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

    Neuronpedia

    INDEX
    Explanations

    financial figures and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.21
    1:0.31
    2:0.03
    3:0.03
    4:0.03
    5:0.14
    6:0.02
    7:0.01
    8:0.07
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
     seiz
    -2.23
     Authors
    -2.02
    bush
    -1.99
     Ambro
    -1.87
     Surviv
    -1.77
     Place
    -1.76
     behav
    -1.76
     Views
    -1.73
    yout
    -1.70
     srfAttach
    -1.70
    POSITIVE LOGITS
    の魔
    2.55
     310
    2.38
    ��士
    2.37
     370
    2.35
     325
    2.29
     330
    2.28
    330
    2.25
     321
    2.24
     295
    2.16
     320
    2.14
    Act Density 0.034%

    No Known Activations