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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "selected."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uar
    -0.16
    rior
    -0.16
    usan
    -0.16
     incl
    -0.15
    044
    -0.15
    ãn
    -0.14
    inar
    -0.14
     constit
    -0.14
    924
    -0.14
    uess
    -0.14
    POSITIVE LOGITS
    ↵↵
    0.17
    >>>(
    0.14
    اسب
    0.14
    çªģ
    0.14
    agus
    0.13
    NavController
    0.13
    662
    0.13
    icals
    0.13
    zahl
    0.13
    pcs
    0.13
    Act Density 0.016%

    No Known Activations