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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns representing groups of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and their relationships or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DX
    -0.58
    iverse
    -0.56
    zan
    -0.53
    versible
    -0.52
    Prev
    -0.52
     Nadu
    -0.52
    GO
    -0.51
    NOR
    -0.50
     compr
    -0.49
    Temperature
    -0.49
    POSITIVE LOGITS
     of
    1.59
     thereof
    1.54
    of
    1.26
    Of
    1.22
     Of
    1.15
    oft
    1.11
     OF
    1.10
    hip
    0.93
    paces
    0.90
    hips
    0.84
    Act Density 0.272%

    No Known Activations