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

    Neuronpedia

    INDEX
    Explanations

    mentions related to humanitarian aid and aid workers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of aid or humanitarian assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beard
    -0.76
    theless
    -0.76
    beard
    -0.69
    agall
    -0.68
    âĸ¬
    -0.67
     Schne
    -0.66
     Coat
    -0.64
     Bellev
    -0.63
     Ran
    -0.63
    WithNo
    -0.62
    POSITIVE LOGITS
    giving
    0.95
     aid
    0.89
     convoy
    0.79
    abil
    0.78
     supplies
    0.76
     worker
    0.74
     shipments
    0.74
     recip
    0.73
    worthy
    0.73
     workers
    0.72
    Act Density 0.029%

    No Known Activations