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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an increase or emphasis on quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oud
    -0.16
    ogne
    -0.16
    uben
    -0.14
    isko
    -0.14
    ritch
    -0.14
    kest
    -0.14
    ourg
    -0.14
    rat
    -0.14
    buff
    -0.13
    çĨ
    -0.13
    POSITIVE LOGITS
    idges
    0.18
    isons
    0.16
    -than
    0.15
    mary
    0.15
    idge
    0.15
    -git
    0.14
    vari
    0.14
    pery
    0.14
    zes
    0.14
    -live
    0.14
    Act Density 0.021%

    No Known Activations