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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connecting words that indicate relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itage
    -0.15
    mux
    -0.15
    isse
    -0.14
    ÙĬÙĥÙĬ
    -0.14
    gett
    -0.14
    ocuk
    -0.13
    è·
    -0.13
    ãĥŃãĥ³
    -0.13
    Cookie
    -0.13
    pty
    -0.13
    POSITIVE LOGITS
    .onView
    0.16
    oldem
    0.16
    .mx
    0.16
    anged
    0.15
    emon
    0.14
    éo
    0.14
    enha
    0.14
    оÑģк
    0.14
     Chall
    0.14
    ër
    0.14
    Act Density 0.002%

    No Known Activations