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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations or countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ResourceManager
    -0.16
    coop
    -0.15
    immer
    -0.15
    ertia
    -0.15
    iona
    -0.14
     kabil
    -0.14
     Mansion
    -0.14
    klä
    -0.14
     sm
    -0.14
     subjective
    -0.14
    POSITIVE LOGITS
    iche
    0.16
    ERIC
    0.14
    oci
    0.14
    uste
    0.14
    IDER
    0.14
    itan
    0.14
    akes
    0.14
    ÙĪÙĦÙĬÙĪ
    0.14
    References
    0.13
     Thumb
    0.13
    Act Density 0.023%

    No Known Activations