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

    Neuronpedia

    INDEX
    Explanations

    references to authority or positions of power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.32
    1:0.13
    2:0.04
    3:0.04
    4:0.02
    5:0.14
    6:0.07
    7:0.01
    8:0.05
    9:0.07
    10:0.03
    11:0.03
    Negative Logits
     princ
    -1.58
    VIDIA
    -1.45
     withdrawals
    -1.43
     capt
    -1.43
    INGTON
    -1.39
    TextColor
    -1.38
     CS
    -1.36
     ste
    -1.34
     elev
    -1.34
     cartoon
    -1.33
    POSITIVE LOGITS
    .,
    1.84
    friends
    1.74
    aea
    1.71
    aceae
    1.69
    ema
    1.68
    yne
    1.64
    ngth
    1.64
    iour
    1.63
    -.
    1.62
    forums
    1.61
    Act Density 0.039%

    No Known Activations