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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leadership roles

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "captain."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mia
    -0.69
    heres
    -0.69
     Beir
    -0.69
    imb
    -0.68
    closed
    -0.67
    puting
    -0.65
    ulia
    -0.64
    itten
    -0.64
    ocene
    -0.64
     Estate
    -0.64
    POSITIVE LOGITS
     captain
    1.12
    cies
    0.96
     captains
    0.89
    cy
    0.87
    esses
    0.86
     Captain
    0.80
    士
    0.79
    TAIN
    0.75
     praises
    0.73
    Captain
    0.72
    Act Density 0.009%

    No Known Activations