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

    Neuronpedia

    INDEX
    Explanations

    mentions of activities or items related to gardening

    oai_token-act-pair · gpt-3.5-turbo

    references to gardens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sem
    -0.70
    ccording
    -0.65
    utan
    -0.64
    esty
    -0.63
    uum
    -0.63
    andem
    -0.63
    nm
    -0.62
    ictional
    -0.62
     derail
    -0.61
    profits
    -0.61
    POSITIVE LOGITS
     garden
    1.15
     gardens
    1.14
     gardening
    0.99
     Garden
    0.93
     gard
    0.89
     Gardens
    0.89
     Eden
    0.85
    keeper
    0.82
     patio
    0.80
     lett
    0.80
    Act Density 0.006%

    No Known Activations