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

    Neuronpedia

    INDEX
    Explanations

    references to high values, particularly in the context of health and risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zcze
    -0.15
    adu
    -0.14
    sav
    -0.14
    bral
    -0.14
    oria
    -0.13
     wikipedia
    -0.13
    Eu
    -0.13
    896
    -0.13
    733
    -0.13
    iphone
    -0.13
    POSITIVE LOGITS
    rid
    0.15
    ware
    0.15
    okin
    0.15
    unge
    0.14
    utow
    0.14
    ridge
    0.14
    immer
    0.13
     неÑģк
    0.13
    STRU
    0.13
    StandardItem
    0.13
    Act Density 0.074%

    No Known Activations