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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "welcome."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Or
    -0.39
    DSS
    -0.34
     Nicholas
    -0.34
    みる
    -0.33
     D
    -0.33
     SS
    -0.32
    Попис
    -0.32
     '{@
    -0.32
     ex
    -0.31
    úl
    -0.31
    POSITIVE LOGITS
     aboard
    0.92
    arangay
    0.62
     mukaan
    0.62
     braccia
    0.62
     pouvoit
    0.60
     Willkommen
    0.58
     feroit
    0.58
     bienvenue
    0.58
    elcome
    0.57
     bienvenida
    0.57
    Act Density 0.072%

    No Known Activations