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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to complex relationships and moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ActionCreators
    -0.15
    cko
    -0.15
     stake
    -0.15
    ($)
    -0.15
    ittel
    -0.15
    ivor
    -0.14
    estre
    -0.14
    adlo
    -0.14
    ạo
    -0.14
    yte
    -0.14
    POSITIVE LOGITS
    pNet
    0.15
    é¸
    0.15
     {{
    0.14
     ("
    0.14
     ([[
    0.14
     âĹ
    0.14
    PointerType
    0.13
     trope
    0.13
    пÑĢ
    0.13
    è½
    0.13
    Act Density 0.011%

    No Known Activations