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

    Neuronpedia

    INDEX
    Explanations

    terms related to controversial or illicit actions, such as land grabs, cherry-picking, power grabs, and spying

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "land grabs," manipulation, and governmental overreach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellar
    -0.72
    alg
    -0.69
    birth
    -0.68
    cit
    -0.68
    ube
    -0.67
    reci
    -0.65
    cil
    -0.65
    ale
    -0.64
     latch
    -0.64
    Lear
    -0.64
    POSITIVE LOGITS
     perpetrated
    1.22
     tactics
    1.09
     spree
    1.00
     targeting
    0.96
     crimes
    0.85
     retaliation
    0.81
     tactic
    0.80
    ionage
    0.79
     scandals
    0.79
     schemes
    0.79
    Act Density 0.225%

    No Known Activations