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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'attention'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.78
    (!__
    -0.75
    mybatisplus
    -0.74
     oorsp
    -0.71
     précédents
    -0.71
     Füße
    -0.69
     Wadsworth
    -0.68
    raborty
    -0.68
    enschaften
    -0.67
     recensement
    -0.67
    POSITIVE LOGITS
     attention
    3.04
     Attention
    2.74
    attention
    2.56
    Attention
    2.48
     ATTENTION
    2.39
     attentions
    1.96
    ATTENTION
    1.85
     atención
    1.65
     aten
    1.59
     atenção
    1.56
    Act Density 0.063%

    No Known Activations