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

    Neuronpedia

    INDEX
    Explanations

    mentions of vouchers or related terms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    voucher, voxel, veneer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    -0.44
    seems
    -0.42
    as
    -0.41
     Desarrollo
    -0.40
    in
    -0.39
    III
    -0.39
     właści
    -0.38
    <eos>
    -0.38
    Hi
    -0.38
    ↵↵↵↵↵
    -0.37
    POSITIVE LOGITS
     voucher
    2.33
     Voucher
    2.27
     vouchers
    2.14
    ouchers
    2.05
    Voucher
    2.02
    voucher
    1.94
     coupon
    1.29
     coupons
    1.27
     Coupon
    1.22
     vouch
    1.19
    Act Density 0.000%

    No Known Activations