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

    Neuronpedia

    INDEX
    Explanations

    references to flowers

    oai_token-act-pair · gpt-3.5-turbo

    references to flowers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oaded
    -0.79
    eport
    -0.78
     councill
    -0.75
    Þ
    -0.71
    ugu
    -0.71
    venants
    -0.71
    eger
    -0.69
    */(
    -0.69
    avez
    -0.69
    ufact
    -0.69
    POSITIVE LOGITS
     flowers
    1.08
     bloom
    1.08
     blo
    0.97
     flower
    0.94
     arranging
    0.92
    flower
    0.91
     Flower
    0.89
     Gardens
    0.88
     buds
    0.88
    fruit
    0.87
    Act Density 0.018%

    No Known Activations