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

    Neuronpedia

    INDEX
    Explanations

    specific past tense verbs denoting actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĮĴ
    -0.16
    ãĥ³ãĥ
    -0.15
    angel
    -0.15
    ¦¬
    -0.15
    682
    -0.14
    елей
    -0.14
    achu
    -0.14
    801
    -0.14
     Fal
    -0.14
    ural
    -0.13
    POSITIVE LOGITS
     zero
    0.17
    0
    0.15
     nil
    0.15
    eries
    0.14
    URLConnection
    0.14
     Nil
    0.14
    yor
    0.13
     nothing
    0.13
     Blueprint
    0.13
    ائÙģ
    0.13
    Act Density 0.016%

    No Known Activations