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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "public" and its context, especially in relation to concerns or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.07
    4:0.18
    5:0.03
    6:0.04
    7:0.32
    8:0.03
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    lav
    -1.78
    veyard
    -1.59
    oother
    -1.58
     vantage
    -1.54
    pei
    -1.49
    microsoft
    -1.48
    luent
    -1.48
    ocratic
    -1.47
    isites
    -1.46
    tie
    -1.45
    POSITIVE LOGITS
     wrongdoing
    1.68
     abnorm
    1.48
     inacc
    1.48
    arthed
    1.47
    エル
    1.42
     commits
    1.40
     boldly
    1.40
    terday
    1.39
     details
    1.39
     accusations
    1.38
    Act Density 0.001%

    No Known Activations