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

    Neuronpedia

    INDEX
    Explanations

    time-related information, particularly focusing on mentions of recent months and years and changes over time

    oai_token-act-pair · gpt-3.5-turbo

    references to recent economic trends and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -1.05
     oath
    -0.79
    Ĥ¬
    -0.75
    anamo
    -0.64
    eatured
    -0.63
    anners
    -0.62
    pired
    -0.61
    hid
    -0.61
    iris
    -0.61
    enko
    -0.60
    POSITIVE LOGITS
     due
    1.01
     thanks
    0.99
     owing
    0.98
     compared
    0.94
     lows
    0.91
     amid
    0.90
    thanks
    0.88
    flation
    0.88
     (âĪĴ
    0.87
     (%
    0.85
    Act Density 0.306%

    No Known Activations