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

    Neuronpedia

    INDEX
    Explanations

    instances where attention is being paid or drawn to specific subjects or details

    oai_token-act-pair · gpt-3.5-turbo

    references to attention and its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lins
    -0.67
     Tale
    -0.66
    nia
    -0.65
     Rebell
    -0.61
     Tycoon
    -0.61
    mos
    -0.61
     Mehran
    -0.60
     testament
    -0.60
     Vers
    -0.60
    ston
    -0.59
    POSITIVE LOGITS
     spans
    1.14
     span
    1.12
     attention
    0.92
     gaze
    0.82
    orial
    0.80
     scrutiny
    0.77
     grabbing
    0.77
    grab
    0.77
     Attention
    0.76
     seekers
    0.74
    Act Density 0.035%

    No Known Activations