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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HEST
    -0.13
    ÃĤ
    -0.13
     hazard
    -0.13
    iв
    -0.12
    apture
    -0.12
    apro
    -0.12
     balance
    -0.12
    aso
    -0.12
     (
    -0.12
    oda
    -0.12
    POSITIVE LOGITS
    quir
    0.17
    phia
    0.15
     Bernstein
    0.14
    çĻ¾
    0.13
    ãĥ¼ãĤ¹
    0.13
    ISIBLE
    0.13
    nbsp
    0.13
    å¼ı
    0.13
    qué
    0.13
    iez
    0.13
    Act Density 0.816%

    No Known Activations