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

    Neuronpedia

    INDEX
    Explanations

    statements involving controversial or sensitive political topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èļ
    -0.17
    TION
    -0.16
    alar
    -0.15
     Slut
    -0.14
    legates
    -0.14
    ault
    -0.14
     Britt
    -0.14
    oms
    -0.14
    cheon
    -0.14
    ura
    -0.14
    POSITIVE LOGITS
    ench
    0.15
     Johns
    0.14
    Portal
    0.14
    ogonal
    0.14
    erver
    0.13
     Sources
    0.13
    dater
    0.13
     Hoe
    0.13
    enna
    0.13
    íĥĪ
    0.13
    Act Density 0.031%

    No Known Activations