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

    Neuronpedia

    INDEX
    Explanations

    references to ordinal numbers or positions within a sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.14
    1:0.18
    2:0.05
    3:0.04
    4:0.05
    5:0.18
    6:0.05
    7:0.03
    8:0.03
    9:0.06
    10:0.08
    11:0.05
    Negative Logits
    }}}
    -1.79
    RED
    -1.76
    20439
    -1.70
    Est
    -1.67
    FIN
    -1.58
    STER
    -1.57
     imag
    -1.55
    Documents
    -1.54
    Elect
    -1.53
    hered
    -1.52
    POSITIVE LOGITS
    iday
    2.03
     inning
    2.00
    undown
    1.99
     morning
    1.79
     rundown
    1.77
    ixties
    1.76
    intendent
    1.74
    imester
    1.70
     Quarter
    1.68
     afternoon
    1.68
    Act Density 0.002%

    No Known Activations