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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the relationship between different factors or elements in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idd
    -0.17
    imas
    -0.15
    ÑĨез
    -0.14
    hya
    -0.14
    stor
    -0.14
    atre
    -0.14
    IDL
    -0.13
    uforia
    -0.13
     Silva
    -0.13
    umont
    -0.13
    POSITIVE LOGITS
    isters
    0.15
     bình
    0.15
    åĩĢ
    0.14
    itus
    0.14
     anim
    0.14
    UZ
    0.14
     Hale
    0.14
    CNT
    0.14
     testName
    0.14
     Rubin
    0.13
    Act Density 0.017%

    No Known Activations