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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases associated with conflict, action, and attempts at change or influence

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

    pursuit of power or goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.69
    awtextra
    -0.60
    IContainer
    -0.59
    ArgsConstructor
    -0.56
    setopt
    -0.54
     OnTrigger
    -0.52
     nonUne
    -0.52
    sistor
    -0.49
     lenker
    -0.48
    iſen
    -0.48
    POSITIVE LOGITS
     objetivo
    0.42
     wants
    0.40
     désir
    0.39
     فريبيس
    0.38
    的目标
    0.37
     mục
    0.36
     goal
    0.36
     olmak
    0.35
     wollen
    0.35
     obiettivi
    0.35
    Act Density 0.108%

    No Known Activations