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

    Neuronpedia

    INDEX
    Explanations

    instances where attention is being emphasized or discussed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "attention" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     halves
    -0.78
     Yugoslavia
    -0.68
     Tale
    -0.66
     Recon
    -0.65
     Mehran
    -0.63
    tre
    -0.62
    iche
    -0.61
    tein
    -0.60
    ourke
    -0.60
     Townsend
    -0.58
    POSITIVE LOGITS
    estinal
    1.05
    orial
    0.91
    ively
    0.91
    arios
    0.88
     attention
    0.86
    atile
    0.84
     Attention
    0.79
    ibility
    0.76
     largeDownload
    0.76
    stadt
    0.76
    Act Density 0.017%

    No Known Activations