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

    Neuronpedia

    INDEX
    Explanations

    phrases related to generating content, revenue, or specific outcomes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    nee
    -0.87
    hai
    -0.83
    mare
    -0.78
    say
    -0.77
    yer
    -0.74
    rock
    -0.72
    hid
    -0.70
    gerald
    -0.68
    phia
    -0.68
    bones
    -0.67
    POSITIVE LOGITS
     generate
    0.88
     generators
    0.86
     kWh
    0.83
     electricity
    0.82
     revenue
    0.81
     generates
    0.80
     generated
    0.78
     generating
    0.78
     generator
    0.75
    assets
    0.74
    Act Density 7.804%

    No Known Activations