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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.16
     ÐĴик
    -0.16
     crackers
    -0.16
    aspers
    -0.15
    phylum
    -0.15
     British
    -0.15
     McKin
    -0.15
     Mediterr
    -0.15
    British
    -0.15
    lef
    -0.14
    POSITIVE LOGITS
     boy
    0.23
    boy
    0.23
     Suz
    0.22
     Grand
    0.22
     Princip
    0.22
     Mus
    0.21
     Nov
    0.21
     Lith
    0.21
     Kiev
    0.20
    -boy
    0.19
    Act Density 0.018%

    No Known Activations