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

    Neuronpedia

    INDEX
    Explanations

    references to structure and organization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ottes
    -0.17
    obe
    -0.15
     çı
    -0.15
    áze
    -0.15
    embre
    -0.14
    OMPI
    -0.14
    uard
    -0.14
     Colbert
    -0.14
    áo
    -0.14
     паÑĢа
    -0.14
    POSITIVE LOGITS
    /ar
    0.22
     ar
    0.20
     Ar
    0.19
    -ar
    0.18
    .Ar
    0.17
    (ar
    0.16
     AR
    0.16
    Ar
    0.16
    openh
    0.16
    .AR
    0.15
    Act Density 0.104%

    No Known Activations