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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reporting or conveying information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ophers
    -0.68
    enta
    -0.66
    creen
    -0.66
    ococ
    -0.64
     wedge
    -0.64
    osate
    -0.63
    stad
    -0.61
    osi
    -0.59
     gauge
    -0.59
    wich
    -0.59
    POSITIVE LOGITS
    ufact
    0.86
    ounces
    0.81
     sightings
    0.81
    Crash
    0.77
     briefings
    0.68
    ribe
    0.66
    Reporting
    0.66
    è¦ļéĨĴ
    0.65
    lies
    0.65
     reports
    0.64
    Act Density 1.768%

    No Known Activations