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

    Neuronpedia

    INDEX
    Explanations

    expressions related to decision-making, regulation, and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.81
     дописавши
    -0.63
     <<<<<<<<<<<<<<
    -0.56
     accordingly
    -0.53
    […]
    -0.53
    ).
    -0.53
    ….
    -0.52
     avancée
    -0.52
     appunto
    -0.51
     européens
    -0.51
    POSITIVE LOGITS
    tvguidetime
    0.79
     betweenstory
    0.78
     Мексичка
    0.77
    ChildScrollView
    0.74
    ########.
    0.74
     MainAxisSize
    0.69
    Архівовано
    0.65
     Saltar
    0.62
    出版年
    0.61
     GenerationType
    0.61
    Act Density 1.421%

    No Known Activations