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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating lack of accountability or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inski
    -0.17
     edm
    -0.15
    .sym
    -0.14
    idlo
    -0.14
    atif
    -0.14
    ãģĵãģĿ
    -0.14
    /cpp
    -0.14
    ãĥ«ãĥĪ
    -0.13
    Å¡il
    -0.13
     mand
    -0.13
    POSITIVE LOGITS
    że
    0.16
     Bret
    0.15
     saturn
    0.14
     Thur
    0.14
    ç²¾
    0.14
    anda
    0.14
    omat
    0.14
    forced
    0.13
     Tham
    0.13
    unc
    0.13
    Act Density 0.239%

    No Known Activations