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

    Neuronpedia

    INDEX
    Explanations

    references to political statements and documents, particularly those related to public figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.02
    2:0.04
    3:0.50
    4:0.02
    5:0.10
    6:0.02
    7:0.03
    8:0.03
    9:0.02
    10:0.07
    11:0.01
    Negative Logits
     predators
    -2.28
    zees
    -2.05
    ampires
    -1.96
     sheltered
    -1.95
     extremes
    -1.94
     vampires
    -1.93
     fortunate
    -1.93
     suburbs
    -1.93
     advant
    -1.93
     disadvantaged
    -1.92
    POSITIVE LOGITS
     manifesto
    3.62
     transcript
    3.39
     article
    3.33
    Letter
    3.30
     pamphlet
    3.27
     document
    3.19
     booklet
    3.16
     Declaration
    3.12
     manuscript
    3.06
     dossier
    3.04
    Act Density 1.934%

    No Known Activations