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

    Neuronpedia

    INDEX
    Explanations

    references to specific figures of authority or leadership in a religious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.20
    3:0.06
    4:0.15
    5:0.04
    6:0.13
    7:0.06
    8:0.05
    9:0.05
    10:0.06
    11:0.09
    Negative Logits
     ACTIONS
    -1.68
    Interstitial
    -1.60
    sth
    -1.51
     Definitions
    -1.49
    sg
    -1.49
     anten
    -1.44
    mental
    -1.43
     confidentiality
    -1.41
     approval
    -1.40
     mant
    -1.39
    POSITIVE LOGITS
    pires
    1.83
    iasco
    1.66
    htaking
    1.55
    udi
    1.51
    leans
    1.50
    chuk
    1.39
    ovych
    1.38
    iewicz
    1.38
    agan
    1.34
    achev
    1.33
    Act Density 0.000%

    No Known Activations