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

    Neuronpedia

    INDEX
    Explanations

    structured data patterns, particularly in tabular formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIC
    -0.14
    hana
    -0.14
    ucci
    -0.14
    otta
    -0.14
    ndo
    -0.14
    hoe
    -0.13
    éĻµ
    -0.13
    cé
    -0.13
    nech
    -0.13
    åģ¥
    -0.13
    POSITIVE LOGITS
    0.17
    ount
    0.17
      č↵
    0.17
    au
    0.16
      ↵
    0.16
    orts
    0.16
      ↵↵
    0.15
      č↵č↵
    0.15
    #ad
    0.15
    ¿
    0.14
    Act Density 0.058%

    No Known Activations