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

    Neuronpedia

    INDEX
    Explanations

    numerical values or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stewards
    -0.79
     inform
    -0.71
     fundament
    -0.71
    */(
    -0.70
     melanch
    -0.69
     greeting
    -0.68
     scrut
    -0.68
    ĪĴ
    -0.67
     coh
    -0.67
     eclectic
    -0.67
    POSITIVE LOGITS
    ±
    0.84
     TOTAL
    0.84
    Total
    0.79
    total
    0.79
    mean
    0.78
    6666
    0.77
     Total
    0.72
    States
    0.69
     Avg
    0.69
    "></
    0.68
    Act Density 0.156%

    No Known Activations