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

    Neuronpedia

    INDEX
    Explanations

    words related to roles, titles, or states of being

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

    assumption of office, tenure, mentor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ckså
    -0.51
    anghai
    -0.46
     policiers
    -0.45
     Agassi
    -0.44
     Grecs
    -0.42
     escar
    -0.42
     Griswold
    -0.42
     Coppola
    -0.41
    phoneNumber
    -0.40
    fileId
    -0.40
    POSITIVE LOGITS
    任
    2.25
     任
    1.77
     임
    0.92
    임
    0.91
    担任
    0.81
     Ren
    0.77
    擔任
    0.75
    就任
    0.75
     nhiệm
    0.66
    Ren
    0.65
    Act Density 0.001%

    No Known Activations