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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating estimates or approximations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Descriptor
    -0.15
     Joi
    -0.15
    oÅĻ
    -0.15
    ocoder
    -0.15
    ÐĶÐļ
    -0.14
    stown
    -0.14
     oslo
    -0.14
    orsi
    -0.14
    ilos
    -0.14
     pearl
    -0.14
    POSITIVE LOGITS
    ernel
    0.17
     Grant
    0.14
    æŁ±
    0.14
    tec
    0.14
     Be
    0.13
    mis
    0.13
     Derby
    0.13
    tek
    0.13
    llib
    0.13
     ÑĢавно
    0.13
    Act Density 0.050%

    No Known Activations