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

    Neuronpedia

    INDEX
    Explanations

    phrases related to origin and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.54
     بيها
    -0.52
     Wicidata
    -0.52
    AsUp
    -0.50
     <<<<<<<<<<<<<<
    -0.48
    Démographie
    -0.48
     ModelExpression
    -0.47
    PasswordEncoder
    -0.45
     Monfieur
    -0.45
     NSCoder
    -0.45
    POSITIVE LOGITS
     originate
    2.23
     originates
    2.22
     origin
    2.17
     originated
    1.97
     Origin
    1.94
    origin
    1.94
     originating
    1.92
    Origin
    1.89
     origins
    1.85
     berasal
    1.81
    Act Density 1.207%

    No Known Activations