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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the importance or significance of something

    oai_token-act-pair · gpt-3.5-turbo

    the usage of the word "much" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emy
    -0.88
    İĭ
    -0.79
    idon
    -0.75
    esome
    -0.73
    swick
    -0.72
    EStream
    -0.72
    agate
    -0.71
    atures
    -0.71
    ogens
    -0.70
    opers
    -0.70
    POSITIVE LOGITS
     ado
    0.91
     esteemed
    0.78
    NESS
    0.77
     else
    0.76
     appreciated
    0.73
     simpler
    0.70
     interest
    0.69
    body
    0.68
     hinges
    0.68
     effort
    0.67
    Act Density 0.055%

    No Known Activations