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

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and quantifiers in detailed explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sawyer
    -0.16
    uter
    -0.16
     Eden
    -0.15
    ῦ
    -0.15
    chl
    -0.15
    ancell
    -0.15
     punched
    -0.14
    trand
    -0.14
    invisible
    -0.14
    ãĤ·ãĥ§ãĥ³
    -0.14
    POSITIVE LOGITS
    leck
    0.16
    nga
    0.15
    /Dk
    0.14
     Haut
    0.14
    AXB
    0.14
    inez
    0.14
    PEnd
    0.14
    Topics
    0.14
    .inst
    0.14
    ácil
    0.14
    Act Density 0.005%

    No Known Activations