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

    Neuronpedia

    INDEX
    Explanations

    instances of notable or impactful words and phrases, often related to emotional or physical experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĤ¡
    -0.15
    ancias
    -0.15
    §
    -0.15
     пÑĥÑģÑĤ
    -0.15
     attribution
    -0.14
    robat
    -0.14
     isEmpty
    -0.14
    gesch
    -0.14
     nextPage
    -0.14
    upon
    -0.14
    POSITIVE LOGITS
     attempt
    0.18
     Attempt
    0.18
     attempted
    0.18
    è¯ķ
    0.17
     attempts
    0.17
     confused
    0.16
    attempt
    0.16
    try
    0.16
     try
    0.16
    Ñĥже
    0.15
    Act Density 0.004%

    No Known Activations