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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intended purpose or design in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.75
    ⓧ
    -0.73
     مشين
    -0.72
     كومونز
    -0.69
     disponibilités
    -0.67
    WEBPACK
    -0.66
    Humble
    -0.64
     disambiguazione
    -0.63
     препратки
    -0.62
    AndEndTag
    -0.60
    POSITIVE LOGITS
     designed
    1.09
     intended
    1.00
    designed
    0.90
     meant
    0.88
     Designed
    0.88
    Intended
    0.87
    intended
    0.85
    Designed
    0.84
    meant
    0.78
     aimed
    0.77
    Act Density 0.172%

    No Known Activations