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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chrétien
    -0.54
    gjenge
    -0.49
     judiciaire
    -0.46
     feroit
    -0.46
    ïsme
    -0.45
     auroit
    -0.45
     ſever
    -0.45
     Conſ
    -0.45
     húmedo
    -0.45
     anſ
    -0.44
    POSITIVE LOGITS
     của
    1.14
    ของ
    0.93
     ของ
    0.81
    ủa
    0.75
     cua
    0.74
    enumi
    0.69
    Clik
    0.69
     של
    0.68
     OF
    0.65
     of
    0.62
    Act Density 0.000%

    No Known Activations