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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal agreements and liabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     :↵
    -0.15
     Âł
    -0.15
     
    -0.14
     :↵↵
    -0.14
     Dann
    -0.13
     termin
    -0.13
    unge
    -0.13
     Earth
    -0.13
    Ãĥ
    -0.13
    '
    -0.12
    POSITIVE LOGITS
     \↵
    0.37
    \↵
    0.32
    ,\↵
    0.29
     &↵
    0.25
     \č↵
    0.23
     "\↵
    0.23
     ${↵
    0.20
    ãĢģ↵
    0.19
    '+↵
    0.18
    ØĮ↵
    0.18
    Act Density 5.746%

    No Known Activations