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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sanctuary cities

    oai_token-act-pair · gpt-3.5-turbo

    references to "sanctuary" and related policies or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahon
    -0.95
    ONES
    -0.83
    agher
    -0.75
    agers
    -0.74
    thin
    -0.73
    inness
    -0.72
    PUT
    -0.69
    drivers
    -0.69
    olf
    -0.68
    uscript
    -0.68
    POSITIVE LOGITS
    ctuary
    1.41
     sanctuary
    1.14
     Sanctuary
    0.93
     havens
    0.85
     jurisdictions
    0.82
    keeper
    0.73
     refuge
    0.71
     keeper
    0.70
     harbor
    0.69
    peace
    0.68
    Act Density 0.007%

    No Known Activations