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

    Neuronpedia

    INDEX
    Explanations

    tokens related to numerical values and upgrades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agne
    -0.18
    831
    -0.16
    odal
    -0.14
    azzi
    -0.14
    ianne
    -0.14
    agna
    -0.14
    anchise
    -0.14
    pora
    -0.14
    odial
    -0.14
    276
    -0.14
    POSITIVE LOGITS
    anim
    0.17
    ports
    0.15
    brids
    0.15
    /packages
    0.15
     Sabha
    0.15
    sst
    0.14
    antt
    0.14
    nex
    0.14
    ìłĿ
    0.14
    orest
    0.13
    Act Density 0.003%

    No Known Activations