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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or strong emphasis in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uner
    -0.15
    erson
    -0.15
    ç§
    -0.15
     absence
    -0.15
    elli
    -0.14
     application
    -0.14
     Accept
    -0.14
    ÙĪرا
    -0.14
    elligence
    -0.14
    uz
    -0.14
    POSITIVE LOGITS
    jang
    0.16
    -names
    0.15
    .datatables
    0.15
    .scalablytyped
    0.14
    fault
    0.14
    .updateDynamic
    0.14
    .EMPTY
    0.14
    \Doctrine
    0.14
     pParent
    0.14
    ãĥ¼ãĥĬ
    0.14
    Act Density 0.036%

    No Known Activations