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

    Neuronpedia

    INDEX
    Explanations

    numbers related to the value 90

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 90 across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    board
    -0.70
    lay
    -0.69
    gets
    -0.67
    teen
    -0.66
    untu
    -0.65
    wan
    -0.64
    holder
    -0.63
    folk
    -0.62
    sworth
    -0.62
    maid
    -0.61
    POSITIVE LOGITS
    %
    1.23
    %:
    1.18
    %"
    1.13
    %;
    1.11
     percent
    1.10
    %,
    1.08
    %-
    1.08
    %.
    1.04
    %),
    0.98
    %)
    0.98
    Act Density 0.086%

    No Known Activations