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

    Neuronpedia

    INDEX
    Explanations

    references to specific years, particularly in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agner
    -0.15
    icable
    -0.15
    antic
    -0.15
    ying
    -0.15
    abbix
    -0.15
    ÑĢе
    -0.15
    ova
    -0.14
    gid
    -0.14
    cce
    -0.14
    ubes
    -0.14
    POSITIVE LOGITS
    hart
    0.18
    alendar
    0.16
    vier
    0.15
    rim
    0.15
    quent
    0.15
    ureau
    0.14
    esti
    0.14
    ukes
    0.14
    ograph
    0.14
    Äĥm
    0.14
    Act Density 0.010%

    No Known Activations