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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.77
     purpoſe
    -0.77
     pleaſure
    -0.72
     Monfieur
    -0.71
     Perſ
    -0.70
     raiſ
    -0.68
     Theſe
    -0.68
     ―――――
    -0.67
     Majefty
    -0.67
     ſtate
    -0.65
    POSITIVE LOGITS
     в
    1.43
     у
    0.92
     ў
    0.92
    В
    0.90
     В
    0.89
     في
    0.87
    Trong
    0.85
     във
    0.85
     în
    0.83
     trong
    0.82
    Act Density 0.028%

    No Known Activations