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

    Neuronpedia

    INDEX
    Explanations

    references to studios and related facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ned
    -0.22
    fully
    -0.21
    ment
    -0.18
    ning
    -0.17
    nya
    -0.17
    markets
    -0.17
    lest
    -0.17
    mente
    -0.17
    tra
    -0.16
    ures
    -0.16
    POSITIVE LOGITS
    /gallery
    0.22
    elling
    0.20
    -wide
    0.19
    alink
    0.18
     space
    0.18
    /lab
    0.18
    /shop
    0.18
     apartment
    0.17
    Binder
    0.17
    -ap
    0.16
    Act Density 0.030%

    No Known Activations