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

    Neuronpedia

    INDEX
    Explanations

    words related to generators

    oai_token-act-pair · gpt-3.5-turbo

    terms related to generators and generating processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.81
    clair
    -0.79
    odore
    -0.73
    eneg
    -0.73
    een
    -0.72
    nee
    -0.72
    ean
    -0.70
    say
    -0.69
    Sea
    -0.68
    chie
    -0.68
    POSITIVE LOGITS
     generator
    0.90
     generators
    0.88
    vernment
    0.84
     Generator
    0.73
     generate
    0.72
    ption
    0.69
    andom
    0.69
    osity
    0.68
     generating
    0.67
     fodder
    0.67
    Act Density 0.010%

    No Known Activations