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

    Neuronpedia

    INDEX
    Explanations

    instances and contexts of betrayal and trust violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -span
    -0.14
    estate
    -0.14
    itas
    -0.14
    égor
    -0.14
    geb
    -0.14
    oyer
    -0.13
    ì¦Ŀ
    -0.13
    ien
    -0.13
    itate
    -0.13
    OrElse
    -0.13
    POSITIVE LOGITS
    ishes
    0.17
     const
    0.16
     prof
    0.16
    пи
    0.15
    eyer
    0.15
     conf
    0.15
     cle
    0.15
     predict
    0.15
     glob
    0.14
     origin
    0.14
    Act Density 0.032%

    No Known Activations