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

    Neuronpedia

    INDEX
    Explanations

    references to councils and discussions relating to oversight and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     underneath
    -0.51
     ​​
    -0.49
    ❷
    -0.49
    -0.49
     Bomber
    -0.46
     Gastro
    -0.46
     innocently
    -0.45
     engulfed
    -0.45
    LUT
    -0.44
    ombus
    -0.43
    POSITIVE LOGITS
     Council
    0.78
     COUNCIL
    0.75
     council
    0.74
    Council
    0.69
    council
    0.60
    pecabe
    0.59
    fören
    0.54
     models
    0.52
     study
    0.52
     versions
    0.52
    Act Density 0.316%

    No Known Activations