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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements such as temperatures, percentages, days, and years

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or ranges related to time and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MSN
    -0.80
    hess
    -0.77
    lance
    -0.76
    Joy
    -0.76
    NAS
    -0.75
    BIL
    -0.72
    112
    -0.67
    511
    -0.67
    abol
    -0.67
    Agent
    -0.67
    POSITIVE LOGITS
    ths
    1.04
     percent
    1.04
     times
    1.00
     depending
    0.90
     thousand
    0.88
     years
    0.88
     inches
    0.86
     dozen
    0.83
     weeks
    0.83
     certs
    0.82
    Act Density 0.145%

    No Known Activations