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

    Neuronpedia

    INDEX
    Explanations

    phrases focused on various approaches to topics or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasi
    -0.17
    ovny
    -0.16
    sse
    -0.16
    arry
    -0.15
    одав
    -0.15
    oba
    -0.15
    .onView
    -0.15
    .embedding
    -0.15
    leigh
    -0.14
    -Line
    -0.14
    POSITIVE LOGITS
    ise
    0.20
     approach
    0.20
    esti
    0.17
     approached
    0.16
     style
    0.15
     finish
    0.15
     truth
    0.14
     approaches
    0.14
    weise
    0.14
     conception
    0.14
    Act Density 0.087%

    No Known Activations