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

    Neuronpedia

    INDEX
    Explanations

    numbers representing a quantity of items or a specific count

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "10."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.76
    netflix
    -0.76
    TextColor
    -0.74
    atem
    -0.72
    rely
    -0.69
    hammad
    -0.67
    unct
    -0.66
    rette
    -0.65
    isoft
    -0.64
     tradem
    -0.64
    POSITIVE LOGITS
    %"
    0.96
    84
    0.91
    85
    0.90
    92
    0.90
    81
    0.90
    th
    0.90
    600
    0.89
    82
    0.89
    400
    0.87
    ^{
    0.87
    Act Density 0.048%

    No Known Activations