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

    Neuronpedia

    INDEX
    Explanations

    discussions about programming or technical implementation issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mare
    -0.16
    illez
    -0.15
    aight
    -0.14
    漫
    -0.14
    c
    -0.13
    253
    -0.13
     Barker
    -0.13
    ought
    -0.13
    hab
    -0.13
    okus
    -0.13
    POSITIVE LOGITS
    agrams
    0.15
    eya
    0.14
    onu
    0.14
    ensch
    0.14
    orra
    0.14
    anzeigen
    0.14
    ptime
    0.13
    ÑĥÑĢа
    0.13
    ropa
    0.13
    vice
    0.13
    Act Density 0.256%

    No Known Activations