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

    Neuronpedia

    INDEX
    Explanations

    specific names and places associated with individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elm
    -0.16
    adal
    -0.16
    iw
    -0.16
     majority
    -0.15
    jes
    -0.15
    mong
    -0.15
    agna
    -0.15
    ìĦľëĬĶ
    -0.15
    inters
    -0.15
    iap
    -0.14
    POSITIVE LOGITS
    serter
    0.21
    apolis
    0.18
    arily
    0.17
    aires
    0.15
    fov
    0.15
    Throwable
    0.15
    ALLY
    0.14
    uvre
    0.14
    airo
    0.14
    odzi
    0.14
    Act Density 0.349%

    No Known Activations