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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating increasing quantities or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cks
    -0.16
    agnostic
    -0.16
    isty
    -0.15
    bons
    -0.15
    lub
    -0.14
    ع
    -0.14
    rijk
    -0.14
     Inventory
    -0.14
    iced
    -0.14
    ZA
    -0.14
    POSITIVE LOGITS
    /down
    0.19
    ois
    0.17
    aeda
    0.17
    icontrol
    0.15
    #ab
    0.15
    adr
    0.15
     fungi
    0.15
    datable
    0.15
    «
    0.14
    oj
    0.14
    Act Density 0.038%

    No Known Activations