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

    Neuronpedia

    INDEX
    Explanations

    references to societal roles and expectations, particularly regarding behavior and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affichés
    -0.57
     vPvB
    -0.51
     augmenté
    -0.50
    ∬
    -0.49
    tensive
    -0.48
    Tbh
    -0.48
     rencontré
    -0.48
     fiquei
    -0.48
    éroport
    -0.47
     pled
    -0.47
    POSITIVE LOGITS
     life
    1.19
     humanity
    1.05
     nature
    0.99
     civilization
    0.91
     mankind
    0.90
     civilisation
    0.89
     society
    0.86
     humankind
    0.85
     everything
    0.84
     fate
    0.81
    Act Density 0.845%

    No Known Activations