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

    Neuronpedia

    INDEX
    Explanations

    instances of hypocrisy and self-contradictory behavior in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikes
    -0.17
    çĸ
    -0.14
    erdale
    -0.14
     Tru
    -0.14
    aghan
    -0.14
     kå
    -0.14
     SETTINGS
    -0.13
     perg
    -0.13
     Elem
    -0.13
    pecting
    -0.13
    POSITIVE LOGITS
    nun
    0.15
    ouro
    0.15
     éħ
    0.15
     Celt
    0.14
    adil
    0.14
    essel
    0.14
    obus
    0.14
    Vision
    0.14
    ause
    0.14
    aste
    0.14
    Act Density 0.295%

    No Known Activations