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

    Neuronpedia

    INDEX
    Explanations

    narrative structures and operational details in a context of description or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?).
    -0.66
     thereof
    -0.63
     }}
    -0.63
    =]
    -0.62
    .).
    -0.58
    SPONSORED
    -0.57
    )."
    -0.55
     theirs
    -0.55
    %).
    -0.55
     lately
    -0.54
    POSITIVE LOGITS
     Proced
    0.72
     procedural
    0.63
     chronological
    0.60
    intensive
    0.56
     hinges
    0.56
     proced
    0.56
     modular
    0.55
     Kickstarter
    0.54
     parchment
    0.54
     rectangular
    0.54
    Act Density 0.452%

    No Known Activations