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

    Neuronpedia

    INDEX
    Explanations

    references to scientific processes and factors affecting results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "including" or "such"

    np_acts-logits-general · gemini-2.0-flash

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    either
    -0.79
    Either
    -0.73
     Either
    -0.69
     either
    -0.65
     propOrder
    -0.62
    ITHER
    -0.52
    rshire
    -0.52
    Hochspringen
    -0.50
     либо
    -0.49
    omiast
    -0.49
    POSITIVE LOGITS
     including
    2.22
     Including
    1.78
    including
    1.72
    Including
    1.70
     incluindo
    1.55
     INCLUDING
    1.54
     incluyendo
    1.45
     includes
    1.45
     include
    1.44
    包括
    1.36
    Act Density 0.312%

    No Known Activations