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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of observing or making observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    templateUrl
    -0.65
     P
    -0.60
    </h1>
    -0.55
    P
    -0.55
    jins
    -0.55
     A
    -0.54
     All
    -0.54
    <eos>
    -0.54
     Brittany
    -0.53
     The
    -0.53
    POSITIVE LOGITS
     observations
    2.02
     observation
    1.99
     OBSERV
    1.99
     Observation
    1.98
     observes
    1.97
     observe
    1.97
     Observations
    1.94
    observations
    1.93
     observed
    1.92
     obser
    1.90
    Act Density 0.067%

    No Known Activations