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

    Neuronpedia

    INDEX
    Explanations

    references to scientific and academic entities or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uce
    -0.18
     guise
    -0.15
    ken
    -0.15
    .Selenium
    -0.15
    evin
    -0.15
    gether
    -0.15
    ppard
    -0.14
    uo
    -0.14
    loys
    -0.14
    ORAGE
    -0.14
    POSITIVE LOGITS
    ierrez
    0.17
    ibraltar
    0.17
     phép
    0.17
    SSIP
    0.16
    bread
    0.16
    äºĪ
    0.16
    father
    0.15
    roupon
    0.15
    reich
    0.15
    ospels
    0.15
    Act Density 1.432%

    No Known Activations