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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to assertions or statements of fact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     writ
    -0.16
     наÑĤ
    -0.16
    RunLoop
    -0.15
    mailto
    -0.14
    ildo
    -0.14
    airo
    -0.14
    aÄį
    -0.14
    halb
    -0.14
    oblin
    -0.14
    каз
    -0.14
    POSITIVE LOGITS
     cock
    0.18
    uh
    0.17
    apr
    0.16
     cockpit
    0.16
    ICO
    0.15
    alth
    0.14
    mdl
    0.14
    007
    0.14
    idot
    0.14
    sut
    0.14
    Act Density 0.043%

    No Known Activations