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

    Neuronpedia

    INDEX
    Explanations

    references to studies or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /apis
    -0.16
    .timeScale
    -0.15
    ë¹
    -0.15
    makta
    -0.14
    orate
    -0.14
    viron
    -0.14
    craft
    -0.13
    ãģĨãĤĵ
    -0.13
    gency
    -0.13
    ÑĢави
    -0.13
    POSITIVE LOGITS
    riot
    0.14
     swept
    0.14
     thought
    0.13
     egret
    0.13
    istrar
    0.13
     viz
    0.13
    ead
    0.13
     log
    0.13
     Waters
    0.13
     Log
    0.13
    Act Density 0.022%

    No Known Activations