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

    Neuronpedia

    INDEX
    Explanations

    percentages and numbers related to statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rav
    -0.74
    kefeller
    -0.62
    Attributes
    -0.61
    Redd
    -0.61
    åĤ
    -0.60
    Merit
    -0.60
    GROUP
    -0.58
    iden
    -0.58
    pload
    -0.57
     Renaissance
    -0.56
    POSITIVE LOGITS
    xual
    0.92
     ABV
    0.86
     percent
    0.79
    imet
    0.79
    percent
    0.75
    +)
    0.73
     utilization
    0.72
    iles
    0.70
    +.
    0.70
     humidity
    0.69
    Act Density 2.439%

    No Known Activations