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

    Neuronpedia

    INDEX
    Explanations

    phrases that express opinion or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hin
    -0.15
     rotations
    -0.14
     Force
    -0.14
     Rum
    -0.14
     carts
    -0.13
    pent
    -0.13
    rot
    -0.13
    setProperty
    -0.13
     Practice
    -0.13
    sson
    -0.13
    POSITIVE LOGITS
    och
    0.17
    /stdc
    0.16
    ediator
    0.16
    ectl
    0.15
    HandlerContext
    0.15
    Äĩi
    0.15
    erras
    0.14
     æĥħ
    0.14
    erti
    0.14
    ãĥ¼ãĥ³
    0.14
    Act Density 0.017%

    No Known Activations