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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a state of being or characteristics associated with descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orum
    -0.16
    /Internal
    -0.16
    oop
    -0.15
    arda
    -0.15
    uai
    -0.15
    à¥Ĥद
    -0.15
     decomposition
    -0.15
    -placeholder
    -0.15
    arius
    -0.14
    ellar
    -0.14
    POSITIVE LOGITS
    ceipt
    0.15
    eder
    0.14
    omik
    0.14
    лÑİ
    0.14
     publication
    0.14
    exels
    0.14
    avigation
    0.14
    amins
    0.14
    DP
    0.14
    otte
    0.14
    Act Density 0.234%

    No Known Activations