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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural elements in code and text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entropy
    -0.16
    tl
    -0.15
    ickle
    -0.15
     fran
    -0.15
    dsl
    -0.15
    odos
    -0.15
    oty
    -0.14
    annis
    -0.14
     Gale
    -0.14
     entropy
    -0.14
    POSITIVE LOGITS
    \<^
    0.17
    ãģĵãģĿ
    0.16
     Banner
    0.14
    缮
    0.14
    ÅĪ
    0.13
    itude
    0.13
    ķĮ
    0.13
     Ryder
    0.13
     Baldwin
    0.13
    onium
    0.13
    Act Density 0.001%

    No Known Activations