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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a reply or reaction related to requests or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    in response to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Constitucional
    -0.59
     constitucional
    -0.50
    eterangan
    -0.47
     administratif
    -0.45
     Constitutional
    -0.45
    MessageOf
    -0.44
    AllAfrica
    -0.43
     institucional
    -0.43
     mensaj
    -0.42
     Rockefeller
    -0.42
    POSITIVE LOGITS
    __(/*!
    0.64
     estekak
    0.56
    dientemente
    0.50
     behalf
    0.49
     sumpay
    0.47
    CascadeType
    0.47
    OGND
    0.45
     accordance
    0.44
     spite
    0.44
    Rüyada
    0.44
    Act Density 0.045%

    No Known Activations