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

    Neuronpedia

    INDEX
    Explanations

    comparisons showing a specific ratio of difference

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating quantities or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ETF
    -0.68
    Null
    -0.65
    PLA
    -0.64
    ãĥ¥
    -0.64
    éŃĶ
    -0.62
    \<
    -0.60
     Examiner
    -0.59
    ãĤº
    -0.59
     deduction
    -0.59
     Ctrl
    -0.58
    POSITIVE LOGITS
    pired
    0.93
    ylum
    0.86
    vernment
    0.82
    pires
    0.74
    phalt
    0.74
    bestos
    0.74
    pell
    0.73
    vol
    0.72
    leep
    0.71
    pire
    0.68
    Act Density 0.045%

    No Known Activations