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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "urban" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to urban areas or related geographical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.86
    aurus
    -0.80
    creen
    -0.80
    prus
    -0.72
    rehensive
    -0.67
    ertodd
    -0.67
    lder
    -0.66
    ppo
    -0.66
    CHR
    -0.65
    paio
    -0.64
    POSITIVE LOGITS
    urb
    1.01
    ulent
    0.90
    ulence
    0.89
    abies
    0.86
    inson
    0.86
    inator
    0.81
    inators
    0.80
    icz
    0.75
    yrinth
    0.74
    orph
    0.74
    Act Density 0.022%

    No Known Activations