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

    Neuronpedia

    INDEX
    Explanations

    specific keywords or terms related to scientific papers, academic citations, or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ()]
    -0.79
     ]
    -0.76
    bufio
    -0.73
    ’”
    -0.72
    ]")]
    -0.71
     ")
    -0.71
    >");
    -0.71
     contextLoads
    -0.70
     ''
    -0.69
    UnitTesting
    -0.69
    POSITIVE LOGITS
     probably
    0.51
    ategy
    0.47
     pretty
    0.47
     somewhere
    0.47
     lunares
    0.47
    pade
    0.46
     marcadas
    0.46
    >[]
    0.45
    跡
    0.45
     Mu
    0.45
    Act Density 1.117%

    No Known Activations