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

    Neuronpedia

    INDEX
    Explanations

    indicators of social welfare and assistance programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĭĹ
    -0.16
     Tato
    -0.16
     bubble
    -0.16
    bubble
    -0.15
     Bubble
    -0.15
    Bubble
    -0.15
    SystemService
    -0.15
     derec
    -0.14
     Seat
    -0.14
    aylor
    -0.14
    POSITIVE LOGITS
     SNAP
    0.39
    _snap
    0.30
     snap
    0.29
     Snap
    0.29
    SN
    0.28
     food
    0.28
    .snap
    0.28
    Snap
    0.26
     welfare
    0.26
    snap
    0.25
    Act Density 0.025%

    No Known Activations