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

    Neuronpedia

    INDEX
    Explanations

    phrases and transitions that introduce or reference discussions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ron
    -0.15
    RON
    -0.15
     Stuart
    -0.14
    llib
    -0.14
    à¸ķล
    -0.13
    ullan
    -0.13
     principle
    -0.13
    ÑĢап
    -0.13
    èħ¹
    -0.13
    UMB
    -0.13
    POSITIVE LOGITS
    ós
    0.15
     onAnimation
    0.15
    ema
    0.15
    ars
    0.14
    жен
    0.14
    acked
    0.14
    ettle
    0.14
    rott
    0.14
    adic
    0.14
    GRAM
    0.13
    Act Density 0.016%

    No Known Activations