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

    Neuronpedia

    INDEX
    Explanations

    terms related to factual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.52
     createState
    -0.47
    LookAnd
    -0.42
    发表于
    -0.37
    Portail
    -0.37
    WriteBarrier
    -0.37
    Input
    -0.36
    -0.36
     خارجية
    -0.35
    jsxFileName
    -0.35
    POSITIVE LOGITS
     tele
    0.83
    sustainability
    0.71
     sustainability
    0.68
     facts
    0.67
     Sustainability
    0.66
    sustainable
    0.66
     FACTS
    0.66
     Fakten
    0.66
    Tele
    0.65
     Tele
    0.65
    Act Density 0.061%

    No Known Activations