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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numbers, indicating a focus on structure or formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adir
    -0.16
    èģŀ
    -0.15
    kir
    -0.15
    ?url
    -0.15
    pie
    -0.15
    ndern
    -0.14
    pa
    -0.14
     SEQ
    -0.14
    leo
    -0.14
    .pa
    -0.14
    POSITIVE LOGITS
     Werner
    0.15
    568
    0.15
    uars
    0.15
    lassian
    0.15
    418
    0.15
    Č↵
    0.14
    ramer
    0.14
    ipse
    0.14
    ymous
    0.14
     oto
    0.14
    Act Density 0.004%

    No Known Activations