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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases emphasizing the word "always" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uestamente
    -0.72
     Efq
    -0.70
     вікі
    -0.69
     Савезне
    -0.67
    addContainerGap
    -0.67
     Skipper
    -0.66
     Patro
    -0.65
     papyrus
    -0.63
     Cocktails
    -0.63
     hierogly
    -0.63
    POSITIVE LOGITS
    kháu
    0.64
     came
    0.55
     became
    0.53
     grew
    0.50
     geldig
    0.50
     пришел
    0.49
     and
    0.49
    Histoire
    0.48
    Історія
    0.48
    Growing
    0.48
    Act Density 0.148%

    No Known Activations