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

    Neuronpedia

    INDEX
    Explanations

    instances of the author discussing their writing process in real-time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rub
    -0.15
     Buck
    -0.14
    gren
    -0.14
    士
    -0.14
     Status
    -0.14
    383
    -0.14
     tre
    -0.14
    annes
    -0.14
     bad
    -0.14
    478
    -0.13
    POSITIVE LOGITS
    argon
    0.16
    æĴ°
    0.16
    argo
    0.16
     Äijang
    0.15
     Leer
    0.15
    .synthetic
    0.15
    .scalablytyped
    0.15
    äºŃ
    0.14
     writing
    0.14
    мÑĸн
    0.14
    Act Density 0.096%

    No Known Activations