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

    Neuronpedia

    INDEX
    Explanations

    descriptors and phrases related to authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nish
    -0.16
    .lv
    -0.16
    arga
    -0.14
    ilha
    -0.14
    iw
    -0.14
    avn
    -0.14
    iesel
    -0.13
    edn
    -0.13
    asses
    -0.13
     Attention
    -0.13
    POSITIVE LOGITS
    ardu
    0.16
    /auth
    0.15
    ìĸ´ëĤĺ
    0.15
    ipse
    0.15
    uggle
    0.14
    izza
    0.14
    heed
    0.14
    WindowState
    0.14
    yntax
    0.14
    ktor
    0.14
    Act Density 0.005%

    No Known Activations