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

    Neuronpedia

    INDEX
    Explanations

    patterns of repetitive phrases or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    polymers-08-00159

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Вікіпе
    -0.40
    ":[{
    -0.38
    ))),
    -0.34
    ">//
    -0.34
    }>{
    -0.33
    有一种
    -0.33
     always
    -0.33
    ESOME
    -0.31
    yelidikan
    -0.31
     naturally
    -0.31
    POSITIVE LOGITS
     betweenstory
    0.57
     utafitiHapana
    0.56
    August
    0.55
     Савезне
    0.53
    sidemargin
    0.52
    parsedMessage
    0.52
     transfieras
    0.52
    SharedDtor
    0.52
     axio
    0.50
     Augustus
    0.50
    Act Density 0.017%

    No Known Activations