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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating denial or contradiction in narratives

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

    belief and what people know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.60
     surla
    -0.50
     ModelExpression
    -0.48
    SOUNDBITE
    -0.47
     témoins
    -0.47
     GenerationType
    -0.47
    AnchorStyles
    -0.47
    ContentAsync
    -0.46
     témoignages
    -0.45
    หน้านี้
    -0.45
    POSITIVE LOGITS
     otomatig
    0.44
    endphp
    0.42
    Хьажоргаш
    0.38
    цездатний
    0.35
     об
    0.35
    ksi
    0.34
     Tac
    0.33
     بوس
    0.33
    Tac
    0.32
    KSI
    0.32
    Act Density 0.087%

    No Known Activations