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

    Neuronpedia

    INDEX
    Explanations

    statistical patterns and relationships within the data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥªãĥ¼
    -0.16
    RIES
    -0.16
    æŁĦ
    -0.15
    avery
    -0.14
     Hunts
    -0.14
    imetype
    -0.14
    inae
    -0.13
     Greenwood
    -0.13
    avl
    -0.13
    ek
    -0.13
    POSITIVE LOGITS
    /Dk
    0.19
    irk
    0.18
    NamedQuery
    0.17
    plash
    0.16
    ñana
    0.15
    umont
    0.15
    aysia
    0.14
    òi
    0.14
     cazzo
    0.14
    /km
    0.13
    Act Density 0.330%

    No Known Activations