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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critical health and safety issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵn
    -0.17
    /html
    -0.15
     Contemporary
    -0.15
     Fro
    -0.15
    aria
    -0.14
    zim
    -0.14
    anyl
    -0.14
     Ferd
    -0.14
    yas
    -0.14
    dorf
    -0.14
    POSITIVE LOGITS
     medic
    0.15
    775
    0.15
     multic
    0.15
    MeasureSpec
    0.14
     desirable
    0.14
    AIL
    0.14
    239
    0.14
    iec
    0.13
    abee
    0.13
    velle
    0.13
    Act Density 0.242%

    No Known Activations