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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of "nothing" or insignificance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agli
    -0.15
    WAYS
    -0.14
     Slater
    -0.14
    WAY
    -0.14
    udem
    -0.13
    upp
    -0.13
    ulis
    -0.13
    ëĭ¨
    -0.13
    mont
    -0.13
    serv
    -0.13
    POSITIVE LOGITS
     else
    0.20
    ness
    0.18
    else
    0.18
    burger
    0.18
    icias
    0.17
    issant
    0.16
    /no
    0.14
    inke
    0.14
    alamat
    0.14
    epad
    0.14
    Act Density 0.029%

    No Known Activations