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

    Neuronpedia

    INDEX
    Explanations

    numeric values and measurements of quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hundred" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Nav
    -0.69
    HAM
    -0.68
    obal
    -0.68
    NetMessage
    -0.65
    Land
    -0.63
    kamp
    -0.63
    udic
    -0.63
    Screen
    -0.62
    Bind
    -0.62
    estine
    -0.61
    POSITIVE LOGITS
     thousand
    1.37
    ousand
    1.05
    ths
    1.04
     dollars
    1.02
     metres
    0.98
     Thousand
    0.98
     eighty
    0.97
     pounds
    0.95
    eenth
    0.94
     fifty
    0.92
    Act Density 0.045%

    No Known Activations