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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusivity or universality

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity and general appeal to audiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsu
    -0.67
    amide
    -0.62
    inventoryQuantity
    -0.61
     Miko
    -0.58
    Weak
    -0.58
     virginity
    -0.58
    olic
    -0.58
    hift
    -0.58
     Weak
    -0.58
    ãĤ¢
    -0.57
    POSITIVE LOGITS
     enjoyment
    0.94
     convenience
    0.89
     sake
    0.86
     purposes
    0.85
    ummies
    0.82
     amusement
    0.74
     satisfaction
    0.74
     viewing
    0.73
     download
    0.73
     eBook
    0.71
    Act Density 0.243%

    No Known Activations