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

    Neuronpedia

    INDEX
    Explanations

    percentage-related phrases and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.15
    reh
    -0.14
    ternal
    -0.14
    iÃŁ
    -0.14
    onom
    -0.14
    chter
    -0.14
    ours
    -0.14
    king
    -0.14
    ische
    -0.14
    ger
    -0.13
    POSITIVE LOGITS
     majority
    0.23
     Majority
    0.18
    éºĹ
    0.16
    Sizer
    0.15
    licken
    0.15
    OSC
    0.14
    ppv
    0.14
     every
    0.13
     none
    0.13
     Barton
    0.13
    Act Density 0.081%

    No Known Activations