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

    Neuronpedia

    INDEX
    Explanations

    references to attention and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RunWith
    -0.61
     den
    -0.52
    Portail
    -0.51
     numberOfRows
    -0.50
    strophy
    -0.50
    ushan
    -0.49
     meg
    -0.49
    SourceChecksum
    -0.49
     나
    -0.48
    ջ
    -0.48
    POSITIVE LOGITS
     itſelf
    0.99
     gratuits
    0.88
     metabolic
    0.81
     ſever
    0.80
     purpoſe
    0.77
     attention
    0.77
     betweenstory
    0.77
     Anſ
    0.75
     doubtnut
    0.75
     Ovid
    0.74
    Act Density 0.067%

    No Known Activations