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

    Neuronpedia

    INDEX
    Explanations

    references to historical time periods and chronological markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.07
    3:0.06
    4:0.10
    5:0.04
    6:0.08
    7:0.09
    8:0.08
    9:0.04
    10:0.10
    11:0.25
    Negative Logits
     Autob
    -1.57
     Santiago
    -1.56
    BUS
    -1.54
     transistor
    -1.53
     Mitch
    -1.51
     Booker
    -1.50
     minds
    -1.50
     Lear
    -1.49
    ERN
    -1.48
     polio
    -1.48
    POSITIVE LOGITS
    ocrin
    1.78
    ascular
    1.74
    */(
    1.65
    artments
    1.65
     exemption
    1.62
     indemn
    1.59
     Marketable
    1.59
     clipping
    1.59
    osponsors
    1.57
    ony
    1.54
    Act Density 0.001%

    No Known Activations