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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.39
    3:0.04
    4:0.02
    5:0.03
    6:0.04
    7:0.03
    8:0.04
    9:0.03
    10:0.16
    11:0.03
    Negative Logits
     cf
    -2.47
     breaths
    -2.26
     Hib
    -2.23
     Cosponsors
    -2.21
     \'
    -2.20
    �
    -2.20
    �士
    -2.17
     Peb
    -2.15
    cffff
    -2.14
    IB
    -2.04
    POSITIVE LOGITS
    on
    3.21
    ron
    2.57
    iton
    2.51
     Lon
    2.46
    ON
    2.46
    ons
    2.43
    tor
    2.43
    eon
    2.37
    abin
    2.36
    serial
    2.35
    Act Density 0.001%

    No Known Activations