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

    Neuronpedia

    INDEX
    Explanations

    information related to statistics and data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to specific groups or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itness
    -0.66
    ELL
    -0.61
    ANA
    -0.59
    atson
    -0.57
    aternal
    -0.57
    isse
    -0.55
    anus
    -0.54
    NG
    -0.53
    ENTS
    -0.52
    Pand
    -0.52
    POSITIVE LOGITS
    of
    1.46
     of
    1.44
    Of
    1.19
     OF
    1.17
     Of
    1.17
     thereof
    1.14
    OF
    1.00
    oft
    0.88
    76561
    0.78
    )=(
    0.68
    Act Density 0.242%

    No Known Activations