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

    Neuronpedia

    INDEX
    Explanations

    references to contrasting or supplementary elements or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    οÏĤ
    -0.16
    amba
    -0.15
    ling
    -0.14
    led
    -0.14
    vet
    -0.14
    ãģ£ãģı
    -0.14
    eya
    -0.13
    illes
    -0.13
    ottes
    -0.13
    les
    -0.13
    POSITIVE LOGITS
    rek
    0.18
    hand
    0.17
     two
    0.17
    ws
    0.17
    idge
    0.17
    world
    0.16
    iero
    0.15
    ero
    0.15
    est
    0.15
    woord
    0.15
    Act Density 0.039%

    No Known Activations