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

    Neuronpedia

    INDEX
    Explanations

    references to statistics or numerical data related to population trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     promptly
    -0.70
     upstairs
    -0.69
    iton
    -0.69
     himself
    -0.67
     inactive
    -0.65
     undermin
    -0.64
     Creed
    -0.64
     prosec
    -0.64
     overth
    -0.64
     citiz
    -0.64
    POSITIVE LOGITS
    ³³³³³³³³
    0.94
    ³³³³³³³³³³³³³³³³
    0.93
    Consider
    0.92
    ³³³
    0.92
    ³³³³
    0.90
    Its
    0.88
    Imagine
    0.83
    Research
    0.82
    Unless
    0.82
    Econom
    0.81
    Act Density 0.266%

    No Known Activations