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

    Neuronpedia

    INDEX
    Explanations

    details related to safety and accessibility at a venue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruk
    -0.14
    ilit
    -0.14
    lingen
    -0.13
    âr
    -0.13
    ZN
    -0.13
     ting
    -0.13
     ComVisible
    -0.13
    znik
    -0.13
    istr
    -0.13
     thanks
    -0.13
    POSITIVE LOGITS
     unless
    0.19
    unless
    0.19
    Unless
    0.17
     Unless
    0.16
    ein
    0.16
    èİ«
    0.16
     if
    0.15
     yourself
    0.15
    IENTATION
    0.15
    άÏĤ
    0.14
    Act Density 0.160%

    No Known Activations