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

    Neuronpedia

    INDEX
    Explanations

    instances where a request for comment is made but not immediately responded to

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to requests for comments or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ranked
    -0.68
     ingred
    -0.64
     impro
    -0.62
    oiler
    -0.61
     beware
    -0.59
    ilic
    -0.57
    emies
    -0.56
    rouse
    -0.56
    Maps
    -0.56
     sacrific
    -0.56
    POSITIVE LOGITS
     Wednesday
    0.92
     Tuesday
    0.91
     Thursday
    0.90
     Friday
    0.88
     Monday
    0.87
     regarding
    0.86
     emailed
    0.83
     Saturday
    0.78
     citing
    0.78
     yesterday
    0.77
    Act Density 0.063%

    No Known Activations