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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or attribution to actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     málo
    -0.16
    empo
    -0.16
    amiliar
    -0.15
    nelly
    -0.15
    ibrary
    -0.15
    irit
    -0.14
    ively
    -0.14
    KeySpec
    -0.14
    å¿Ļ
    -0.14
     доÑĢ
    -0.14
    POSITIVE LOGITS
    -products
    0.25
     means
    0.24
    products
    0.21
    gone
    0.20
     chance
    0.20
    -election
    0.20
     virtue
    0.20
    /on
    0.19
    rne
    0.18
    voor
    0.17
    Act Density 0.316%

    No Known Activations