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

    Neuronpedia

    INDEX
    Explanations

    occurrences of "At" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    multiple uses of the phrase "At" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alpha
    -0.69
    clean
    -0.67
    aceutical
    -0.64
     benefited
    -0.64
    FTWARE
    -0.63
     nailed
    -0.61
    adoes
    -0.60
    tools
    -0.59
     thereof
    -0.58
    Tube
    -0.58
    POSITIVE LOGITS
     least
    1.17
    mosp
    1.06
    hens
    0.96
    kinson
    0.93
     times
    0.87
    chieve
    0.83
    ention
    0.82
    onement
    0.82
    £ı
    0.82
    roph
    0.79
    Act Density 0.059%

    No Known Activations