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

    Neuronpedia

    INDEX
    Explanations

    the word "aide" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to aides in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aval
    -0.80
    avery
    -0.71
    odus
    -0.71
    Bul
    -0.67
    Population
    -0.66
    Ü
    -0.65
    é¾
    -0.64
    rights
    -0.64
    acular
    -0.62
    PASS
    -0.62
    POSITIVE LOGITS
     aide
    1.11
     Huma
    0.95
    maid
    0.92
     aides
    0.91
    wife
    0.84
     staffer
    0.82
     tasked
    0.81
     adviser
    0.80
     counsel
    0.78
     advisor
    0.78
    Act Density 0.008%

    No Known Activations