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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the conclusion or ending of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ises
    -0.15
    plib
    -0.15
     Dawn
    -0.15
    mts
    -0.15
    िà¤
    -0.15
     early
    -0.15
    èµ·æĿ¥
    -0.15
     Early
    -0.15
     dawn
    -0.14
    uese
    -0.14
    POSITIVE LOGITS
     credits
    0.18
    /start
    0.17
    ulton
    0.17
    ovich
    0.15
    orph
    0.15
     ustanov
    0.15
    credits
    0.15
    ENCIL
    0.14
    mast
    0.14
    atest
    0.14
    Act Density 0.031%

    No Known Activations