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

    Neuronpedia

    INDEX
    Explanations

    references to data collection and verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipro
    -0.15
     ekip
    -0.14
    sein
    -0.14
    itom
    -0.14
    UBLISH
    -0.14
    amat
    -0.14
     Fragen
    -0.14
    è©
    -0.14
    _dual
    -0.13
    åĿĤ
    -0.13
    POSITIVE LOGITS
     sources
    0.27
    sources
    0.21
     direct
    0.19
    ources
    0.19
     Sources
    0.18
     official
    0.18
     previous
    0.18
     reliable
    0.17
     relevant
    0.17
     observation
    0.17
    Act Density 0.233%

    No Known Activations