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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fact" and related phrases indicating certainty or truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙģت
    -0.17
     else
    -0.16
    EventListener
    -0.15
    anded
    -0.15
    adolu
    -0.15
    stras
    -0.14
    theless
    -0.14
    ZE
    -0.13
    sea
    -0.13
    EMPLARY
    -0.13
    POSITIVE LOGITS
     fact
    0.22
    oring
    0.19
    um
    0.18
    ually
    0.17
    itious
    0.17
    eur
    0.17
    icity
    0.16
    oid
    0.16
     Fact
    0.16
    ularity
    0.16
    Act Density 0.017%

    No Known Activations