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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Bon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PasswordEncoder
    -0.17
    eah
    -0.17
    ulis
    -0.16
    ırı
    -0.16
    esan
    -0.15
    eum
    -0.15
    phon
    -0.15
    /lang
    -0.15
    ãĤīãģĹ
    -0.14
    heet
    -0.14
    POSITIVE LOGITS
    anza
    0.22
    ny
    0.22
    iface
    0.21
     bon
    0.21
    kers
    0.20
    ÄĽk
    0.20
    anno
    0.18
     mile
    0.18
    ycastle
    0.18
     Bon
    0.17
    Act Density 0.010%

    No Known Activations