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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "name" and variations of "title."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sei
    -0.16
    oui
    -0.14
     adlı
    -0.14
    heim
    -0.14
    eties
    -0.14
    ampo
    -0.14
    elow
    -0.14
     Hive
    -0.13
    562
    -0.13
    Named
    -0.13
    POSITIVE LOGITS
    éĢļãĤĬ
    0.24
    plates
    0.22
     given
    0.22
    plate
    0.21
     chosen
    0.21
    ake
    0.20
     sake
    0.19
    given
    0.19
    chosen
    0.18
    ì§ĵ
    0.18
    Act Density 0.066%

    No Known Activations