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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to numerical data, measurements, or quantitative descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     all
    -0.45
     general
    -0.42
     im
    -0.40
    прав
    -0.40
    nim
    -0.40
    -
    -0.40
    ,
    -0.40
    {{
    -0.38
    .
    -0.38
     forever
    -0.36
    POSITIVE LOGITS
    AddTagHelper
    0.97
     '\\;'
    0.93
    RectangleBorder
    0.88
     propOrder
    0.85
    rungsseite
    0.83
     مرئيه
    0.82
    Rhestr
    0.82
    Попис
    0.82
     auffi
    0.82
    dafx
    0.80
    Act Density 0.755%

    No Known Activations