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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the value and impact of written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azine
    -0.17
    _tensors
    -0.15
     overall
    -0.15
     disabled
    -0.15
    iment
    -0.15
    е
    -0.15
     inline
    -0.14
    æijĺ
    -0.14
     moral
    -0.14
    .disabled
    -0.14
    POSITIVE LOGITS
     pixels
    0.21
    Words
    0.17
    WORDS
    0.16
     hopefully
    0.16
     plá
    0.16
    steel
    0.15
     electrons
    0.15
     karÅŁ
    0.15
    pixels
    0.15
     words
    0.15
    Act Density 0.313%

    No Known Activations