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

    Neuronpedia

    INDEX
    Explanations

    elements related to organizational or structural components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zelf
    -0.22
    apses
    -0.15
    isor
    -0.15
    andalone
    -0.15
    gable
    -0.14
    /is
    -0.14
    ãĤĤ
    -0.14
    åºľ
    -0.14
    sel
    -0.14
    ugas
    -0.14
    POSITIVE LOGITS
    /-
    0.31
    ++++++++++++++++++++++++++++++++
    0.29
    ++++
    0.25
    ++↵
    0.22
    ++++++++
    0.21
    ++++++++++++++++
    0.21
    ieurs
    0.18
    holding
    0.18
     ça
    0.17
    ++.
    0.17
    Act Density 0.118%

    No Known Activations