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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heck
    -0.15
    wick
    -0.15
    TypeInfo
    -0.15
    ntl
    -0.15
     èĩ
    -0.14
    loat
    -0.14
    imson
    -0.14
    ovan
    -0.14
    lý
    -0.14
    antee
    -0.14
    POSITIVE LOGITS
     itself
    0.15
     everywhere
    0.15
    apon
    0.14
     meaning
    0.14
     VÆ°Æ¡ng
    0.14
    olis
    0.14
    ائ
    0.13
    ierz
    0.13
    ÑĥлÑı
    0.13
    atural
    0.13
    Act Density 0.339%

    No Known Activations