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

    Neuronpedia

    INDEX
    Explanations

    terms related to observation and measurement in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @[+][
    -0.67
    Darius
    -0.61
    jins
    -0.56
     Henn
    -0.56
    wyn
    -0.54
    Brittany
    -0.54
     Biggs
    -0.54
    意思
    -0.54
     A
    -0.53
    <eos>
    -0.52
    POSITIVE LOGITS
    observations
    1.11
     Observations
    1.07
     Observation
    1.03
     observations
    1.00
    Observations
    0.95
     observes
    0.95
     Observ
    0.94
     OBSERV
    0.93
     observers
    0.93
    OBSERV
    0.91
    Act Density 0.107%

    No Known Activations