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
    nesota
    -0.76
    gregation
    -0.75
     unden
    -0.75
    lde
    -0.70
    Þ
    -0.66
    ulhu
    -0.64
    ormons
    -0.64
    resy
    -0.63
     Rapp
    -0.63
    redit
    -0.62
    POSITIVE LOGITS
     bloom
    1.02
    pots
    1.02
     arranging
    0.97
     buds
    0.97
     blo
    0.96
     flowers
    0.92
    flower
    0.90
     gardens
    0.88
    fruit
    0.85
     Gardens
    0.85
    Act Density 0.038%

    No Known Activations