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

    Neuronpedia

    INDEX
    Explanations

    expressions of rights and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.13
    3:0.05
    4:0.07
    5:0.02
    6:0.04
    7:0.35
    8:0.03
    9:0.03
    10:0.09
    11:0.09
    Negative Logits
    effic
    -1.65
    MRI
    -1.59
    eteenth
    -1.46
    flows
    -1.41
     Faust
    -1.41
     Fernand
    -1.39
    cock
    -1.39
     revolving
    -1.35
    olved
    -1.34
    cule
    -1.32
    POSITIVE LOGITS
     Choice
    1.48
    qualified
    1.47
     Vote
    1.42
     veto
    1.41
     chance
    1.40
    Alert
    1.38
     qualified
    1.37
     qualify
    1.33
     declare
    1.32
     Quit
    1.32
    Act Density 0.004%

    No Known Activations