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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantitative analysis and statistical interpretation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _LP
    -0.16
     whose
    -0.14
    ÈĽ
    -0.14
    desc
    -0.14
    ţ
    -0.14
    /if
    -0.14
    whose
    -0.13
     inconsistency
    -0.13
     inconsistencies
    -0.13
    airo
    -0.13
    POSITIVE LOGITS
     fact
    0.45
    fact
    0.37
     lack
    0.33
     absence
    0.29
     amount
    0.28
    Fact
    0.28
     presence
    0.27
    lack
    0.27
     size
    0.25
     rarity
    0.25
    Act Density 0.435%

    No Known Activations