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

    Neuronpedia

    INDEX
    Explanations

    references to mechanisms of production and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cul
    -0.14
    iste
    -0.14
     Census
    -0.14
     Laur
    -0.14
     imported
    -0.14
     recent
    -0.14
     Dyn
    -0.14
     clause
    -0.13
     activity
    -0.13
     blow
    -0.13
    POSITIVE LOGITS
     produced
    0.18
     OUTPUT
    0.17
     output
    0.17
    -production
    0.16
    neh
    0.16
     outputs
    0.16
    Outcome
    0.16
    oleans
    0.15
    _OUTPUT
    0.15
     Creation
    0.15
    Act Density 0.133%

    No Known Activations