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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names related to people, places, or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    麦
    -0.16
    activex
    -0.15
    angel
    -0.15
    imum
    -0.15
    arges
    -0.14
    xfff
    -0.14
    iaux
    -0.14
    ildren
    -0.14
     Enumerator
    -0.14
    gere
    -0.14
    POSITIVE LOGITS
     bo
    0.21
    bo
    0.20
    Bo
    0.19
    -bo
    0.17
    BOOLE
    0.17
     boy
    0.16
     Boy
    0.16
    .bo
    0.16
     Boh
    0.16
    ÏĦÏī
    0.16
    Act Density 0.047%

    No Known Activations