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

    Neuronpedia

    INDEX
    Explanations

    words related to physical structures or locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "garden" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.70
    aunder
    -0.70
    atility
    -0.68
    EStream
    -0.68
    udeau
    -0.67
    ilion
    -0.67
    udge
    -0.66
    uled
    -0.66
    urgical
    -0.65
    atile
    -0.65
    POSITIVE LOGITS
    arden
    0.82
    yll
    0.80
    eering
    0.78
    IOR
    0.77
     Adidas
    0.77
     Lauder
    0.74
    bats
    0.73
    ccoli
    0.72
     Melody
    0.72
    ly
    0.69
    Act Density 0.034%

    No Known Activations