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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "written" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogan
    -0.15
     Settlement
    -0.15
     Mud
    -0.14
    phet
    -0.14
    Äįky
    -0.14
     pump
    -0.14
    ive
    -0.14
    ropri
    -0.13
     Principal
    -0.13
     former
    -0.13
    POSITIVE LOGITS
    adu
    0.15
    bars
    0.15
    UILTIN
    0.15
    ษ
    0.15
    ãĥIJãĥ¼
    0.15
    ICENSE
    0.14
    amespace
    0.14
    shaw
    0.14
    axy
    0.14
    .googleapis
    0.14
    Act Density 0.010%

    No Known Activations