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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or doubt

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

    expressing belief or suspicion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.50
     ansatte
    -0.48
     autorytatywna
    -0.48
    parsedMessage
    -0.44
    ritsar
    -0.43
     againſt
    -0.43
     snippetHide
    -0.42
     Perſ
    -0.42
    baguna
    -0.42
    ſelf
    -0.42
    POSITIVE LOGITS
    setVerticalGroup
    0.42
    ImageContext
    0.42
     believe
    0.41
     maybe
    0.39
     thinks
    0.39
     think
    0.38
    ValueGenerated
    0.37
     creen
    0.37
     believes
    0.37
    XmlRootElement
    0.37
    Act Density 0.280%

    No Known Activations