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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fear and control tactics in a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zvuky
    -0.52
     roze
    -0.44
    ########.
    -0.42
     Pflicht
    -0.41
    TAIN
    -0.40
     tốc
    -0.39
     consommation
    -0.38
    '];?>
    -0.38
     fæ
    -0.38
     recherche
    -0.38
    POSITIVE LOGITS
     deterrent
    0.76
     coercive
    0.75
     coercion
    0.70
     deterrence
    0.70
     dissu
    0.66
     scare
    0.66
    TypedDataSet
    0.66
     deterred
    0.66
     relâche
    0.64
     intimidation
    0.64
    Act Density 0.304%

    No Known Activations