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

    Neuronpedia

    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to large numerical values or statistics, particularly in the millions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queues
    -0.86
     histories
    -0.81
    ties
    -0.78
     angles
    -0.78
    casts
    -0.74
     forks
    -0.73
     lows
    -0.72
     highs
    -0.72
     ages
    -0.71
     fences
    -0.71
    POSITIVE LOGITS
    st
    1.28
    Password
    1.23
    125
    1.08
    120
    0.96
    ½
    0.96
    âģ
    0.85
    123
    0.84
    128
    0.84
    RM
    0.83
     kilomet
    0.82
    Act Density 0.070%

    No Known Activations