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

    Neuronpedia

    INDEX
    Explanations

    references to financial bonuses or compensation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.09
    3:0.05
    4:0.07
    5:0.06
    6:0.12
    7:0.05
    8:0.07
    9:0.20
    10:0.06
    11:0.04
    Negative Logits
    elling
    -3.02
    е
    -2.93
    abel
    -2.84
     Reynolds
    -2.74
    ̶
    -2.69
     phys
    -2.65
     Frag
    -2.64
     Origin
    -2.61
    nes
    -2.54
     Jensen
    -2.54
    POSITIVE LOGITS
     Bonus
    5.45
     bonuses
    5.33
     bonus
    5.13
    Bonus
    4.69
     (+
    3.45
    trap
    3.41
    Thu
    3.29
     additive
    3.20
     Trap
    3.16
    Balt
    3.16
    Act Density 0.002%

    No Known Activations