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

    Neuronpedia

    INDEX
    Explanations

    phrases that express conditionality or uncertainty in decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.70
    Personendaten
    -0.65
     étoit
    -0.64
     zoude
    -0.60
    RegistryLite
    -0.59
     élector
    -0.59
     EconPapers
    -0.58
     cliquant
    -0.57
     AssemblyVersion
    -0.57
     zijne
    -0.57
    POSITIVE LOGITS
     make
    1.09
     decide
    1.09
     use
    1.07
     give
    1.07
     get
    1.07
     take
    1.06
     find
    1.05
     create
    1.05
     choose
    1.04
     go
    1.03
    Act Density 1.788%

    No Known Activations