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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions or protests

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "adjunct" and related variations in the context of education and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dru
    -0.75
    laws
    -0.72
     Zer
    -0.67
     Cub
    -0.67
    HOU
    -0.66
     Scouts
    -0.64
     release
    -0.64
     Walker
    -0.62
     Ale
    -0.61
     crates
    -0.61
    POSITIVE LOGITS
    unct
    3.14
    unction
    3.03
    unctions
    2.41
    acent
    1.61
    icult
    1.52
    uncture
    1.46
    acet
    1.41
    azeera
    1.23
    inent
    1.21
    ugal
    1.18
    Act Density 0.033%

    No Known Activations