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

    Neuronpedia

    INDEX
    Explanations

    references to migrants and their experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to migrants and migration issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rah
    -0.75
    EXT
    -0.70
    INA
    -0.69
    NESS
    -0.67
    Sensor
    -0.67
    ventory
    -0.65
    MOD
    -0.65
    REE
    -0.65
    POSE
    -0.64
    efer
    -0.64
    POSITIVE LOGITS
     migrants
    1.31
     migrant
    1.14
     Refugees
    0.98
     refugees
    0.97
    igrants
    0.92
    ugg
    0.85
     smugglers
    0.84
    interstitial
    0.83
     fleeing
    0.82
    ploy
    0.80
    Act Density 0.013%

    No Known Activations