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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to interpretation and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isms
    -0.15
    edik
    -0.15
    ed
    -0.15
    urally
    -0.14
    wheel
    -0.14
    usercontent
    -0.14
    nings
    -0.14
     wheel
    -0.14
    (
    -0.14
    igu
    -0.14
    POSITIVE LOGITS
    ation
    1.12
    ations
    0.79
    ATION
    0.72
    ATIONS
    0.50
    ational
    0.43
    ación
    0.43
    atio
    0.41
    à¥ĩशन
    0.41
    ationToken
    0.40
    acion
    0.40
    Act Density 0.110%

    No Known Activations