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

    Neuronpedia

    INDEX
    Explanations

    patterns of prepositions and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.69
     a
    -0.57
    And
    -0.52
     precum
    -0.51
    ing
    -0.50
     partea
    -0.49
     And
    -0.49
    distas
    -0.48
    cznego
    -0.48
     esplor
    -0.47
    POSITIVE LOGITS
    UIControlState
    1.00
     betweenstory
    0.89
    [::-
    0.85
     GenerationType
    0.82
    ]='\
    0.81
    ждый
    0.80
    Externé
    0.80
    SEGUIR
    0.78
     Мексичка
    0.75
    iffance
    0.75
    Act Density 0.319%

    No Known Activations