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

    Neuronpedia

    INDEX
    Explanations

    words related to merit or approval

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "mer" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.77
    ORY
    -0.72
    ONES
    -0.70
    URN
    -0.65
    Ĥİ
    -0.64
    Ĥª
    -0.64
     fixed
    -0.64
    ORN
    -0.63
    prototype
    -0.62
     Decay
    -0.61
    POSITIVE LOGITS
    cedes
    1.34
    maid
    1.20
    cial
    1.05
    folk
    0.99
    ited
    0.96
    idian
    0.93
    gers
    0.91
    iously
    0.90
    gue
    0.88
    ial
    0.84
    Act Density 0.003%

    No Known Activations