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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.02
    3:0.06
    4:0.10
    5:0.07
    6:0.03
    7:0.01
    8:0.06
    9:0.43
    10:0.02
    11:0.01
    Negative Logits
     Annotations
    -2.38
    Located
    -2.32
    Afee
    -2.25
    ori
    -2.13
     Usually
    -2.13
    Usually
    -2.04
    folios
    -2.01
     usually
    -2.01
     Probably
    -2.01
     Estimates
    -2.01
    POSITIVE LOGITS
     somehow
    2.53
     sufficiently
    2.53
     someday
    2.52
     pans
    2.33
     succeeds
    2.29
     fails
    2.27
     materially
    2.13
    pires
    2.13
     weren
    2.08
     bothers
    2.05
    Act Density 0.316%

    No Known Activations