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

    Neuronpedia

    INDEX
    Explanations

    references to places identified as sanctuary cities

    oai_token-act-pair · gpt-3.5-turbo

    references to sanctuary cities and related policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahon
    -0.94
    ONES
    -0.80
    thin
    -0.75
    agers
    -0.75
    agher
    -0.70
    inness
    -0.69
    enges
    -0.67
    eq
    -0.67
    liam
    -0.66
    olf
    -0.66
    POSITIVE LOGITS
    ctuary
    1.25
     sanctuary
    1.01
     Sanctuary
    0.83
     jurisdictions
    0.77
     havens
    0.73
    keeper
    0.68
     harbor
    0.67
     keeper
    0.66
    ility
    0.66
    adelphia
    0.65
    Act Density 0.011%

    No Known Activations