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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strengths and advantages in research or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "that" or "in" and meaning "the fact."

    np_acts-logits-general · gemini-2.0-flash

    is that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    scrapy
    -0.72
     neceff
    -0.65
     neceſſ
    -0.63
    !("{}",
    -0.63
     neceffary
    -0.63
    MENAFN
    -0.63
    ThroughAttribute
    -0.61
    TestingModule
    -0.59
    tanleria
    -0.56
    ichier
    -0.54
    POSITIVE LOGITS
     faptul
    0.72
     because
    0.68
     ligiloj
    0.67
    ValueStyle
    0.66
     karena
    0.65
     kenyataan
    0.65
     notare
    0.63
     Tatsache
    0.63
     bahwa
    0.61
     fact
    0.60
    Act Density 0.268%

    No Known Activations