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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political power dynamics and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.30
    1:0.02
    2:0.27
    3:0.07
    4:0.03
    5:0.04
    6:0.02
    7:0.04
    8:0.03
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
    eeds
    -2.73
     Plot
    -2.66
    Stat
    -2.63
     plots
    -2.59
     Cipher
    -2.52
    yton
    -2.52
    atana
    -2.47
    Points
    -2.41
    bold
    -2.39
    eed
    -2.37
    POSITIVE LOGITS
     vacuum
    5.21
     Vac
    4.05
     vacancy
    3.84
     vac
    3.77
     vacancies
    3.32
     cleaners
    3.16
     emptied
    3.13
     vacated
    3.12
     expel
    3.03
    uum
    2.92
    Act Density 0.000%

    No Known Activations