissiez
    -0.55
     hés
    -0.53
     évent
    -0.51
     spared
    -0.50
     gela
    -0.47
     referenties
    -0.47
    telser
    -0.47
    POSITIVE LOGITS
     ridiculous
    0.88
     absurd
    0.78
     ludicrous
    0.77
     absurdity
    0.75
    icrous
    0.74
     uncons
    0.74
     absurdo
    0.73
     utterly
    0.70
     unacceptable
    0.69
     gross
    0.68
    Act Density 0.700%

    No Known Activations