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

    Neuronpedia

    INDEX
    Explanations

    parentheses and numbers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sworth
    -0.16
    epad
    -0.15
    end
    -0.14
    kah
    -0.14
    ardless
    -0.14
    iere
    -0.14
    prite
    -0.13
    enheim
    -0.13
    arro
    -0.13
     overs
    -0.13
    POSITIVE LOGITS
    itty
    0.19
    /generated
    0.18
     åĽ
    0.16
     aka
    0.15
    imer
    0.15
    еви
    0.15
     Hip
    0.14
    erb
    0.14
    ÙĦا
    0.14
    ruc
    0.13
    Act Density 0.039%

    No Known Activations