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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with punctuation common in coding, like periods, commas, and paragraph separators

    oai_token-act-pair · gpt-3.5-turbo

    instances of statistical information or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.81
     directly
    -0.72
     promptly
    -0.69
     expressly
    -0.68
     tradem
    -0.66
     exclusively
    -0.65
     due
    -0.64
     furnished
    -0.64
    hement
    -0.64
    uling
    -0.63
    POSITIVE LOGITS
    Anonymous
    0.99
    Each
    0.91
    Advertisement
    0.90
    Yet
    0.89
    Newsletter
    0.87
    Eventually
    0.87
    Suddenly
    0.87
    Often
    0.87
    Except
    0.86
    Every
    0.86
    Act Density 0.488%

    No Known Activations