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

    Neuronpedia

    INDEX
    Explanations

    words related to generating or creating something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "generate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nee
    -0.81
    hai
    -0.77
    mare
    -0.74
    yer
    -0.71
    hid
    -0.68
    say
    -0.68
    uku
    -0.68
    gerald
    -0.66
    phis
    -0.65
    phia
    -0.64
    POSITIVE LOGITS
     generators
    0.85
     kWh
    0.84
     generate
    0.81
     electricity
    0.80
     generates
    0.76
     revenue
    0.75
     generated
    0.74
     generator
    0.74
    generated
    0.73
     generating
    0.72
    Act Density 0.028%

    No Known Activations