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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate private ownership or privately held entities

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

    privately, secretly, internally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    -0.49
    шеб
    -0.46
    lccn
    -0.45
     Hodge
    -0.45
     שוליים
    -0.43
    IFICATE
    -0.43
    Honorable
    -0.43
     Pardo
    -0.42
     those
    -0.42
     Hamburg
    -0.41
    POSITIVE LOGITS
     privately
    1.80
     Priv
    1.09
    Priv
    1.05
    priv
    0.99
     secretly
    0.81
     independently
    0.77
     publicly
    0.71
     inwardly
    0.71
     internally
    0.71
     informally
    0.68
    Act Density 0.007%

    No Known Activations