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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals in positions of power or influence

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

    people or roles and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bred
    -0.52
    TagMode
    -0.47
    ival
    -0.47
    ineſs
    -0.47
    irmar
    -0.46
    yant
    -0.46
    bilità
    -0.46
    liability
    -0.46
    ineda
    -0.45
     sumpay
    -0.45
    POSITIVE LOGITS
     ivelany
    0.45
     otomatig
    0.44
    WithIOException
    0.38
    didSet
    0.37
    RTHOOK
    0.34
    참고
    0.33
     crimen
    0.33
    enumii
    0.32
    styleType
    0.31
    :][
    0.31
    Act Density 0.091%

    No Known Activations