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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and interactions between people or entities

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

    與, 他, 相, 与 / with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fubject
    -0.73
     ſta
    -0.71
    ſelf
    -0.69
     ſche
    -0.66
     poffe
    -0.65
     anſ
    -0.64
     myſelf
    -0.62
     ſtate
    -0.61
     poffible
    -0.61
     perſon
    -0.61
    POSITIVE LOGITS
    与
    1.54
     与
    1.33
    與
    1.27
     與
    1.05
    与其
    0.63
    与此
    0.60
    就跟
    0.56
    人と
    0.55
    with
    0.55
    跟
    0.54
    Act Density 0.001%

    No Known Activations