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

    Neuronpedia

    INDEX
    Explanations

    verbs related to creating or generating something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "produce" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.81
    imb
    -0.70
    leans
    -0.69
    nee
    -0.68
    bi
    -0.68
    cknow
    -0.67
    phe
    -0.64
    istani
    -0.64
    stra
    -0.63
    zai
    -0.62
    POSITIVE LOGITS
    ivity
    0.95
    女
    0.87
    Output
    0.81
    encers
    0.81
    ivities
    0.76
     offspring
    0.73
     prod
    0.72
     output
    0.71
     outputs
    0.71
     produce
    0.70
    Act Density 0.042%

    No Known Activations