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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating impossibility or absence of options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Byl
    -0.16
     zdrav
    -0.15
    isten
    -0.15
     ÙĪاØŃ
    -0.15
    venida
    -0.14
    øre
    -0.14
    ãĥ³ãĥĨ
    -0.14
    inal
    -0.14
    ENTE
    -0.14
    ason
    -0.14
    POSITIVE LOGITS
    mium
    0.18
    ê·ľ
    0.15
    morgan
    0.14
    ï¸
    0.14
    advisor
    0.13
    146
    0.13
     braces
    0.13
    lland
    0.13
    åģļ
    0.13
     tzv
    0.13
    Act Density 0.034%

    No Known Activations