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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to credibility and inconsistencies in testimonies and evidence

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

    inconsistency, improbability, believability, fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eſt
    -0.30
     preview
    -0.28
     lé
    -0.27
    KindOfClass
    -0.27
     ſtate
    -0.27
    HasAnnotation
    -0.26
     orto
    -0.26
    threshold
    -0.26
     influ
    -0.25
     invari
    -0.25
    POSITIVE LOGITS
    TagMode
    0.65
     kasarigan
    0.61
    featureID
    0.60
    脚注の使い方
    0.59
     pinulongan
    0.58
     inconsistencies
    0.57
     intptr
    0.57
    lanca
    0.56
    bability
    0.56
     believable
    0.56
    Act Density 0.551%

    No Known Activations