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

    Neuronpedia

    INDEX
    Explanations

    the word "para" in various contexts, indicating a focus on purpose or intention

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

    para / pour / for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.56
     fubject
    -0.52
     itſelf
    -0.52
     paff
    -0.51
     Diſ
    -0.49
     poffible
    -0.48
     Grecs
    -0.47
     Juifs
    -0.45
     Majefty
    -0.45
    acción
    -0.44
    POSITIVE LOGITS
     para
    1.25
     Para
    1.06
    Para
    1.02
     PARA
    1.02
    para
    0.98
     untuk
    0.98
     для
    0.95
    PARA
    0.87
     for
    0.85
    для
    0.85
    Act Density 0.004%

    No Known Activations