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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly focusing on the number 90

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seeing
    -0.83
    lay
    -0.77
    untu
    -0.72
    wan
    -0.72
    pocket
    -0.72
    think
    -0.70
    cles
    -0.70
    lish
    -0.68
    wered
    -0.66
     RTX
    -0.64
    POSITIVE LOGITS
    %"
    1.03
    %
    0.98
     percent
    0.98
    %:
    0.94
     ILCS
    0.94
    °
    0.94
    º
    0.93
     degrees
    0.92
     mph
    0.88
    %;
    0.86
    Act Density 0.031%

    No Known Activations