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

    Neuronpedia

    INDEX
    Explanations

    references to sociopolitical structures and their implications on society

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

    Follows "the majority"

    np_acts-logits-general · gemini-2.0-flash

    majority discovers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сотрудни
    -0.45
     puzzled
    -0.45
     współpra
    -0.43
    IBOutlet
    -0.43
     Recovery
    -0.43
     कॉ
    -0.43
     unprofessional
    -0.42
     جدًا
    -0.42
    Split
    -0.42
     bort
    -0.42
    POSITIVE LOGITS
     defaultstate
    0.73
    0.72
    \{\\
    0.70
    LookAnd
    0.69
    Personendaten
    0.68
    InstrumentedTest
    0.68
    :✨
    0.66
     */;
    0.66
    AccessorTable
    0.64
    __':
    0.64
    Act Density 0.520%

    No Known Activations