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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases indicating levels or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.84
     Italijani
    -0.76
    saraba
    -0.66
    setVerticalGroup
    -0.66
     betweenstory
    -0.65
    DockStyle
    -0.64
     queſta
    -0.64
    parsedMessage
    -0.63
     للمعارف
    -0.62
    makeConstraints
    -0.61
    POSITIVE LOGITS
     level
    1.09
     Level
    0.83
     levels
    0.83
     LEVEL
    0.81
     floor
    0.80
     display
    0.73
    level
    0.73
    Level
    0.72
    LEVEL
    0.69
     niveau
    0.67
    Act Density 0.266%

    No Known Activations