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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to financial or administrative actions involving borrowing and expenditures

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

    ownership

    np_acts-logits-general · gemini-2.0-flash

    its and itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.83
     doInBackground
    -0.70
     fubject
    -0.68
     purpoſe
    -0.67
     Diſ
    -0.66
     himſelf
    -0.65
     Monfieur
    -0.64
     بيها
    -0.60
    Enllaces
    -0.60
    parsedMessage
    -0.56
    POSITIVE LOGITS
     itself
    1.30
     its
    1.19
     Itself
    1.00
    itself
    1.00
     Its
    0.93
    Its
    0.87
     themselves
    0.76
     ihren
    0.72
    在其
    0.71
    its
    0.68
    Act Density 0.881%

    No Known Activations