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

    Neuronpedia

    INDEX
    Explanations

    phrases related to generation or creation

    oai_token-act-pair · gpt-3.5-turbo

    the term "generate" and its variations, indicating a focus on creation or production contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nee
    -0.78
    hai
    -0.75
    say
    -0.69
    mare
    -0.68
    phis
    -0.67
    yer
    -0.65
    done
    -0.65
    gerald
    -0.65
    rock
    -0.62
    kov
    -0.61
    POSITIVE LOGITS
     generate
    0.85
     kWh
    0.84
     generates
    0.80
    vernment
    0.79
     generating
    0.76
    idable
    0.75
     generators
    0.75
    ãĤº
    0.74
     generated
    0.72
     electricity
    0.71
    Act Density 0.030%

    No Known Activations