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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a part of a series or list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    layoutManager
    -0.69
    versy
    -0.65
    "?>
    -0.62
     haw
    -0.59
     kasa
    -0.58
    volts
    -0.58
    ynie
    -0.58
     ADM
    -0.57
     sauer
    -0.57
    〗
    -0.57
    POSITIVE LOGITS
     Protobuf
    0.69
     toilettes
    0.67
    matchCondition
    0.65
     član
    0.65
    [{
    0.65
     two
    0.65
     acestei
    0.64
     två
    0.63
     unei
    0.63
     beiden
    0.63
    Act Density 0.118%

    No Known Activations