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

    Neuronpedia

    INDEX
    Explanations

    terms related to illegal immigration laws and detention criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     препратки
    -0.85
     surla
    -0.69
    Diweddarwch
    -0.68
    FactoryBean
    -0.63
     تضيفلها
    -0.63
    Pautan
    -0.60
    存于互联网档案馆
    -0.59
    ValueStyle
    -0.59
    phur
    -0.59
    Tikang
    -0.57
    POSITIVE LOGITS
     immigration
    1.82
     Immigration
    1.71
    Immigration
    1.53
     immigrant
    1.46
     immigrants
    1.46
    immigration
    1.43
     Immigrant
    1.34
     immig
    1.34
     migrant
    1.30
     Immig
    1.29
    Act Density 0.518%

    No Known Activations